worldbench/awesome-ai-auto-research

🔥 A Survey on AI Auto-Research

HTML

530

26 commits

updated Sep 1, 2026

worldbench.github.io/awesome-ai-auto-research

See the code

README

:sunglasses: Awesome AI Auto-Research

This repository accompanies the survey paper "AI for Auto-Research: Roadmap & User Guide" and tracks papers on AI-assisted and automated scientific research, covering the full research lifecycle.

:robot: AI Auto-Research

We organize the academic research lifecycle as eight interconnected stages grouped into four epistemological phases. Each phase serves a distinct function in producing, scrutinizing, and communicating scientific knowledge.


	Phase 1: Creation Generating novel research ideas, searching and synthesizing literature, running coding experiments, and creating publication-quality tables and figures. This phase spans Idea Generation, Literature Review, Coding & Experiments, and Tables & Figures.
	Phase 2: Writing Drafting, editing, and polishing academic manuscripts. AI assistance ranges from semi-automated grammar and citation tools to fully automated paper generation — the most commercially mature yet ethically contested stage.
	Phase 3: Validation Automated peer review generation, reviewer-paper matching, review quality assessment, and AI-assisted author rebuttals. This phase covers Peer Review and Rebuttal & Revision.
	Phase 4: Dissemination Converting papers into slides, posters, videos, websites, and social media content. Each output format targets a different audience and demands its own design logic and AI tool chain.

For additional details, kindly refer to our :books: Paper and :earth_asia: Project Page.

:books: Citation

If you find this work helpful for your research, please kindly consider citing our paper:

@article{survey-ai-auto-research,
  title   = {{AI} for {Auto-Research}: Roadmap \& User Guide},
  author  = {Kong, Lingdong and Sun, Xian and Chow, Wei and Li, Linfeng and Lin, Kevin Qinghong and Zhang, Xuan Billy
             and Wang, Song and Li, Rong and Wu, Qing and Gao, Wei and Wang, Yingshuo and Xie, Shaoyuan
             and Liu, Jiachen and Qu, Leigang and Li, Shijie and Ng, Lai Xing and Cottereau, Benoit R.
             and Liu, Ziwei and Chua, Tat-Seng and Ooi, Wei Tsang},
  journal = {arXiv preprint arXiv:2605.18661},
  year    = {2026}
}

0. Background

1. Idea Generation
2. Literature Review & Paper Search
3. Coding & Experimentation
4. Tables & Figures
5. Paper Writing
6. Peer Review
7. Rebuttal
8. Dissemination (Paper2X)
9. End-to-End Systems
10. Societal & Critical Perspectives
11. Surveys & Curated Lists
12. Tools & GitHub Repos

1. Idea Generation

LLM Internal Knowledge-Based Generation

Model	Paper	Venue	Website	GitHub

`Chain of Ideas`	Chain of Ideas: Revolutionizing Research Via Novel Idea Development with LLM Agents	arXiv '24	-
`ResearchAgent`	ResearchAgent: Iterative Research Idea Generation over Scientific Literature with Large Language Models	NAACL '25	-
`SciMON`	SciMON: Scientific Inspiration Machines Optimized for Novelty	ACL '24	-
`Idea Gen Agent`	Can LLMs Generate Novel Research Ideas? A Large Scale Human Study with 100+ NLP Researchers	arXiv '24	-	-
`IRIS`	IRIS: Interactive Research Ideation System for Accelerating Scientific Discovery	ACL '25	-
`Spark`	Spark: A System for Scientifically Creative Idea Generation	ICCC '25	-	-
`Diverse Hypo. Search`	Towards Diverse Scientific Hypothesis Search with Large Language Models	arXiv '26	-	-
`Tree-of-Ideas`	Tree-of-Ideas: Automated Research Ideation via Cross-Trajectory Reasoning over Scholarly Evolution	arXiv '26	-	-
`IDEAgent`	IDEAgent: Agentic Quality-Diversity Search for Research Idea Generation	arXiv '26	-	-

External Signal-Driven Generation

Model	Paper	Venue	Website	GitHub
`SGHA`	SGHA: Evidence-Grounded Research Problem Discovery with Local Language Models	arXiv '26	-	-
`MAIL`	MAIL: Memory-driven, Adaptive, Incremental, and Literature-grounded Framework for Hypothesis Generation in Chemistry	arXiv '26	-	-

`MOOSE-Chem`	MOOSE-Chem: Large Language Models for Rediscovering Unseen Chemistry Scientific Hypotheses	ICLR '25	-	-
`Nova`	Nova: An Iterative Planning and Search Approach to Enhance Novelty and Diversity of LLM Generated Ideas	arXiv '24	-	-
`SciAgents`	SciAgents: Automating Scientific Discovery through Multi-Agent Intelligent Graph Reasoning	arXiv '24	-
`SciPIP`	SciPIP: An LLM-based Scientific Paper Idea Proposer	arXiv '24	-
`IdeaSynth`	IdeaSynth: Iterative Research Idea Development Through Evolving and Composing Idea Facets with Literature-Grounded Feedback	CHI '25	-	-
`MOOSE-Chem2`	MOOSE-Chem2: Exploring LLM Limits in Fine-Grained Scientific Hypothesis Discovery via Hierarchical Search	NeurIPS '25	-	-
`HALO`	HALO: Interactive Co-abductive Reasoning in Scientific Hypothesis Generation	arXiv '26	-	-
`TCA-SIR`	TCA-SIR: Learning Target-Conditioned Abstractions for Scientific Inspiration Retrieval	arXiv '26	-	-
`ECLAIR`	ECLAIR: A Causally-Grounded AI Framework for Scientific Discovery in Empirical Software Engineering	arXiv '26	-	-

Multi-Agent Collaborative Generation

Model	Paper	Venue	Website	GitHub
`HypoForge`	HypoForge: A Self-Improving Multi-Agent Framework for Automated Hypothesis Generation and Testing via Scientific Skill Learning	arXiv '26	-	-

`Combi. Creativity`	Combi. Creativity	arXiv '24	-	-
`Deep Ideation`	Deep Ideation: Designing LLM Agents to Generate Novel Research Ideas on Scientific Concept Network	arXiv '25	-
`VirSci`	Many Heads Are Better Than One: Improved Scientific Idea Generation by A LLM-Based Multi-Agent System	ACL '25	-
`Multi-Agent Dial.`	Multi-Agent Dial.	SIGDIAL '25	-	-
`Artificial Hivemind`	Artificial Hivemind: The Open-Ended Homogeneity of Language Models (and Beyond)	NeurIPS '25	-	-
`Auditable AI Sci.`	Toward Auditable AI Scientists: A Hypothesis Evolution Protocol for LLM Agents	arXiv '26	-	-
`Diverse Personalized Ideation`	Diversifying Personalized Research Ideation against AI-Induced Homogenization	arXiv '26	-	-

Novelty and Feasibility Assessment

Model	Paper	Venue	Website	GitHub
`RATIO`	RATIO: A Benchmark for Retrieval Across Typed Ideation Operations in Scientific Literature	arXiv '26	-	-
`Lit2Test`	What Proves You Wrong: Benchmarking Language Models on Falsifiable Research Ideation	arXiv '26	-	-
`Energy Scoring`	Do LLMs Know a Good Hypothesis When They See One? Logit-Based Energy Scoring Outperforms Prompted LLM-as-Judge for Scientific Hypothesis Ranking	arXiv '26	-	-
`Think-Probe-Respond`	Think-Probe-Respond: Improving Large Language Models as Judges of Research Idea Novelty	EMNLP '26	-	-

`IdeaBench`	LiveIdeaBench: Evaluating LLMs' Scientific Creativity and Idea Generation with Minimal Context	KDD '25	-	-
`LiveIdeaBench`	LiveIdeaBench: Evaluating LLMs' Scientific Creativity and Idea Generation with Minimal Context	arXiv '24	-	-
`AI Idea Bench 2025`	AI Idea Bench 2025: AI Research Idea Generation Benchmark	arXiv '25	-
`HeurekaBench`	HeurekaBench: A Benchmarking Framework for AI Co-scientist	ICLR '26	-
`ResearchBench`	ResearchBench: Benchmarking LLMs in Scientific Discovery via Inspiration-Based Task Decomposition	ACL '26	-	-
`HindSight`	HindSight: Evaluating LLM-Generated Research Ideas via Future Impact	arXiv '26	-	-
`Rubric Rewards`	Training AI Co-Scientists Using Rubric Rewards	arXiv '25	-	-
`DeepInnovator`	DeepInnovator: Triggering the Innovative Capabilities of LLMs	arXiv '26	-
`FlowPIE`	FlowPIE: Test-Time Scientific Idea Evolution with Flow-Guided Literature Exploration	arXiv '26	-	-
`SoundnessBench`	SoundnessBench: Can Your AI Scientist Really Tell Good Research Ideas from Bad Ones?	arXiv '26	-	-
`LLM-Judge Novelty`	On the Limits of LLM-as-Judge for Scientific Novelty Assessment	arXiv '26	-	-
`LigBench`	LigBench: A Unified and Human-Aligned Benchmark for LLM-based Research Idea Generation	arXiv '26	-	-
`Reconstruction`	Reconstruction: A Blind Benchmark for Recovering Research Ideas from Pre-Publication Bibliographies	arXiv '26	-	-

2. Literature Review & Paper Search

Literature Retrieval

Model	Paper	Venue	Website	GitHub
`ITER`	ITER: Interaction-Aware Retrieval for Agentic Search	arXiv '26	-	-
`Multi-Aspect Retrieval`	Can Retrievers Find the Same Paper from Different Aspects? A Multi-Aspect Full-Paper Scientific Retrieval Benchmark	arXiv '26	-	-

`CiteME`	CiteME: Can Language Models Accurately Cite Scientific Claims?	arXiv '24	-	-
`LitLLM`	LitLLM: A Toolkit for Literature Review with Large Language Models	arXiv '24	-	-
`LitSearch`	LitSearch: A Retrieval Benchmark for Scientific Literature Search	arXiv '24	-
`PaperQA2`	Language Agents Achieve Superhuman Synthesis of Scientific Knowledge	arXiv '24	-
`OpenResearcher`	OpenResearcher: Unleashing AI for Accelerated Scientific Research	EMNLP '24	-	-
`PaSa`	PaSa: An LLM Agent for Comprehensive Academic Paper Search	arXiv '25	-
`Self-Evolving Retrieval`	Towards Self-Evolving Agentic Literature Retrieval	arXiv '26	-	-
`MasterSet`	MasterSet: A Large-Scale Benchmark for Must-Cite Citation Recommendation in the AI/ML Literature	arXiv '26	-	-
`Search, Inspect, Fetch`	Search, Inspect, Fetch: Exploiting Structure-Aware Boolean Retrieval for Deep-Research Agents	arXiv '26	-	-
`Rubric Reranker`	Training Documents Reranker with Search Rubrics for Deep Research Agent	arXiv '26	-	-
`Personalized DR Refinement`	Personalized Deep Research Query Refinement with Graph-Scaffolded Evidence Grounding	arXiv '26	-	-

Model	Paper	Venue	Website	GitHub
`DAS`	Deep Academic Survey: Stateful Agentic Closed-Loop Paradigm for Academic Survey Automation	arXiv '26	-	-
`Tree-of-Concerns`	Tree-of-Concerns: Hierarchical Multi-Agent Debate for Unstated-Limitation Extraction in Scientific Critique	EMNLP '26	-	-

`ChatPaper`	ChatPaper: Use LLM to summarize papers	GitHub '23	-
`PaperQA`	PaperQA: Retrieval-Augmented Generative Agent for Scientific Research	arXiv '23	-
`AutoSurvey`	AutoSurvey: Large Language Models Can Automatically Write Surveys	arXiv '24	-
`GPT Researcher`	GPT Researcher: Autonomous Agent for Comprehensive Online Research	GitHub '24	-
`LLMs for Lit. Review`	LLMs for Lit. Review	arXiv '24	-	-
`STORM`	Assisting in Writing Wikipedia-like Articles From Scratch with Large Language Models	arXiv '24	-
`Agentic AutoSurvey`	Agentic AutoSurvey: Let LLMs Survey LLMs	arXiv '25	-	-
`Citegeist`	Citegeist: Automated Generation of Related Work Analysis on the arXiv Corpus	arXiv '25	-	-
`IterSurvey`	IterSurvey: Deep Literature Survey Automation with an Iterative Workflow	arXiv '25	-
`LiRA`	LiRA: A Multi-Agent Framework for Reliable and Readable Literature Review Generation	arXiv '25	-	-
`SurveyForge`	SurveyForge: On the Outline Heuristics, Memory-Driven Generation, and Multi-dimensional Evaluation for Automated Survey Writing	arXiv '25	-
`SurveyG`	SurveyG: A Multi-Agent LLM Framework with Hierarchical Citation Graph for Automated Survey Generation	arXiv '25	-	-
`SurveyX`	SurveyX: Academic Survey Automation via Large Language Models	arXiv '25	-	-
`InteractiveSurvey`	InteractiveSurvey: An LLM-based Personalized and Interactive Survey Paper Generation System	arXiv '25	-
`CiteLLM`	CiteLLM: An Agentic Platform for Trustworthy Scientific Reference Discovery	arXiv '26	-	-
`DeepSurvey`	DeepSurvey: Enhancing Analytical Depth and Citation Reliability in Automated Survey Generation	arXiv '26	-	-
`STRUCTSURVEY`	STRUCTSURVEY: Structured Agentic Retrieval for Automated Survey Paper Generation	arXiv '26	-	-

Deep Research Agents

Model	Paper	Venue	Website	GitHub
`Crase`	Structurally-bounded Agentic Graph Exploration for Evidence-Grounded Scholarly DeepSearch	arXiv '26	-	-
`DeepWeaver`	DeepWeaver: Bridging the Evidence Synthesis Gap in Open-Ended Question Answering	arXiv '26	-	-
`AgentR`	AgentR A Stateful and Recovery-Aware Software Architecture for LLM-based Auditable Workflows	arXiv '26	-	-

`ASReview`	An Open Source Machine Learning Framework for Efficient and Transparent Systematic Reviews	Nature MI '21	-
`CHIME`	CHIME: LLM-Assisted Hierarchical Organization of Scientific Studies for Literature Review Support	arXiv '24	-	-
`DeepResearch-Agent`	DeepResearchAgent: A Hierarchical Multi-Agent System for Deep Research	GitHub '25	-
`DeerFlow`	DeerFlow: A Deep Research Framework Orchestrating Sub-Agents, Memory, and Sandboxes	GitHub '25	-
`OpenScholar`	OpenScholar: Synthesizing Scientific Literature with Retrieval-Augmented LMs	Nature '26	-	-
`AutoAgent`	AutoAgent	arXiv '25	-	-
`Tongyi DeepResearch`	Tongyi DeepResearch	GitHub '25	-
`O-Researcher`	O-Researcher: An Open Ended Deep Research Model via Multi-Agent Distillation and Agentic RL	arXiv '26	-	-
`OpenResearcher`	OpenResearcher: Unleashing AI for Accelerated Scientific Research	arXiv '26	-
`AREX`	AREX: Towards a Recursively Self-Improving Agent for Deep Research	arXiv '26	-	-
`Predictive Navigation`	Deep Research Pretraining via Predictive Navigation	arXiv '26	-	-
`On-Device DR (4B)`	On-Device Deep Research at 4B: Exposure Bounds Faithfulness, Retrieval Bounds Coverage	arXiv '26	-	-
`Carnot`	Carnot: Interpretable, Interactive, and Optimized Execution of Deep Research Queries	VLDB '26	-	-
`Marginal Value Est.`	Not Worth Another Token: Marginal Value Estimation for Efficient Deep Research Agents	arXiv '26	-	-
`Retrieval-Aware Control`	When Deep Research Agents Stagnate: Enhancing Reasoning with Retrieval-Aware Agent Control	arXiv '26	-	-
`Analogical Deep Research`	Analogical Deep Research: Retrieving and Integrating Historical Analogies for Foresight Analysis	arXiv '26	-	-
`Plato-Bio`	Plato-Bio: verification-first biological novelty screening with temporal rediscovery and structural benchmarks	arXiv '26	-	-
`Albilich`	Albilich: Steerable Proof-State Orchestration for LLM-Based Mathematical Research with CAS Integration	arXiv '26	-	-

Retrieval and Synthesis Quality Assessment

Model	Paper	Venue	Website	GitHub
`IBIS`	From Inertia to Objectivity: Improving Deep Research Agents with Noise Isolation	EMNLP '26	-	-
`Agent to Blame`	Who is the Agent to Blame? Localizing Faithfulness and Citation Mistakes in Agentic Deep Research	EMNLP '26	-	-

`DeepScholar-Bench`	DeepScholar-Bench: A Live Benchmark and Automated Evaluation for Generative Research Synthesis	arXiv '25	-
`ReportBench`	ReportBench: Evaluating Deep Research Agents via Academic Survey Tasks	arXiv '25	-
`IDRBench`	IDRBench: Interactive Deep Research Benchmark	arXiv '26	-	-
`ScholarGym`	ScholarGym: Benchmarking Large Language Model Capabilities in the Information-Gathering Stage of Deep Research	arXiv '26	-	-
`SciNetBench`	SciNetBench: A Relation-Aware Benchmark for Scientific Literature Retrieval Agents	arXiv '26	-	-
`AutoResearchBench`	AutoResearchBench: Benchmarking AI Agents on Complex Scientific Literature Discovery	arXiv '26	-	-
`PaperMind`	PaperMind: Benchmarking Agentic Reasoning and Critique over Scientific Papers in Multimodal LLMs	arXiv '26	-	-
`DRNOISE`	DRNOISE: Benchmarking Deep Research Agents in Misleading Evidence Environments	arXiv '26	-	-
`HiEviDR-Bench`	HiEviDR-Bench: A Benchmark for Hierarchical Evidence Aggregation in Deep Research	arXiv '26	-	-
`SciExplore`	SciExplore: Evaluating Autonomous Agents from Scientific Navigation to Information Integration	arXiv '26	-	-
`WANDR`	WANDR: A Benchmark for Wide and Deep Research	arXiv '26	-	-
`QA-to-DR Bench`	From Simple QA to Deep Research: A Verifiable Benchmark Constructed through Iterative Task Evolution	arXiv '26	-	-

3. Coding & Experimentation

Code Generation

Model	Paper	Venue	Website	GitHub

`SWE-bench`	SWE-bench: Can Language Models Resolve Real-World GitHub Issues?	ICLR '24	-
`SWE-agent`	SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering	arXiv '24	-
`OpenHands`	OpenHands: An Open Platform for AI Software Developers as Generalist Agents	ICLR '25	-
`SWE-bench Pro`	SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?	arXiv '25	-	-
`SWE-EVO`	SWE-EVO: Benchmarking Coding Agents in Long-Horizon Software Evolution Scenarios	arXiv '25	-	-

Paper-to-Code

Model	Paper	Venue	Website	GitHub
`ReproAgent`	ReproAgent: Contract-Guided Paper-to-Code Reproduction	EMNLP '26	-	-
`DeepRepro`	DeepRepro: State-Aware Subplanning for Paper-to-Code Reproduction in Evolving Repositories	CIKM '26	-	-

`FunSearch`	Mathematical Discoveries from Program Search with Large Language Models	Nature '24	-
`SciCode`	SciCode: A Research Coding Benchmark Curated by Scientists	arXiv '24	-
`PaperBench`	PaperBench: Evaluating AI's Ability to Replicate AI Research	arXiv '25	-
`PaperCoder`	Paper2Code: Automating Code Generation from Scientific Papers in Machine Learning	arXiv '25	-
`ResearchCodeBench`	ResearchCodeBench: Benchmarking LLMs on Implementing Novel ML Research Code	arXiv '25	-	-
`SciReplicate-Bench`	SciReplicate-Bench: Benchmarking LLMs in Agent-driven Algorithmic Reproduction from Research Papers	arXiv '25	-

Experiment Execution & Orchestration

Model	Paper	Venue	Website	GitHub
`Praxist`	Praxist: From Experimental Artifacts to Solution Lineages	arXiv '26	-	-
`Skill-Based Baselines`	Can Coding Agents Build Robust Baselines? A Skill-Based Approach for Automating the Medical Imaging Model-Development Pipeline	MICCAI '26	-	-

`BioPlanner`	BioPlanner: Automatic Evaluation of LLMs on Protocol Planning	arXiv '23	-
`CRISPR-GPT`	CRISPR-GPT for Agentic Automation of Gene-Editing Experiments	arXiv '24	-	-
`DS-Agent`	DS-Agent: Automated Data Science by Empowering Large Language Models with Case-Based Reasoning	arXiv '24	-
`MLE-Bench`	MLE-Bench: Evaluating Machine Learning Agents on Machine Learning Engineering	arXiv '24	-	-
`MLAgentBench`	MLAgentBench: Evaluating Language Agents on Machine Learning Experimentation	arXiv '24	-
`MLR-Copilot`	MLR-Copilot: Autonomous Machine Learning Research based on Large Language Models Agents	arXiv '24	-	-
`AIDE`	AIDE: AI-Driven Exploration in the Space of Code	arXiv '25	-	-
`AlphaEvolve`	AlphaEvolve: A Coding Agent for Scientific and Algorithmic Discovery	arXiv '25	-	-
`AutoReproduce`	AutoReproduce: Automatic AI Experiment Reproduction with Paper Lineage	arXiv '25	-
`CURIE`	Curie: Toward Rigorous and Automated Scientific Experimentation with AI Agents	arXiv '25	-
`MLGym`	MLGym: A New Framework and Benchmark for Advancing AI Research Agents	arXiv '25	-	-
`MLR-Bench`	MLR-Bench: Evaluating AI Agents on Open-Ended Machine Learning Research	arXiv '25	-	-
`Execution-Grounded`	Towards Execution-Grounded Automated AI Research	arXiv '26	-	-
`Learn to Discover`	Learning to Discover at Test Time	arXiv '26	-	-
`AutoNumerics`	AutoNumerics: An Autonomous, PDE-Agnostic Multi-Agent Pipeline for Scientific Computing	arXiv '26	-
`SciNav`	SciNav: A General Agent Framework for Scientific Coding Tasks	arXiv '26	-	-
`FrontierScience`	FrontierScience: Evaluating AI's Ability to Perform Expert-Level Scientific Tasks	arXiv '26	-	-
`EvoDS`	EvoDS: Self-Evolving Autonomous Data Science Agent with Skill Learning and Context Management	arXiv '26	-	-
`AutoTTS`	LLMs Improving LLMs: Agentic Discovery for Test-Time Scaling	arXiv '26	-
`AutoScientists`	AutoScientists: Self-Organizing Agent Teams for Long-Running Scientific Experimentation	arXiv '26	-	-
`EurekAgent`	EurekAgent: Agent Environment Engineering is All You Need For Autonomous Scientific Discovery	arXiv '26	-	-

Code Correctness and Reproducibility Assessment

Model	Paper	Venue	Website	GitHub
`Experimental Fidelity`	Beyond Execution: Auditing Experimental Fidelity in LLM-Driven Scientific Research	arXiv '26	-	-

`DiscoveryBench`	DiscoveryBench: Towards Data-Driven Discovery with Large Language Models	arXiv '24	-
`DiscoveryWorld`	DiscoveryWorld: A Virtual Environment for Developing and Evaluating Automated Scientific Discovery Agents	arXiv '24	-
`InfiAgent-DABench`	InfiAgent-DABench: Evaluating Agents on Data Analysis Tasks	arXiv '24	-	-
`ScienceAgentBench`	ScienceAgentBench: Toward Rigorous Assessment of Language Agents for Data-Driven Scientific Discovery	arXiv '24	-	-
`LAB-Bench`	Lab-Bench: Measuring Capabilities of Language Models for Biology Research	arXiv '24	-
`KernelBench`	KernelBench: Can LLMs Write Efficient GPU Kernels?	arXiv '25	-
`TritonBench`	TritonBench: Benchmarking Large Language Model Capabilities for Generating Triton Operators	arXiv '25	-
`AstaBench`	AstaBench: Rigorous Benchmarking of AI Agents with a Scientific Research Suite	arXiv '25	-
`ResearchClawBench`	Probing Scientific General Intelligence of LLMs with Scientist-Aligned Workflows	arXiv '25	-
`EXP-Bench`	EXP-Bench: Can AI Conduct AI Research Experiments?	ICLR '26	-
`PostTrainBench`	PostTrainBench: Can LLM Agents Automate LLM Post-Training?	arXiv '26	-
`MLReplicate`	MLReplicate: Benchmarking Autonomous Research Systems for Machine Learning Reproducibility	arXiv '26	-	-
`BeyondSWE`	BeyondSWE: Can Current Code Agent Survive Beyond Single-Repo Bug Fixing?	arXiv '26
`NatureBench`	NatureBench: Can Coding Agents Match the Published SOTA of Nature-Family Papers?	arXiv '26	-	-
`SciCoQA`	SciCoQA: Quality Assurance for Scientific Paper--Code Alignment	ACL '26

4. Tables & Figures

Scientific Figure Generation

Model	Paper	Venue	Website	GitHub

`ChartGPT`	ChartGPT: Leveraging LLMs to Generate Charts from Abstract Natural Language	arXiv '23	-	-
`MatPlotAgent`	MatPlotAgent: Method and Evaluation for LLM-Based Agentic Scientific Data Visualization	arXiv '24	-	-
`CoDA`	CoDA: Agentic Systems for Collaborative Data Visualization	arXiv '25	-	-
`PlotGen`	PlotGen: Multi-Agent LLM-based Scientific Data Visualization via Multimodal Feedback	arXiv '25	-	-
`VIS-Shepherd`	VIS-Shepherd: Constructing Critic for LLM-based Data Visualization Generation	arXiv '25	-	-
`DiagramAgent`	From Words to Structured Visuals: A Benchmark and Framework for Text-to-Diagram Generation and Editing	CVPR '25	-	-
`StarVector`	StarVector: Generating Scalable Vector Graphics Code from Images and Text	CVPR '25	-	-
`VisCoder`	VisCoder: Fine-Tuning LLMs for Executable Python Visualization Code Generation	EMNLP '25	-	-
`AI-Generated Figures`	AI-Generated Figures	arXiv '26	-	-
`AutoFigure-Edit`	AutoFigure-Edit: Generating Editable Scientific Illustration	arXiv '26	-
`AutoFigure`	AutoFigure-Edit: Generating Editable Scientific Illustration	ICLR '26	-
`PaperBanana`	PaperBanana: Automating Academic Illustration for AI Scientists	arXiv '26	-	-
`SAIL`	Setting SAIL: Leveraging Scientist-AI-Loops for Rigorous Visualization Tools	arXiv '26	-	-
`Crafter`	Crafter: A Multi-Agent Harness for Editable Scientific Figure Generation from Diverse Inputs	arXiv '26	-	-
`DiagramRAG`	DiagramRAG: A Lightweight Framework to Retrieve Scientific Diagram for Figure Generation	arXiv '26	-	-
`GeoSVG-RL`	GeoSVG-RL: Geometry-Aware Reinforcement Learning for Layout-Constrained Text-to-SVG Diagram Generation	arXiv '26	-	-
`Can AI Draw Sci.`	Can AI Draw Science? A Benchmark for Evaluating Scientific Figure Generation by Text-to-Image and Multimodal Models	arXiv '26	-	-
`SciDiagramEdit`	SciDiagramEdit: Learning to Edit Scientific Diagrams from Paper Revisions	arXiv '26	-	-
`GenGA`	GenGA: Editable and Data-Grounded Graphical Abstract Generation for Academic Papers	arXiv '26	-	-

Table Understanding & Generation

Model	Paper	Venue	Website	GitHub

`ArxivDIGESTables`	ArxivDIGESTables: Synthesizing Scientific Literature into Tables using Language Models	EMNLP '24	-	-
`Chain-of-Table`	Chain-of-Table: Evolving Tables in Reasoning Chain for Table Understanding	ICLR '24	-	-
`ShowTable`	ShowTable: Unlocking Creative Table Visualization with Collaborative Reflection and Refinement	CVPR '26	-	-
`Table2LaTeX-RL`	Table2LaTeX-RL: Converting Table Images to High-Fidelity LaTeX Code Using Reinforced Multimodal Language Models	arXiv '25	-	-
`CSPO`	CSPO: Alleviating Reward Ambiguity for Structured Table-to-LaTeX Generation	arXiv '26	-	-

Mathematical Formulas & TikZ

Model	Paper	Venue	Website	GitHub

`AutomaTikZ`	AutomaTikZ: Text-Guided Synthesis of Scientific Vector Graphics with TikZ	ICLR '24	-	-
`DeTikZify`	DeTikZify: Synthesizing Graphics Programs for Scientific Figures and Sketches with TikZ	NeurIPS '24	-	-
`TikZilla`	TikZilla: Scaling Text-to-TikZ with High-Quality Data and Reinforcement Learning	arXiv '26	-	-
`Edit2TikZ`	Edit2TikZ: A Comprehensive and Challenging Benchmark for Scientific Figure Editing with TikZ	arXiv '26	-	-

Visual Fidelity and Scientific Accuracy Assessment

Model	Paper	Venue	Website	GitHub

`StructEval`	StructEval: Benchmarking LLMs' Capabilities to Generate Structural Outputs	TMLR '25
`PlotCraft`	PlotCraft: Pushing the Limits of LLMs for Complex and Interactive Data Visualization	arXiv '25	-	-
`TeXpert`	TeXpert: Multi-Level Benchmark for LaTeX Code Generation	SDP '25	-	-
`AbGen`	AbGen: Evaluating Large Language Models in Ablation Study Design and Evaluation for Scientific Research	ACL '25	-	-
`SciFig`	SciFig: Towards Automating Scientific Figure Generation	arXiv '26	-	-
`SciFlow-Bench`	SciFlow-Bench: Evaluating Structure-Aware Scientific Diagram Generation via Inverse Parsing	arXiv '26	-	-
`FigureBench`	AutoFigure: Generating and Refining Publication-Ready Scientific Illustrations	ICLR '26	-
`SciFigQual-Bench`	SciFigQual-Bench: A Benchmark for Scientific Figure Quality Assessment with Full-Manuscript Context	arXiv '26	-	-
`SciFigAlign`	SciFigAlign: Scoring Scientific Figures by Fine-tuned Alignment of Visuals with Manuscript Evidence	arXiv '26	-	-
`SciFigPlag-Bench`	SciFigPlag-Bench: A Benchmark for Provenance-Aware Scientific Figure Plagiarism Detection	arXiv '26	-	-
`VLM Blind/Misled`	How Do VLMs Behave When Blind or Misled? Behavioral Evaluation of VLMs on Scientific Figures	arXiv '26	-	-

5. Paper Writing

Semi-Automated Writing Assistance

Model	Paper	Venue	Website	GitHub

`CoAuthor`	CoAuthor: Human-AI Collaborative Writing with Language Models	arXiv '22	-	-
`AI Writing Study`	AI Writing Study	AIED '25	-	-
`DraftMarks`	DraftMarks: Enhancing Transparency in Human-AI Co-Writing Through Interactive Skeuomorphic Process Traces	arXiv '25	-	-
`PaperDebugger`	PaperDebugger: A Plugin-Based Multi-Agent System for In-Editor Academic Writing, Review, and Editing	arXiv '25	-
`ScholarCopilot`	ScholarCopilot: Training LLMs for Academic Writing with Integrated Citation	arXiv '25	-	-
`XtraGPT`	XtraGPT: Context-Aware and Controllable Academic Paper Revision	arXiv '25	-	-
`LimAgents`	Multi-Agent LLMs for Generating Research Limitations	arXiv '26	-	-
`PaperMentor`	PaperMentor: A Human-Centered Multi-Agent Writing Tutor for AI Research Papers on Overleaf	arXiv '26	-	-
`AutoSupervision`	AutoSupervision: Closing the Feedback Loop in Scientific Workflows with Grounded Revision Verification	arXiv '26	-	-
`ReasFlow`	ReasFlow: Assisting Reasoning-Centric Scientific Discovery in Applied Mathematics via a Knowledge-Based Multi-Agent System	arXiv '26	-	-

Fully Automated Paper Generation

Model	Paper	Venue	Website	GitHub

`CycleResearcher`	CycleResearcher: Improving Automated Research via Automated Review	ICLR '25	-	-
`Agent Laboratory`	Agent Laboratory: Using LLM Agents as Research Assistants	EMNLP '25	-	-
`FutureGen`	FutureGen: A RAG-based Approach to Generate the Future Work of Scientific Article	arXiv '25	-	-
`AI Scientist`	The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery	Nature '26	-
`APRES`	APRES: An Agentic Paper Revision and Evaluation System	arXiv '26	-	-
`LECTOR`	LECTOR: Joint Optimization of Scientific Reasoning Graphs and Introduction Generation	arXiv '26	-	-
`RWGBench`	RWGBench: Evaluating Scholarly Positioning in Related Work Generation	arXiv '26	-	-

Societal Analysis

Model	Paper	Venue	Website	GitHub

`AI Writing Adoption`	AI Writing Adoption	Nature '26	-	-
`Nature AI Survey`	More than Half of Researchers Now Use AI for Peer Review	Nature '26	-	-
`Denial of Science`	Distributed Denial of Science: How Indirect Data Poisoning of AI Systems Can Industrialize Scientific Fraud	arXiv '26	-	-
`AI Slop OSS`	"AI Slop is DDoSing Open Source": Understanding the Impact of AI-Generated Contributions on Open Source Sustainability	arXiv '26	-	-

Writing Quality and AI Detection Assessment

Model	Paper	Venue	Website	GitHub

`Mapping LLM Use`	Mapping the Increasing Use of LLMs in Scientific Papers	arXiv '24	-	-
`CycleReviewer`	CycleResearcher: Improving Automated Research via Automated Review	ICLR '25	-	-
`Stanford Agentic`	Stanford Agentic	Web '25	-	-
`SciIG`	Let's Use ChatGPT To Write Our Paper! Benchmarking LLMs To Write the Introduction of a Research Paper	arXiv '25	-	-
`Watermarking`	Detecting LLM-Generated Peer Reviews	arXiv '25	-	-
`PaperWritingBench`	PaperOrchestra: A Multi-Agent Framework for Automated AI Research Paper Writing	arXiv '26	-	-
`CiteTracer`	Source or It Didn't Happen: A Multi-Agent Framework for Citation Hallucination Detection	arXiv '26	-	-
`Process Eval`	Process-Oriented Evaluation of AI-Assisted Scientific Writing	arXiv '26	-	-

6. Peer Review

Automated Review Generation

Model	Paper	Venue	Website	GitHub

`ChatReviewer`	ChatReviewer: ChatGPT-based Paper Reviewing and Response Generation	GitHub '23	-
`AI-Peer-Review`	AI-Peer-Review	GitHub '24	-
`MARG`	MARG: Multi-Agent Review Generation for Scientific Papers	arXiv '24	-	-
`Reviewer2`	Reviewer2: Optimizing Review Generation Through Prompt Generation	arXiv '24	-	-
`ReviewRL`	ReviewRL: Towards Automated Scientific Review with RL	EMNLP '25	-	-
`DeepReviewer`	DeepReview: Improving LLM-based Paper Review with Human-like Deep Thinking Process	arXiv '25	-	-
`OpenReviewer`	OpenReviewer: A Specialized Large Language Model for Generating Critical Scientific Paper Reviews	NAACL '25	-	-
`REMOR`	REMOR: Automated Peer Review Generation with LLM Reasoning and Multi-Objective Reinforcement Learning	arXiv '25	-	-
`ScholarPeer`	ScholarPeer: A Context-Aware Multi-Agent Framework for Automated Peer Review	arXiv '26	-	-
`ProReviewer`	From Passive Generation to Investigation: A Proactive Scientific Peer Review Agent	arXiv '26	-	-
`PeerCheck`	PeerCheck: Enhancing LLM-Generated Academic Reviews Towards Human-Level Quality	arXiv '26	-	-
`Local Pre-Screening`	Local AI pre-screening for human triple-blind peer review in health sciences	arXiv '26	-	-
`ReVoicer`	ReVoicer: Conversational Voice Annotation for Human-Centered, LLM-Assisted Peer Review	arXiv '26	-	-

Meta-Review & Reviewer Matching

Model	Paper	Venue	Website	GitHub
`Metag`	Metag: A dataset to build agentic meta-reviewing capabilities	arXiv '26	-	-

`AgentReview`	AgentReview: Exploring Peer Review Dynamics with LLM Agents	EMNLP '24	-	-
`Meta-Review LLMs`	Meta-Review LLMs	NAACL '25	-	-
`RATE`	RATE: Reviewer Profiling and Annotation-free Training for Expertise Ranking in Peer Review Systems	arXiv '26	-	-
`MERIT`	MERIT: Matching Expertise via Rubric-Informed Training for Reviewer Assignment	arXiv '26	-	-

Adversarial Attacks & Bias Analysis

Model	Paper	Venue	Website	GitHub

`Raina etal`	Raina etal	EMNLP '24	-	-
`AI Review Lottery`	The AI Review Lottery: Widespread AI-Assisted Peer Reviews Boost Paper Scores and Acceptance Rates	arXiv '24	-	-
`Ye etal`	Ye etal	arXiv '24	-	-
`Breaking the Reviewer`	Breaking the Reviewer: Assessing the Vulnerability of Large Language Models in Automated Peer Review Under Textual Adversarial Attacks	arXiv '25	-	-
`LLM Reviewer Bias`	LLM Reviewer Bias	arXiv '25	-	-
`Prompt Injection`	Prompt Injection Attacks on LLM Generated Reviews of Scientific Publications	arXiv '25	-	-
`Sahoo etal`	Sahoo etal	arXiv '25	-	-
`Zhou etal`	Zhou etal	arXiv '25	-	-
`Presentation Gaming`	No Hidden Prompts Needed! You Can Game AI Peer Review with Presentation-Only Revisions	arXiv '26	-	-
`LLMs Favor LLMs?`	Do LLMs Favor LLMs? Quantifying Interaction Effects in Peer Review	arXiv '26	-	-
`Gaming AI Reviews`	Gaming AI-Assisted Peer Reviews Poses New Risks to the Scientific Community	arXiv '26	-	-
`Phantom Refs`	Phantom References: Hallucinated Citations That Survive Peer Review at Top-Tier Conferences	arXiv '26	-	-
`Rhetorical Reward-Hacking`	How Can Rhetoric Reward-Hack AI Reviewers? Dissecting Rhetorical Sensitivity in AI-Based Peer Review	arXiv '26	-	-

Detection & Policy

Model	Paper	Venue	Website	GitHub

`AI Detection`	Is Your Paper Being Reviewed by an LLM? Benchmarking AI Text Detection in Peer Review	arXiv '25	-	-
`AI Use Rejects`	Major Conference Catches Illicit AI Use — and Rejects Hundreds of Papers	Nature '26	-	-
`Nature AI Survey`	More than Half of Researchers Now Use AI for Peer Review	Nature '26	-	-
`Policy Enforcement`	Policy Enforcement	arXiv '26	-	-
`Reviewer Feedback`	What Happens When Reviewers Receive AI Feedback in Their Reviews?	CHI '26	-	-
`AAAI-26 Pilot`	AI-Assisted Peer Review at Scale: The AAAI-26 AI Review Pilot	arXiv '26	-	-
`Reviewer AI Policies`	AI-Assisted Peer Review Across Research Communities: From Reviewer AI Policies to LLM Review Quality	arXiv '26	-	-

Review Consistency and Bias Assessment

Model	Paper	Venue	Website	GitHub
`VERA-RL`	Not Just Reason, Not Just Scan: Reinforcement Learning for Proactive Scientific Error Verification over Academic Paper	EMNLP '26	-	-

`Review Survey`	More than Half of Researchers Now Use AI for Peer Review — often Against Guidance	IF '25	-	-
`Stanford Agentic`	Stanford Agentic	Web '25	-	-
`ClaimCheck`	ClaimCheck: How Grounded are LLM Critiques of Scientific Papers?	EMNLP '25	-	-
`REFUTE`	REFUTE: A Benchmark for Scientific Critique and Epistemic Calibration in Language Models	HF '26	Website	-
`ReViewGraph`	Automatic Paper Reviewing with Heterogeneous Graph Reasoning over LLM-Simulated Reviewer-Author Debates	AAAI '26	-	-
`ReviewAgents`	ReviewAgents: Bridging the Gap Between Human and AI-Generated Paper Reviews	arXiv '25	-	-
`ICLR 2025 Study`	ICLR 2025 Study	NMI '26	-	-
`AI Reviewer Limits`	On the limits and opportunities of AI reviewers: Reviewing the reviews of Nature-family papers with 45 expert scientists	arXiv '26	-	-
`PRISM`	PRISM: A Multi-Dimensional Benchmark for Evaluating LLM Peer Reviewers	arXiv '26	-	-
`LLM-Human Alignment`	How Closely Do LLM Reviews Align with Human Peer Review?	arXiv '26	-	-
`Epistemic Reliability`	Articulate Intuition or Genuine Analysis? Benchmarking Epistemic Reliability in LLM-as-a-Judge Peer Reviews	arXiv '26	-	-
`SurveyReview`	SurveyReview: A Reviewer-Aligned Benchmark for Survey Evaluators	arXiv '26	-	-

7. Rebuttal

Reviewer Comment Analysis

Model	Paper	Venue	Website	GitHub

`ReviewMT`	Peer Review as A Multi-Turn and Long-Context Dialogue with Role-Based Interactions	arXiv '24	-	-
`ICLR Rebuttal Study`	ICLR Rebuttal Study	arXiv '25	-	-
`RbtAct`	RbtAct: Rebuttal as Supervision for Actionable Review Feedback Generation	arXiv '26	-	-
`GoodPoint`	GoodPoint: Learning Constructive Scientific Paper Feedback from Author Responses	arXiv '26	-	-

Automated Rebuttal Generation

Model	Paper	Venue	Website	GitHub

`ReviewerToo`	ReviewerToo: Should AI Join The Program Committee? A Look At The Future of Peer Review	arXiv '25	-	-
`RebuttalAgent`	RebuttalAgent: Strategic Persuasion in Academic Rebuttal via Theory of Mind	ICLR '26	-
`Author-in-the-Loop`	Author-in-the-Loop Response Generation and Evaluation: Integrating Author Expertise and Intent in Responses to Peer Review	ACL '26	-	-
`DRPG`	DRPG: An Agentic Framework for Academic Rebuttal	arXiv '26	-
`Paper2Rebuttal`	Paper2Rebuttal: A Multi-Agent Framework for Transparent Author Response Assistance	arXiv '26	-	-
`Defend`	Defend: Automated Rebuttals for Peer Review with Minimal Author Guidance	arXiv '26	-	-

Rebuttal Effectiveness Assessment

Model	Paper	Venue	Website	GitHub

`Re$^2$`	Re$^2$	arXiv '25	-	-
`Commitment Checklist`	Commitment Checklist: Auditing Author Commitments in Peer Review	arXiv '26	-	-
`Re$^3$Align`	Re$^3$Align	ACL '26	-	-
`Rebuttals Move`	Rebuttals Move Peer-Review Scores, but Initial-Review Structure Bounds the Movement	arXiv '26	-	-
`Trust AI Reviews`	To Trust or Not to Trust: Authors' Response to AI-based Reviews	arXiv '26	-	-

8. Dissemination (Paper2X)

Paper2Poster

Model	Paper	Venue	Website	GitHub

`P2P`	P2P: Automated Paper-to-Poster Generation and Fine-Grained Benchmark	ICLR '26	-	-
`Paper2Poster`	Paper2Poster: Towards Multimodal Poster Automation from Scientific Papers	NeurIPS '25	-
`PosterForest`	PosterForest: Hierarchical Multi-Agent Collaboration for Scientific Poster Generation	arXiv '25	-	-
`PosterGen`	PosterGen: Aesthetic-Aware Paper-to-Poster Generation via Multi-Agent LLMs	arXiv '25	-	-
`APEX`	APEX: Academic Poster Editing Agentic Expert	arXiv '26	-
`PosterOmni`	PosterOmni: Generalized Artistic Poster Creation via Task Distillation and Unified Reward Feedback	arXiv '26	-	-
`Any2Poster`	Any2Poster: Any-Source Poster Generation Across Modalities and Domains	arXiv '26	-	-
`PosterMELD`	PosterMELD: Multi-Agent Paper-to-Poster Generation for Controllable Design Diversity with Editable Print-Ready Outputs	arXiv '26	-	-

Paper2Slides

Model	Paper	Venue	Website	GitHub

`DOC2PPT`	DOC2PPT: Automatic Presentation Slides Generation from Scientific Documents	AAAI '22	-	-
`PPTAgent`	PPTAgent: Generating and Evaluating Presentations Beyond Text-to-Slides	EMNLP '25	-
`AutoPresent`	AutoPresent: Designing Structured Visuals from Scratch	CVPR '25	-	-
`Paper2Slides`	Paper2Slides: From Paper to Presentation in One Click	GitHub '25	-
`Auto-Slides`	Auto-Slides: An Interactive Multi-Agent System for Creating and Customizing Research Presentations	arXiv '25	-	-
`PASS`	PASS: Presentation Automation for Slide Generation and Speech	arXiv '25	-	-
`SlideGen`	SlideGen: Collaborative Multimodal Agents for Scientific Slide Generation	arXiv '25	-	-
`Talk to Your Slides`	Talk to Your Slides: Efficient Slide Editing Agent	arXiv '25	-	-
`SlideTailor`	SlideTailor: Personalized Presentation Slide Generation for Scientific Papers	AAAI '26	-
`DeepPresenter`	DeepPresenter: Environment-Grounded Reflection for Agentic Presentation Generation	arXiv '26	-
`Office Raccoon`	Office Raccoon	Web '26	-	-
`X+Slides`	X+Slides: Benchmarking Audience-Conditioned Slide Generation	arXiv '26	-	-
`SeaSlides`	SeaSlides: Semantic Abstraction Layer for Agentic Slide Generation	arXiv '26	-	-

Paper2Video

Model	Paper	Venue	Website	GitHub

`Preacher`	Preacher: Paper-to-Video Agentic System	ICCV '25	-
`Paper2Video`	Paper2Video: Automatic Video Generation from Scientific Papers	arXiv '25	-
`PresentAgent`	PresentAgent: Multimodal Agent for Presentation Video Generation	EMNLP '25	-
`PresentAgent-2`	PresentAgent-2: Towards Generalist Multimodal Presentation Agents	arXiv '26	-	-
`Paper2Video Talks`	A Good Talk Does not Look Like a Summary, It Teaches You! Measuring Takeaways from Paper-to-Video Talks	arXiv '26	-	-

Model	Paper	Venue	Website	GitHub

`Paper2Web`	Paper2Web: Let's Make Your Paper Alive!	arXiv '25	-
`ResearchStudio-Reel`	ResearchStudio-Reel: Automate the Last Mile of Research from Paper to Poster, Video, and Blog	arXiv '26	-	-
`I-WebGenBench`	I-WebGenBench: Evaluating Interactivity in LLM-Generated Scientific Web Applications	arXiv '26	-	-
`SciForge`	SciForge: An AI-Native, Multimodal Workbench for Scientific Discovery	arXiv '26	-	-

Fidelity and Adoption Assessment

Model	Paper	Venue	Website	GitHub

`PPTEval`	PPTAgent: Generating and Evaluating Presentations Beyond Text-to-Slides	EMNLP '25	-
`PresentQuiz`	Paper2Video: Automatic Video Generation from Scientific Papers	arXiv '25	-
`PresentEval`	PresentAgent: Multimodal Agent for Presentation Video Generation	EMNLP '25	-
`Sci. Comm. Correspondence`	Unifying Scientific Communication: Fine-Grained Correspondence Across Scientific Media	arXiv '26	-	-

9. End-to-End Systems

Fully Automated Research Systems

Model	Paper	Venue	Website	GitHub
`Gemini Co-Scientist`	Accelerating Scientific Research with Gemini in the Real-World	arXiv 2026	-	-
`AutoResearch`	AutoResearch: Insight In, Hallucination Out	arXiv 2026	-	-
`Eureka`	Eureka: Task-Conditioned Meta-Agent Orchestration for Scientific Discovery	arXiv 2026	-	-
`AutoResearch Diagnosis`	How Do Agents Fail on AutoResearch: End-to-End Diagnostic Evaluation on 100 Real-World Frontier Research Tasks	arXiv 2026	-	-

`ResearchTown`	ResearchTown: Simulator of Human Research Community	ICML 2025
`Agent Laboratory`	Agent Laboratory: Using LLM Agents as Research Assistants	arXiv 2025	-	-
`AgentRxiv`	AgentRxiv: Towards Collaborative Autonomous Research	arXiv 2025	-	-
`ARIS`	-	GitHub 2025	-
`freephdlabor`	Build Your Personalized Research Group: A Multiagent Framework for Continual and Interactive Science Automation	arXiv 2025	-	-
`SciMaster`	SciMaster: Towards General-Purpose Scientific AI Agents	arXiv 2025	-
-	Towards End-to-End Automation of AI Research	Nature 2026
`Idea2Story`	Idea2Story: An Automated Pipeline for Transforming Research Concepts into Complete Scientific Narratives	arXiv 2026	-	-
`UniScientist`	-	Web 2026	-	-
`ASI-Evolve`	-	GitHub 2026	-
`FARS`	-	Web 2026	-	-
`AutoResearchClaw`	-	GitHub 2026	-
`CORAL`	CORAL: Towards Autonomous Multi-Agent Evolution for Open-Ended Discovery	arXiv 2026	-
`AutoSOTA`	AutoSOTA: An End-to-End Automated Research System for State-of-the-Art AI Model Discovery	arXiv 2026	-
`AiScientist-LH`	Toward Autonomous Long-Horizon Engineering for ML Research	arXiv 2026	-
`OpenResearcher (2026)`	OpenResearcher: A Fully Open Pipeline for Long-Horizon Deep Research Trajectory Synthesis	arXiv 2026	-
`Aletheia`	Towards Autonomous Mathematics Research	arXiv 2026	-
`AutoSci`	AutoSci: A Memory-Centric Agentic System for the Full Scientific Research Lifecycle	arXiv 2026	-	-
`ScientistOne`	ScientistOne: Towards Human-Level Autonomous Research via Chain-of-Evidence	arXiv 2026	-	-
`Arbor`	Toward Generalist Autonomous Research via Hypothesis-Tree Refinement	arXiv 2026	-	-
`Agon`	Agon: An Autonomous Large-Scale Omnidisciplinary Research System Built on Prompt Economy	arXiv 2026	-
`ResearchClawBench`	ResearchClawBench: A Benchmark for End-to-End Autonomous Scientific Research	arXiv 2026	-	-
`Act as Real Researcher`	Act As a Real Researcher: A Suite of Benchmarks Evaluating Frontier LLMs and Agentic Harnesses in Research Lifecycle	arXiv 2026	-	-
`ResearchArena`	How Far Are We From True Auto-Research?	arXiv 2026	-	-
`NVAITC AI Sci.`	NVAITC AI Scientist: A Governed End-to-End Research System -- A Hypertension GWAS Case Study	arXiv '26	-	-
`DeepResearch Agent Sys.`	DeepResearch Agent System	arXiv '26	-	-
`ScienceFlow`	ScienceFlow: A long-horizon agent for ML research, scientific discovery and beyond	arXiv '26	-	-
`Spark-to-Paper`	Spark-to-Paper: End-to-End Research Paper Generation as a Composable Skill	arXiv '26	-	-
`OmniScientist`	OmniScientist: An Omni-Modal Omni-Discipline AI Scientist	arXiv '26	-	-

Domain-Specific Systems

Model	Paper	Venue	Website	GitHub
`AutoSR`	AutoSR: Automatic Symbolic Regression by Searching Research States	arXiv 2026	-	-
`The AI Engineer`	Closed-loop AI achieves certifiable engineering design	arXiv 2026	-	-

`AlphaFold 3`	Accurate Structure Prediction of Biomolecular Interactions with AlphaFold 3	Nature 2024		-
`Medical AI Scientist`	Towards a Medical AI Scientist	arXiv 2026	-	-
`Cognitive Scientist`	Closing the Loop to Discover Psychological Theories with an Automated Cognitive Scientist	arXiv '26	-	-
`Molecular Closed-Loop`	Closed-loop Auto Research for Molecular Property Prediction: Discovering and Certifying Generalizable Improvements	arXiv '26	-	-
`Auto Research (Materials)`	Auto Research for Materials: Auditable AI-Scientist Workflows with Held-Out Transfer	arXiv '26	-	-
`OmniQEC`	OmniQEC: discovering practical quantum error-correcting codes by an AI scientist	arXiv '26	-	-
`Andy`	Andy: A Mathematical Agent for Rigorous Proof and Autonomous Research	arXiv '26	-	-
`BaT`	BaT: Towards Self-Evolving Medical Research Agent with Stage Rubrics	arXiv '26	-	-
`Agentic Sci. Community`	An Agentic AI Scientific Community for Automated Neural Operator Discovery	arXiv '26	-	-
`WARA`	WARA: A Closed-Loop Multi-Agent Framework for Wireless Optimization Autoresearch	ICCC '26	-	-

Evolutionary & Self-Improving Systems

Model	Paper	Venue	Website	GitHub

`ShinkaEvolve`	ShinkaEvolve: Towards Open-Ended and Sample-Efficient Program Evolution	arXiv 2025	-
`Darwin Godel Machine`	Darwin Godel Machine: Open-Ended Evolution of Self-Improving Agents	arXiv 2025	-
`EvoMaster`	EvoMaster: A Foundational Evolving Agent Framework for Agentic Science at Scale	arXiv 2026	-	-
`Self-Driving Lab`	Compressing the Validation Bottleneck: An Agentic Self-Driving Lab for Scientific Discovery	arXiv '26	-	-
`Meta-Reflection`	Autonomous Scientific Discovery via Iterative Meta-Reflection	arXiv '26	-	-
`Project2Task`	Project2Task: Graph-Guided Project-Level Planning for Autonomous Research	arXiv '26	-	-
`Adaptive Inquiry`	Beyond Solution-Centric Search: Adaptive Inquiry and Knowledge Revision for Autonomous ML Engineering	arXiv '26	-	-
`CausalForge`	CausalForge: A Formally Grounded, Self-Improving Agentic Framework for Automated Research in Causal Inference	arXiv '26	-	-
`World-Model Scaling`	Scaling Automatic Research Agents via World Models	arXiv '26	-	-
`Research Preference Models`	AI Research Preference Models	arXiv '26	-	-

Research Platforms & Infrastructure

Model	Paper	Venue	Website	GitHub
`Symposium`	Symposium: Trust via Auditable Records for Communities of AI Scientist Agents	arXiv 2026	-	-

`Towards an AI co-scientist`	Towards an AI co-scientist	arXiv 2025	-	-
`PiFlow`	PiFlow: Principle-aware Scientific Discovery with Multi-Agent Collaboration	arXiv 2025	-	-
`LabClaw`	-	Web 2026	-	-
-	OpenAI Is Throwing Everything into Building a Fully Automated Researcher	MIT TR 2026		-
`XScientist`	XScientist: A Git-Like Research Protocol for Long-Running Autonomous Scientific Discovery	arXiv '26	-	-
`Auditable Records`	From Trajectories to Evidence: Auditable Experimental Records for Industrial Research Agents	arXiv '26	-	-
`PEARL`	PEARL: Auditable Repair for Scientific Reasoning Graph Extraction	arXiv '26	-	-
`IdeaTrail`	IdeaTrail: Full-Process Agent Trajectories for Scientific Ideation	arXiv '26	-	-
`EviGraph`	EviGraph: Evidence-Guided Autonomous Research Agents	arXiv '26	-	-
`Discovery Environments`	Scaling Scientific Discovery Environments for Turn-Level Agentic RL	arXiv '26	-	-
`Quantum Theorem Bench`	Benchmarking Agents for Proving Theorems in Quantum Algorithms and Quantum Information	arXiv '26	-	-
`SciDiscovery Readiness`	Are LLMs Ready for Scientific Discovery? A Capability-Oriented Benchmark for AI Scientists	arXiv '26	-	-
`ARAC`	ARAC: Benchmarking Auto-Research's Alignment and Completeness on End-to-End Researchs	arXiv '26	-	-
`Beyond Final Scores`	Beyond Final Scores: A Systematic Evaluation of Agents for Long-Horizon AI Research and Development	arXiv '26	-	-
`Replication Training`	Training AI Scientists to Replicate Research	arXiv '26	-	-
`Rubric Meta-Eval`	Can LLMs Write Reliable Rubrics? A Meta-Evaluation for Experiment Reproduction	arXiv '26	-	-
`Fast-Moving Domains`	Adversarial Fast-Moving Real-World Domains as Test Beds for Benchmarking AI Scientist Capabilities	arXiv '26	-	-
`AutoWorldModel-Bench`	AutoWorldModel-Bench: A State-Centric Benchmark for Automated World-Model Research	arXiv '26	-	-
`Scientific Memory`	Beyond Memory Leaderboards: Evaluating Scientific Memory as Budgeted Context Restoration	arXiv '26	-	-
`SciHazard`	SciHazard: A Benchmark for Measuring Scientific Safety Risks with Decomposed Harm Scoring	arXiv '26	-	-
`Science Edge Eval.`	Science Edge Evaluation: SEE the Missing Step Toward Real Scientific Discovery	arXiv '26	-	-

10. Societal & Critical Perspectives

Model	Paper	Venue	Website	GitHub
-	Science Done on a Machine by a Machine: AI Agents in Computational Chemistry	arXiv 2026	-	-
-	Bayesian Optimization for Self-Driving Materials Laboratories: From Algorithms to Physics-Informed Workflows	arXiv 2026	-	-
-	LLM assisted writing deserves empirical evaluation	arXiv 2026	-	-
-	A Metric with Positive Sectional Curvature on $S^2\times S^3$	arXiv 2026	-	-
-	Weak-Type Bounds for Convolution on the Boolean Hypercube	arXiv 2026	-	-
-	Quo Vadis? Scientific Discovery in the Age of Artificial Intelligence	Theory of Science	-	-
-	Are LLMs becoming similarly creative? Evidence from three years of models	arXiv 2026	-	-

-	Navigating the Jagged Technological Frontier	Org. Sci. 2025		-
-	Reassessing Academic Integrity in the Age of AI	SSH Open 2025		-
`The AI Deskilling Paradox`	The AI Deskilling Paradox	CACM 2025		-
`Hidden Pitfalls of AI Scientist Systems`	The More You Automate, the Less You See: Hidden Pitfalls of AI Scientist Systems	arXiv 2025	-	-
`Rethinking Science in the Age of AI`	Rethinking Science in the Age of Artificial Intelligence	arXiv 2025	-	-
-	Measuring AI Ability to Complete Long Tasks	METR 2025		-
-	Towards a Science of Scaling Agent Systems	arXiv 2025	-	-
-	Artificial Intelligence Tools Expand Scientists' Impact but Contract Science's Focus	Nature 2026		-
-	[](https://www.cell.com/patterns/fulltext/S2666-3899(25) AI for Scientific Discovery is a Social Problem	Patterns 2026	[](https://www.cell.com/patterns/fulltext/S2666-3899(25)	-
`Research Integrity in the Age of AI`	Research Integrity and Academic Authority in the Age of Artificial Intelligence: From Discovery to Curation?	arXiv 2026	-	-
`SciSciGPT`	SciSciGPT: Advancing Human-AI Collaboration in the Science of Science	Nature CS 2026		-
`SimStep`	SimStep: Chain-of-Abstractions for Incremental Specification and Debugging of AI-Generated Interactive Simulations	arXiv 2025	-	-
`ConvoLearn`	ConvoLearn: A Learning Sciences Grounded Dataset for Fine-Tuning Dialogic AI Tutors	arXiv 2026	-	-
`AFIM: Academic Fraud Inclination Metric`	AFIM: Academic Fraud Inclination Metric	Web 2026		-
-	AI Researchers' Views on Automating AI R&D and Intelligence Explosions	arXiv 2026	-	-
-	AI Scientists Are Changing Research	Nature 2026		-
`Learning by Creating (Talk)`	Learning by Creating: A Human-Centered Vision for AI in Education	Talk 2026		-
`AI Sci. No Reasoning`	AI scientists produce results without reasoning scientifically	arXiv 2026	-	-
`Not Built for Autonomy`	Agentic AI Scientists Are Not Built For Autonomous Scientific Discovery	arXiv 2026	-	-
`Workflow != Closure`	Workflow Closure Is Not Scientific Closure in Auto-Research Systems	arXiv 2026	-	-
`PseudoBench`	PseudoBench: Measuring How Agentic Auto-Research Fuels Pseudoscience	arXiv 2026	-	-
`SciIntegrity-Bench`	SciIntegrity-Bench: A Benchmark for Evaluating Academic Integrity in AI Scientist Systems	arXiv 2026	-	-
-	Abduction Without a Body? Representational Grounding and the Abduction Loop for Scientific Hypothesis Generation	arXiv '26	-	-
-	Visualizing Graph-to-Answer Mechanism Recovery in Materials-Science Hypothesis Generation	arXiv '26	-	-
-	Generative AI use in Statistical Research: A Literature Review and Code Generation Case Study	arXiv '26	-	-
-	AI's Capability in Assisting Scientific Research in Physics, Astrophysics, and Cosmology I: Literature Review	arXiv '26	-	-
-	Scientific Knowledge Discovery in the Age of Large Language Models	arXiv '26	-	-
-	Is Deep Research Reliable? Misleading Knowledge Induces False Conclusions	arXiv '26	-	-
-	Diagnosing Search Behavior and Failure Modes in Long-Horizon Search Agents	arXiv '26	-	-
-	A Pathway to General-Purpose Scientific AI: Multimodal Comprehension of Scientific Images	arXiv '26	-	-
-	Position: AI Agents in Scientific Teams Should Be Studied as Human-Agent Systems	arXiv '26	-	-
-	The Past and Future of AI Scientists	arXiv '26	-	-
-	Efficiency Matters in Autonomous Research	arXiv '26	-	-
-	Agentic Auto-Research is Fuzz Testing	arXiv '26	-	-
-	Mechanist: AI as a Scientific Instrument for Discovering the Mechanisms of Intelligence	arXiv '26	-	-
-	An AI Scientist that Doesn't Drift: Taste, Structure, and Falsifiable Findings in a Quadruped Navigation Research Loop	arXiv '26	-	-
-	Long-Horizon Autonomous Architecture Research with a Language-Model Agent: A Behavioural Case Study	arXiv '26	-	-
-	Stress-testing large language model agents in a robotic chemistry laboratory	arXiv '26	-	-

11. Surveys & Curated Lists

Model	Paper	Venue	Website	GitHub

`LLM4SR`	LLM4SR: A Survey on Large Language Models for Scientific Research	arXiv 2025	-	-
`From Automation to Autonomy`	From Automation to Autonomy: A Survey on Large Language Models for Scientific Discovery	arXiv 2025	-	-
`AI4Research`	AI4Research: A Survey of Artificial Intelligence for Scientific Research	arXiv 2025	-	-
`A Survey of AI Scientists`	A Survey of AI Scientists	arXiv 2025	-	-
-	Large Language Models for Scientific Idea Generation: A Creativity-Centered Survey	arXiv 2025	-	-
-	Large Language Models for Automated Scholarly Paper Review: A Survey	Inf. Fusion 2025		-
`AutoResearch Survey`	What's Missing in Autonomous Research? A Systematization of Systems, Benchmarks, and Verification	Web 2026		-

12. Tools & GitHub Repos

Curated Lists

Repository	Stars	Description
Awesome-Deep-Research		Up-to-date collection of agentic deep research resources
Awesome-Scientific-Language-Models		Survey of scientific LLMs (EMNLP'24)
Awesome-LLM-Scientific-Discovery		Three-level autonomy framework (EMNLP'25)
Awesome-AI-Scientist-Papers		Resources on AI Scientist systems
Awesome-Auto-Research-Tools		Automated research tools catalog
awesome-autoresearch		Autonomous improvement loops and research agents
awesome-ai-research-writing		Prompt templates and agent skills for AI-assisted writing

Idea Generation

Repository	Stars	Description
Virtual-Scientists		VirSci: multi-agent collaborative idea generation (ACL'25)
ResearchAgent		Iterative idea proposal with reviewing agents

Literature Review

Repository	Stars	Description
paper-qa		PaperQA2: superhuman RAG for scientific Q&A
local-deep-research		Fully local deep research
researchgpt		Conversational interaction with research papers
gpt-researcher		Autonomous agent for comprehensive online research
AutoSurvey		Automated comprehensive literature surveys
storm		Wikipedia-style article generation (STORM)
lune-mcp-server		MCP client for the hosted Lune Research corpus: paper search, citation traversal, evidence extraction, quote-backed claim verification (API key required)

Coding & Experiments

Repository	Stars	Description
autoresearch (Karpathy)		Autonomous ML experiments, ~12 exp/hour overnight
Paper2Code		Multi-agent ML paper to code transformation
RD-Agent		Microsoft's LLM framework for autonomous data science
MLAgentBench		13 end-to-end ML experimentation tasks
SWE-bench		Real-world GitHub issue resolution benchmark
Thoth		Dashboard-first Claude Code and Codex runtime for durable autoresearch runs, work-item locks, ledgers, and reviewable verdicts

Peer Review

Repository	Stars	Description
paper-reviewer		arXiv paper reviews + blog posts
ai-peer-review		Multi-LLM reviews + meta-review synthesis
openreviewer		Llama-8B fine-tuned on 79K expert reviews

⬆ Back to Top

Last updated: 2026-08-31 · Maintained by WorldBench

agent

agentic-ai

ai-research

ai-scientist

auto-research

large-language-models

llm

multi-agent-system

rag

Contributors

20 commits

1 commits

1 commits

1 commits

Similar repos

ResearAI/Awesome-AI-Scientist

This is a survey of research on AI scientists, AI researchers, AI engineers, and a series of…

314

du-nlp-lab/LLM4SR

LLM for Scientific Research Survey

133

aiming-lab/AutoResearchClaw

Fully autonomous & self-evolving research from idea to paper. Chat an Idea. Get a Paper. 🦞

14,506

Omni-Scientist/Awesome-AI-Scientist

🧪 Awesome list of AI Scientist papers, systems, benchmarks, datasets and open-source platforms.

100

OSU-NLP-Group/awesome-agents4science

A curated list of papers on LLMs and agents for scientific research and development

GeminiLight/awesome-agentic-artifact-creation

A curated paper list on agentic artifact creation, an emerging paradigm in which AI agents…

alvinunreal/awesome-autoresearch

A curated list of autonomous improvement loops, research agents, and autoresearch-style systems…

2,539

EvoMap/AutoResearch

AI/ML research agents from idea to paper-ready evidence. An EvoMap open-source project.

3,187

Languages

HTML

100.0%

worldbench/awesome-ai-auto-research

🔥 A Survey on AI Auto-Research

HTML

530

26 commits

updated Sep 1, 2026

worldbench.github.io/awesome-ai-auto-research

See the code

README

:sunglasses: Awesome AI Auto-Research

:robot: AI Auto-Research


	Phase 1: Creation Generating novel research ideas, searching and synthesizing literature, running coding experiments, and creating publication-quality tables and figures. This phase spans Idea Generation, Literature Review, Coding & Experiments, and Tables & Figures.
	Phase 2: Writing Drafting, editing, and polishing academic manuscripts. AI assistance ranges from semi-automated grammar and citation tools to fully automated paper generation — the most commercially mature yet ethically contested stage.
	Phase 3: Validation Automated peer review generation, reviewer-paper matching, review quality assessment, and AI-assisted author rebuttals. This phase covers Peer Review and Rebuttal & Revision.
	Phase 4: Dissemination Converting papers into slides, posters, videos, websites, and social media content. Each output format targets a different audience and demands its own design logic and AI tool chain.

For additional details, kindly refer to our :books: Paper and :earth_asia: Project Page.

:books: Citation

If you find this work helpful for your research, please kindly consider citing our paper:

@article{survey-ai-auto-research,
  title   = {{AI} for {Auto-Research}: Roadmap \& User Guide},
  author  = {Kong, Lingdong and Sun, Xian and Chow, Wei and Li, Linfeng and Lin, Kevin Qinghong and Zhang, Xuan Billy
             and Wang, Song and Li, Rong and Wu, Qing and Gao, Wei and Wang, Yingshuo and Xie, Shaoyuan
             and Liu, Jiachen and Qu, Leigang and Li, Shijie and Ng, Lai Xing and Cottereau, Benoit R.
             and Liu, Ziwei and Chua, Tat-Seng and Ooi, Wei Tsang},
  journal = {arXiv preprint arXiv:2605.18661},
  year    = {2026}
}

0. Background

1. Idea Generation
2. Literature Review & Paper Search
3. Coding & Experimentation
4. Tables & Figures
5. Paper Writing
6. Peer Review
7. Rebuttal
8. Dissemination (Paper2X)
9. End-to-End Systems
10. Societal & Critical Perspectives
11. Surveys & Curated Lists
12. Tools & GitHub Repos

1. Idea Generation

LLM Internal Knowledge-Based Generation

Model	Paper	Venue	Website	GitHub

`Chain of Ideas`	Chain of Ideas: Revolutionizing Research Via Novel Idea Development with LLM Agents	arXiv '24	-
`ResearchAgent`	ResearchAgent: Iterative Research Idea Generation over Scientific Literature with Large Language Models	NAACL '25	-
`SciMON`	SciMON: Scientific Inspiration Machines Optimized for Novelty	ACL '24	-
`Idea Gen Agent`	Can LLMs Generate Novel Research Ideas? A Large Scale Human Study with 100+ NLP Researchers	arXiv '24	-	-
`IRIS`	IRIS: Interactive Research Ideation System for Accelerating Scientific Discovery	ACL '25	-
`Spark`	Spark: A System for Scientifically Creative Idea Generation	ICCC '25	-	-
`Diverse Hypo. Search`	Towards Diverse Scientific Hypothesis Search with Large Language Models	arXiv '26	-	-
`Tree-of-Ideas`	Tree-of-Ideas: Automated Research Ideation via Cross-Trajectory Reasoning over Scholarly Evolution	arXiv '26	-	-
`IDEAgent`	IDEAgent: Agentic Quality-Diversity Search for Research Idea Generation	arXiv '26	-	-

External Signal-Driven Generation

Model	Paper	Venue	Website	GitHub
`SGHA`	SGHA: Evidence-Grounded Research Problem Discovery with Local Language Models	arXiv '26	-	-
`MAIL`	MAIL: Memory-driven, Adaptive, Incremental, and Literature-grounded Framework for Hypothesis Generation in Chemistry	arXiv '26	-	-

`MOOSE-Chem`	MOOSE-Chem: Large Language Models for Rediscovering Unseen Chemistry Scientific Hypotheses	ICLR '25	-	-
`Nova`	Nova: An Iterative Planning and Search Approach to Enhance Novelty and Diversity of LLM Generated Ideas	arXiv '24	-	-
`SciAgents`	SciAgents: Automating Scientific Discovery through Multi-Agent Intelligent Graph Reasoning	arXiv '24	-
`SciPIP`	SciPIP: An LLM-based Scientific Paper Idea Proposer	arXiv '24	-
`IdeaSynth`	IdeaSynth: Iterative Research Idea Development Through Evolving and Composing Idea Facets with Literature-Grounded Feedback	CHI '25	-	-
`MOOSE-Chem2`	MOOSE-Chem2: Exploring LLM Limits in Fine-Grained Scientific Hypothesis Discovery via Hierarchical Search	NeurIPS '25	-	-
`HALO`	HALO: Interactive Co-abductive Reasoning in Scientific Hypothesis Generation	arXiv '26	-	-
`TCA-SIR`	TCA-SIR: Learning Target-Conditioned Abstractions for Scientific Inspiration Retrieval	arXiv '26	-	-
`ECLAIR`	ECLAIR: A Causally-Grounded AI Framework for Scientific Discovery in Empirical Software Engineering	arXiv '26	-	-

Multi-Agent Collaborative Generation

Model	Paper	Venue	Website	GitHub
`HypoForge`	HypoForge: A Self-Improving Multi-Agent Framework for Automated Hypothesis Generation and Testing via Scientific Skill Learning	arXiv '26	-	-

`Combi. Creativity`	Combi. Creativity	arXiv '24	-	-
`Deep Ideation`	Deep Ideation: Designing LLM Agents to Generate Novel Research Ideas on Scientific Concept Network	arXiv '25	-
`VirSci`	Many Heads Are Better Than One: Improved Scientific Idea Generation by A LLM-Based Multi-Agent System	ACL '25	-
`Multi-Agent Dial.`	Multi-Agent Dial.	SIGDIAL '25	-	-
`Artificial Hivemind`	Artificial Hivemind: The Open-Ended Homogeneity of Language Models (and Beyond)	NeurIPS '25	-	-
`Auditable AI Sci.`	Toward Auditable AI Scientists: A Hypothesis Evolution Protocol for LLM Agents	arXiv '26	-	-
`Diverse Personalized Ideation`	Diversifying Personalized Research Ideation against AI-Induced Homogenization	arXiv '26	-	-

Novelty and Feasibility Assessment

Model	Paper	Venue	Website	GitHub
`RATIO`	RATIO: A Benchmark for Retrieval Across Typed Ideation Operations in Scientific Literature	arXiv '26	-	-
`Lit2Test`	What Proves You Wrong: Benchmarking Language Models on Falsifiable Research Ideation	arXiv '26	-	-
`Energy Scoring`	Do LLMs Know a Good Hypothesis When They See One? Logit-Based Energy Scoring Outperforms Prompted LLM-as-Judge for Scientific Hypothesis Ranking	arXiv '26	-	-
`Think-Probe-Respond`	Think-Probe-Respond: Improving Large Language Models as Judges of Research Idea Novelty	EMNLP '26	-	-

`IdeaBench`	LiveIdeaBench: Evaluating LLMs' Scientific Creativity and Idea Generation with Minimal Context	KDD '25	-	-
`LiveIdeaBench`	LiveIdeaBench: Evaluating LLMs' Scientific Creativity and Idea Generation with Minimal Context	arXiv '24	-	-
`AI Idea Bench 2025`	AI Idea Bench 2025: AI Research Idea Generation Benchmark	arXiv '25	-
`HeurekaBench`	HeurekaBench: A Benchmarking Framework for AI Co-scientist	ICLR '26	-
`ResearchBench`	ResearchBench: Benchmarking LLMs in Scientific Discovery via Inspiration-Based Task Decomposition	ACL '26	-	-
`HindSight`	HindSight: Evaluating LLM-Generated Research Ideas via Future Impact	arXiv '26	-	-
`Rubric Rewards`	Training AI Co-Scientists Using Rubric Rewards	arXiv '25	-	-
`DeepInnovator`	DeepInnovator: Triggering the Innovative Capabilities of LLMs	arXiv '26	-
`FlowPIE`	FlowPIE: Test-Time Scientific Idea Evolution with Flow-Guided Literature Exploration	arXiv '26	-	-
`SoundnessBench`	SoundnessBench: Can Your AI Scientist Really Tell Good Research Ideas from Bad Ones?	arXiv '26	-	-
`LLM-Judge Novelty`	On the Limits of LLM-as-Judge for Scientific Novelty Assessment	arXiv '26	-	-
`LigBench`	LigBench: A Unified and Human-Aligned Benchmark for LLM-based Research Idea Generation	arXiv '26	-	-
`Reconstruction`	Reconstruction: A Blind Benchmark for Recovering Research Ideas from Pre-Publication Bibliographies	arXiv '26	-	-

2. Literature Review & Paper Search

Literature Retrieval

Model	Paper	Venue	Website	GitHub
`ITER`	ITER: Interaction-Aware Retrieval for Agentic Search	arXiv '26	-	-
`Multi-Aspect Retrieval`	Can Retrievers Find the Same Paper from Different Aspects? A Multi-Aspect Full-Paper Scientific Retrieval Benchmark	arXiv '26	-	-

`CiteME`	CiteME: Can Language Models Accurately Cite Scientific Claims?	arXiv '24	-	-
`LitLLM`	LitLLM: A Toolkit for Literature Review with Large Language Models	arXiv '24	-	-
`LitSearch`	LitSearch: A Retrieval Benchmark for Scientific Literature Search	arXiv '24	-
`PaperQA2`	Language Agents Achieve Superhuman Synthesis of Scientific Knowledge	arXiv '24	-
`OpenResearcher`	OpenResearcher: Unleashing AI for Accelerated Scientific Research	EMNLP '24	-	-
`PaSa`	PaSa: An LLM Agent for Comprehensive Academic Paper Search	arXiv '25	-
`Self-Evolving Retrieval`	Towards Self-Evolving Agentic Literature Retrieval	arXiv '26	-	-
`MasterSet`	MasterSet: A Large-Scale Benchmark for Must-Cite Citation Recommendation in the AI/ML Literature	arXiv '26	-	-
`Search, Inspect, Fetch`	Search, Inspect, Fetch: Exploiting Structure-Aware Boolean Retrieval for Deep-Research Agents	arXiv '26	-	-
`Rubric Reranker`	Training Documents Reranker with Search Rubrics for Deep Research Agent	arXiv '26	-	-
`Personalized DR Refinement`	Personalized Deep Research Query Refinement with Graph-Scaffolded Evidence Grounding	arXiv '26	-	-

Model	Paper	Venue	Website	GitHub
`DAS`	Deep Academic Survey: Stateful Agentic Closed-Loop Paradigm for Academic Survey Automation	arXiv '26	-	-
`Tree-of-Concerns`	Tree-of-Concerns: Hierarchical Multi-Agent Debate for Unstated-Limitation Extraction in Scientific Critique	EMNLP '26	-	-

`ChatPaper`	ChatPaper: Use LLM to summarize papers	GitHub '23	-
`PaperQA`	PaperQA: Retrieval-Augmented Generative Agent for Scientific Research	arXiv '23	-
`AutoSurvey`	AutoSurvey: Large Language Models Can Automatically Write Surveys	arXiv '24	-
`GPT Researcher`	GPT Researcher: Autonomous Agent for Comprehensive Online Research	GitHub '24	-
`LLMs for Lit. Review`	LLMs for Lit. Review	arXiv '24	-	-
`STORM`	Assisting in Writing Wikipedia-like Articles From Scratch with Large Language Models	arXiv '24	-
`Agentic AutoSurvey`	Agentic AutoSurvey: Let LLMs Survey LLMs	arXiv '25	-	-
`Citegeist`	Citegeist: Automated Generation of Related Work Analysis on the arXiv Corpus	arXiv '25	-	-
`IterSurvey`	IterSurvey: Deep Literature Survey Automation with an Iterative Workflow	arXiv '25	-
`LiRA`	LiRA: A Multi-Agent Framework for Reliable and Readable Literature Review Generation	arXiv '25	-	-
`SurveyForge`	SurveyForge: On the Outline Heuristics, Memory-Driven Generation, and Multi-dimensional Evaluation for Automated Survey Writing	arXiv '25	-
`SurveyG`	SurveyG: A Multi-Agent LLM Framework with Hierarchical Citation Graph for Automated Survey Generation	arXiv '25	-	-
`SurveyX`	SurveyX: Academic Survey Automation via Large Language Models	arXiv '25	-	-
`InteractiveSurvey`	InteractiveSurvey: An LLM-based Personalized and Interactive Survey Paper Generation System	arXiv '25	-
`CiteLLM`	CiteLLM: An Agentic Platform for Trustworthy Scientific Reference Discovery	arXiv '26	-	-
`DeepSurvey`	DeepSurvey: Enhancing Analytical Depth and Citation Reliability in Automated Survey Generation	arXiv '26	-	-
`STRUCTSURVEY`	STRUCTSURVEY: Structured Agentic Retrieval for Automated Survey Paper Generation	arXiv '26	-	-

Deep Research Agents

Model	Paper	Venue	Website	GitHub
`Crase`	Structurally-bounded Agentic Graph Exploration for Evidence-Grounded Scholarly DeepSearch	arXiv '26	-	-
`DeepWeaver`	DeepWeaver: Bridging the Evidence Synthesis Gap in Open-Ended Question Answering	arXiv '26	-	-
`AgentR`	AgentR A Stateful and Recovery-Aware Software Architecture for LLM-based Auditable Workflows	arXiv '26	-	-

`ASReview`	An Open Source Machine Learning Framework for Efficient and Transparent Systematic Reviews	Nature MI '21	-
`CHIME`	CHIME: LLM-Assisted Hierarchical Organization of Scientific Studies for Literature Review Support	arXiv '24	-	-
`DeepResearch-Agent`	DeepResearchAgent: A Hierarchical Multi-Agent System for Deep Research	GitHub '25	-
`DeerFlow`	DeerFlow: A Deep Research Framework Orchestrating Sub-Agents, Memory, and Sandboxes	GitHub '25	-
`OpenScholar`	OpenScholar: Synthesizing Scientific Literature with Retrieval-Augmented LMs	Nature '26	-	-
`AutoAgent`	AutoAgent	arXiv '25	-	-
`Tongyi DeepResearch`	Tongyi DeepResearch	GitHub '25	-
`O-Researcher`	O-Researcher: An Open Ended Deep Research Model via Multi-Agent Distillation and Agentic RL	arXiv '26	-	-
`OpenResearcher`	OpenResearcher: Unleashing AI for Accelerated Scientific Research	arXiv '26	-
`AREX`	AREX: Towards a Recursively Self-Improving Agent for Deep Research	arXiv '26	-	-
`Predictive Navigation`	Deep Research Pretraining via Predictive Navigation	arXiv '26	-	-
`On-Device DR (4B)`	On-Device Deep Research at 4B: Exposure Bounds Faithfulness, Retrieval Bounds Coverage	arXiv '26	-	-
`Carnot`	Carnot: Interpretable, Interactive, and Optimized Execution of Deep Research Queries	VLDB '26	-	-
`Marginal Value Est.`	Not Worth Another Token: Marginal Value Estimation for Efficient Deep Research Agents	arXiv '26	-	-
`Retrieval-Aware Control`	When Deep Research Agents Stagnate: Enhancing Reasoning with Retrieval-Aware Agent Control	arXiv '26	-	-
`Analogical Deep Research`	Analogical Deep Research: Retrieving and Integrating Historical Analogies for Foresight Analysis	arXiv '26	-	-
`Plato-Bio`	Plato-Bio: verification-first biological novelty screening with temporal rediscovery and structural benchmarks	arXiv '26	-	-
`Albilich`	Albilich: Steerable Proof-State Orchestration for LLM-Based Mathematical Research with CAS Integration	arXiv '26	-	-

Retrieval and Synthesis Quality Assessment

Model	Paper	Venue	Website	GitHub
`IBIS`	From Inertia to Objectivity: Improving Deep Research Agents with Noise Isolation	EMNLP '26	-	-
`Agent to Blame`	Who is the Agent to Blame? Localizing Faithfulness and Citation Mistakes in Agentic Deep Research	EMNLP '26	-	-

`DeepScholar-Bench`	DeepScholar-Bench: A Live Benchmark and Automated Evaluation for Generative Research Synthesis	arXiv '25	-
`ReportBench`	ReportBench: Evaluating Deep Research Agents via Academic Survey Tasks	arXiv '25	-
`IDRBench`	IDRBench: Interactive Deep Research Benchmark	arXiv '26	-	-
`ScholarGym`	ScholarGym: Benchmarking Large Language Model Capabilities in the Information-Gathering Stage of Deep Research	arXiv '26	-	-
`SciNetBench`	SciNetBench: A Relation-Aware Benchmark for Scientific Literature Retrieval Agents	arXiv '26	-	-
`AutoResearchBench`	AutoResearchBench: Benchmarking AI Agents on Complex Scientific Literature Discovery	arXiv '26	-	-
`PaperMind`	PaperMind: Benchmarking Agentic Reasoning and Critique over Scientific Papers in Multimodal LLMs	arXiv '26	-	-
`DRNOISE`	DRNOISE: Benchmarking Deep Research Agents in Misleading Evidence Environments	arXiv '26	-	-
`HiEviDR-Bench`	HiEviDR-Bench: A Benchmark for Hierarchical Evidence Aggregation in Deep Research	arXiv '26	-	-
`SciExplore`	SciExplore: Evaluating Autonomous Agents from Scientific Navigation to Information Integration	arXiv '26	-	-
`WANDR`	WANDR: A Benchmark for Wide and Deep Research	arXiv '26	-	-
`QA-to-DR Bench`	From Simple QA to Deep Research: A Verifiable Benchmark Constructed through Iterative Task Evolution	arXiv '26	-	-

3. Coding & Experimentation

Code Generation

Model	Paper	Venue	Website	GitHub

`SWE-bench`	SWE-bench: Can Language Models Resolve Real-World GitHub Issues?	ICLR '24	-
`SWE-agent`	SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering	arXiv '24	-
`OpenHands`	OpenHands: An Open Platform for AI Software Developers as Generalist Agents	ICLR '25	-
`SWE-bench Pro`	SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?	arXiv '25	-	-
`SWE-EVO`	SWE-EVO: Benchmarking Coding Agents in Long-Horizon Software Evolution Scenarios	arXiv '25	-	-

Paper-to-Code

Model	Paper	Venue	Website	GitHub
`ReproAgent`	ReproAgent: Contract-Guided Paper-to-Code Reproduction	EMNLP '26	-	-
`DeepRepro`	DeepRepro: State-Aware Subplanning for Paper-to-Code Reproduction in Evolving Repositories	CIKM '26	-	-

`FunSearch`	Mathematical Discoveries from Program Search with Large Language Models	Nature '24	-
`SciCode`	SciCode: A Research Coding Benchmark Curated by Scientists	arXiv '24	-
`PaperBench`	PaperBench: Evaluating AI's Ability to Replicate AI Research	arXiv '25	-
`PaperCoder`	Paper2Code: Automating Code Generation from Scientific Papers in Machine Learning	arXiv '25	-
`ResearchCodeBench`	ResearchCodeBench: Benchmarking LLMs on Implementing Novel ML Research Code	arXiv '25	-	-
`SciReplicate-Bench`	SciReplicate-Bench: Benchmarking LLMs in Agent-driven Algorithmic Reproduction from Research Papers	arXiv '25	-

Experiment Execution & Orchestration

Model	Paper	Venue	Website	GitHub
`Praxist`	Praxist: From Experimental Artifacts to Solution Lineages	arXiv '26	-	-
`Skill-Based Baselines`	Can Coding Agents Build Robust Baselines? A Skill-Based Approach for Automating the Medical Imaging Model-Development Pipeline	MICCAI '26	-	-

`BioPlanner`	BioPlanner: Automatic Evaluation of LLMs on Protocol Planning	arXiv '23	-
`CRISPR-GPT`	CRISPR-GPT for Agentic Automation of Gene-Editing Experiments	arXiv '24	-	-
`DS-Agent`	DS-Agent: Automated Data Science by Empowering Large Language Models with Case-Based Reasoning	arXiv '24	-
`MLE-Bench`	MLE-Bench: Evaluating Machine Learning Agents on Machine Learning Engineering	arXiv '24	-	-
`MLAgentBench`	MLAgentBench: Evaluating Language Agents on Machine Learning Experimentation	arXiv '24	-
`MLR-Copilot`	MLR-Copilot: Autonomous Machine Learning Research based on Large Language Models Agents	arXiv '24	-	-
`AIDE`	AIDE: AI-Driven Exploration in the Space of Code	arXiv '25	-	-
`AlphaEvolve`	AlphaEvolve: A Coding Agent for Scientific and Algorithmic Discovery	arXiv '25	-	-
`AutoReproduce`	AutoReproduce: Automatic AI Experiment Reproduction with Paper Lineage	arXiv '25	-
`CURIE`	Curie: Toward Rigorous and Automated Scientific Experimentation with AI Agents	arXiv '25	-
`MLGym`	MLGym: A New Framework and Benchmark for Advancing AI Research Agents	arXiv '25	-	-
`MLR-Bench`	MLR-Bench: Evaluating AI Agents on Open-Ended Machine Learning Research	arXiv '25	-	-
`Execution-Grounded`	Towards Execution-Grounded Automated AI Research	arXiv '26	-	-
`Learn to Discover`	Learning to Discover at Test Time	arXiv '26	-	-
`AutoNumerics`	AutoNumerics: An Autonomous, PDE-Agnostic Multi-Agent Pipeline for Scientific Computing	arXiv '26	-
`SciNav`	SciNav: A General Agent Framework for Scientific Coding Tasks	arXiv '26	-	-
`FrontierScience`	FrontierScience: Evaluating AI's Ability to Perform Expert-Level Scientific Tasks	arXiv '26	-	-
`EvoDS`	EvoDS: Self-Evolving Autonomous Data Science Agent with Skill Learning and Context Management	arXiv '26	-	-
`AutoTTS`	LLMs Improving LLMs: Agentic Discovery for Test-Time Scaling	arXiv '26	-
`AutoScientists`	AutoScientists: Self-Organizing Agent Teams for Long-Running Scientific Experimentation	arXiv '26	-	-
`EurekAgent`	EurekAgent: Agent Environment Engineering is All You Need For Autonomous Scientific Discovery	arXiv '26	-	-

Code Correctness and Reproducibility Assessment

Model	Paper	Venue	Website	GitHub
`Experimental Fidelity`	Beyond Execution: Auditing Experimental Fidelity in LLM-Driven Scientific Research	arXiv '26	-	-

`DiscoveryBench`	DiscoveryBench: Towards Data-Driven Discovery with Large Language Models	arXiv '24	-
`DiscoveryWorld`	DiscoveryWorld: A Virtual Environment for Developing and Evaluating Automated Scientific Discovery Agents	arXiv '24	-
`InfiAgent-DABench`	InfiAgent-DABench: Evaluating Agents on Data Analysis Tasks	arXiv '24	-	-
`ScienceAgentBench`	ScienceAgentBench: Toward Rigorous Assessment of Language Agents for Data-Driven Scientific Discovery	arXiv '24	-	-
`LAB-Bench`	Lab-Bench: Measuring Capabilities of Language Models for Biology Research	arXiv '24	-
`KernelBench`	KernelBench: Can LLMs Write Efficient GPU Kernels?	arXiv '25	-
`TritonBench`	TritonBench: Benchmarking Large Language Model Capabilities for Generating Triton Operators	arXiv '25	-
`AstaBench`	AstaBench: Rigorous Benchmarking of AI Agents with a Scientific Research Suite	arXiv '25	-
`ResearchClawBench`	Probing Scientific General Intelligence of LLMs with Scientist-Aligned Workflows	arXiv '25	-
`EXP-Bench`	EXP-Bench: Can AI Conduct AI Research Experiments?	ICLR '26	-
`PostTrainBench`	PostTrainBench: Can LLM Agents Automate LLM Post-Training?	arXiv '26	-
`MLReplicate`	MLReplicate: Benchmarking Autonomous Research Systems for Machine Learning Reproducibility	arXiv '26	-	-
`BeyondSWE`	BeyondSWE: Can Current Code Agent Survive Beyond Single-Repo Bug Fixing?	arXiv '26
`NatureBench`	NatureBench: Can Coding Agents Match the Published SOTA of Nature-Family Papers?	arXiv '26	-	-
`SciCoQA`	SciCoQA: Quality Assurance for Scientific Paper--Code Alignment	ACL '26

4. Tables & Figures

Scientific Figure Generation

Model	Paper	Venue	Website	GitHub

`ChartGPT`	ChartGPT: Leveraging LLMs to Generate Charts from Abstract Natural Language	arXiv '23	-	-
`MatPlotAgent`	MatPlotAgent: Method and Evaluation for LLM-Based Agentic Scientific Data Visualization	arXiv '24	-	-
`CoDA`	CoDA: Agentic Systems for Collaborative Data Visualization	arXiv '25	-	-
`PlotGen`	PlotGen: Multi-Agent LLM-based Scientific Data Visualization via Multimodal Feedback	arXiv '25	-	-
`VIS-Shepherd`	VIS-Shepherd: Constructing Critic for LLM-based Data Visualization Generation	arXiv '25	-	-
`DiagramAgent`	From Words to Structured Visuals: A Benchmark and Framework for Text-to-Diagram Generation and Editing	CVPR '25	-	-
`StarVector`	StarVector: Generating Scalable Vector Graphics Code from Images and Text	CVPR '25	-	-
`VisCoder`	VisCoder: Fine-Tuning LLMs for Executable Python Visualization Code Generation	EMNLP '25	-	-
`AI-Generated Figures`	AI-Generated Figures	arXiv '26	-	-
`AutoFigure-Edit`	AutoFigure-Edit: Generating Editable Scientific Illustration	arXiv '26	-
`AutoFigure`	AutoFigure-Edit: Generating Editable Scientific Illustration	ICLR '26	-
`PaperBanana`	PaperBanana: Automating Academic Illustration for AI Scientists	arXiv '26	-	-
`SAIL`	Setting SAIL: Leveraging Scientist-AI-Loops for Rigorous Visualization Tools	arXiv '26	-	-
`Crafter`	Crafter: A Multi-Agent Harness for Editable Scientific Figure Generation from Diverse Inputs	arXiv '26	-	-
`DiagramRAG`	DiagramRAG: A Lightweight Framework to Retrieve Scientific Diagram for Figure Generation	arXiv '26	-	-
`GeoSVG-RL`	GeoSVG-RL: Geometry-Aware Reinforcement Learning for Layout-Constrained Text-to-SVG Diagram Generation	arXiv '26	-	-
`Can AI Draw Sci.`	Can AI Draw Science? A Benchmark for Evaluating Scientific Figure Generation by Text-to-Image and Multimodal Models	arXiv '26	-	-
`SciDiagramEdit`	SciDiagramEdit: Learning to Edit Scientific Diagrams from Paper Revisions	arXiv '26	-	-
`GenGA`	GenGA: Editable and Data-Grounded Graphical Abstract Generation for Academic Papers	arXiv '26	-	-

Table Understanding & Generation

Model	Paper	Venue	Website	GitHub

`ArxivDIGESTables`	ArxivDIGESTables: Synthesizing Scientific Literature into Tables using Language Models	EMNLP '24	-	-
`Chain-of-Table`	Chain-of-Table: Evolving Tables in Reasoning Chain for Table Understanding	ICLR '24	-	-
`ShowTable`	ShowTable: Unlocking Creative Table Visualization with Collaborative Reflection and Refinement	CVPR '26	-	-
`Table2LaTeX-RL`	Table2LaTeX-RL: Converting Table Images to High-Fidelity LaTeX Code Using Reinforced Multimodal Language Models	arXiv '25	-	-
`CSPO`	CSPO: Alleviating Reward Ambiguity for Structured Table-to-LaTeX Generation	arXiv '26	-	-

Mathematical Formulas & TikZ

Model	Paper	Venue	Website	GitHub

`AutomaTikZ`	AutomaTikZ: Text-Guided Synthesis of Scientific Vector Graphics with TikZ	ICLR '24	-	-
`DeTikZify`	DeTikZify: Synthesizing Graphics Programs for Scientific Figures and Sketches with TikZ	NeurIPS '24	-	-
`TikZilla`	TikZilla: Scaling Text-to-TikZ with High-Quality Data and Reinforcement Learning	arXiv '26	-	-
`Edit2TikZ`	Edit2TikZ: A Comprehensive and Challenging Benchmark for Scientific Figure Editing with TikZ	arXiv '26	-	-

Visual Fidelity and Scientific Accuracy Assessment

Model	Paper	Venue	Website	GitHub

`StructEval`	StructEval: Benchmarking LLMs' Capabilities to Generate Structural Outputs	TMLR '25
`PlotCraft`	PlotCraft: Pushing the Limits of LLMs for Complex and Interactive Data Visualization	arXiv '25	-	-
`TeXpert`	TeXpert: Multi-Level Benchmark for LaTeX Code Generation	SDP '25	-	-
`AbGen`	AbGen: Evaluating Large Language Models in Ablation Study Design and Evaluation for Scientific Research	ACL '25	-	-
`SciFig`	SciFig: Towards Automating Scientific Figure Generation	arXiv '26	-	-
`SciFlow-Bench`	SciFlow-Bench: Evaluating Structure-Aware Scientific Diagram Generation via Inverse Parsing	arXiv '26	-	-
`FigureBench`	AutoFigure: Generating and Refining Publication-Ready Scientific Illustrations	ICLR '26	-
`SciFigQual-Bench`	SciFigQual-Bench: A Benchmark for Scientific Figure Quality Assessment with Full-Manuscript Context	arXiv '26	-	-
`SciFigAlign`	SciFigAlign: Scoring Scientific Figures by Fine-tuned Alignment of Visuals with Manuscript Evidence	arXiv '26	-	-
`SciFigPlag-Bench`	SciFigPlag-Bench: A Benchmark for Provenance-Aware Scientific Figure Plagiarism Detection	arXiv '26	-	-
`VLM Blind/Misled`	How Do VLMs Behave When Blind or Misled? Behavioral Evaluation of VLMs on Scientific Figures	arXiv '26	-	-

5. Paper Writing

Semi-Automated Writing Assistance

Model	Paper	Venue	Website	GitHub

`CoAuthor`	CoAuthor: Human-AI Collaborative Writing with Language Models	arXiv '22	-	-
`AI Writing Study`	AI Writing Study	AIED '25	-	-
`DraftMarks`	DraftMarks: Enhancing Transparency in Human-AI Co-Writing Through Interactive Skeuomorphic Process Traces	arXiv '25	-	-
`PaperDebugger`	PaperDebugger: A Plugin-Based Multi-Agent System for In-Editor Academic Writing, Review, and Editing	arXiv '25	-
`ScholarCopilot`	ScholarCopilot: Training LLMs for Academic Writing with Integrated Citation	arXiv '25	-	-
`XtraGPT`	XtraGPT: Context-Aware and Controllable Academic Paper Revision	arXiv '25	-	-
`LimAgents`	Multi-Agent LLMs for Generating Research Limitations	arXiv '26	-	-
`PaperMentor`	PaperMentor: A Human-Centered Multi-Agent Writing Tutor for AI Research Papers on Overleaf	arXiv '26	-	-
`AutoSupervision`	AutoSupervision: Closing the Feedback Loop in Scientific Workflows with Grounded Revision Verification	arXiv '26	-	-
`ReasFlow`	ReasFlow: Assisting Reasoning-Centric Scientific Discovery in Applied Mathematics via a Knowledge-Based Multi-Agent System	arXiv '26	-	-

Fully Automated Paper Generation

Model	Paper	Venue	Website	GitHub

`CycleResearcher`	CycleResearcher: Improving Automated Research via Automated Review	ICLR '25	-	-
`Agent Laboratory`	Agent Laboratory: Using LLM Agents as Research Assistants	EMNLP '25	-	-
`FutureGen`	FutureGen: A RAG-based Approach to Generate the Future Work of Scientific Article	arXiv '25	-	-
`AI Scientist`	The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery	Nature '26	-
`APRES`	APRES: An Agentic Paper Revision and Evaluation System	arXiv '26	-	-
`LECTOR`	LECTOR: Joint Optimization of Scientific Reasoning Graphs and Introduction Generation	arXiv '26	-	-
`RWGBench`	RWGBench: Evaluating Scholarly Positioning in Related Work Generation	arXiv '26	-	-

Societal Analysis

Model	Paper	Venue	Website	GitHub

`AI Writing Adoption`	AI Writing Adoption	Nature '26	-	-
`Nature AI Survey`	More than Half of Researchers Now Use AI for Peer Review	Nature '26	-	-
`Denial of Science`	Distributed Denial of Science: How Indirect Data Poisoning of AI Systems Can Industrialize Scientific Fraud	arXiv '26	-	-
`AI Slop OSS`	"AI Slop is DDoSing Open Source": Understanding the Impact of AI-Generated Contributions on Open Source Sustainability	arXiv '26	-	-

Writing Quality and AI Detection Assessment

Model	Paper	Venue	Website	GitHub

`Mapping LLM Use`	Mapping the Increasing Use of LLMs in Scientific Papers	arXiv '24	-	-
`CycleReviewer`	CycleResearcher: Improving Automated Research via Automated Review	ICLR '25	-	-
`Stanford Agentic`	Stanford Agentic	Web '25	-	-
`SciIG`	Let's Use ChatGPT To Write Our Paper! Benchmarking LLMs To Write the Introduction of a Research Paper	arXiv '25	-	-
`Watermarking`	Detecting LLM-Generated Peer Reviews	arXiv '25	-	-
`PaperWritingBench`	PaperOrchestra: A Multi-Agent Framework for Automated AI Research Paper Writing	arXiv '26	-	-
`CiteTracer`	Source or It Didn't Happen: A Multi-Agent Framework for Citation Hallucination Detection	arXiv '26	-	-
`Process Eval`	Process-Oriented Evaluation of AI-Assisted Scientific Writing	arXiv '26	-	-

6. Peer Review

Automated Review Generation

Model	Paper	Venue	Website	GitHub

`ChatReviewer`	ChatReviewer: ChatGPT-based Paper Reviewing and Response Generation	GitHub '23	-
`AI-Peer-Review`	AI-Peer-Review	GitHub '24	-
`MARG`	MARG: Multi-Agent Review Generation for Scientific Papers	arXiv '24	-	-
`Reviewer2`	Reviewer2: Optimizing Review Generation Through Prompt Generation	arXiv '24	-	-
`ReviewRL`	ReviewRL: Towards Automated Scientific Review with RL	EMNLP '25	-	-
`DeepReviewer`	DeepReview: Improving LLM-based Paper Review with Human-like Deep Thinking Process	arXiv '25	-	-
`OpenReviewer`	OpenReviewer: A Specialized Large Language Model for Generating Critical Scientific Paper Reviews	NAACL '25	-	-
`REMOR`	REMOR: Automated Peer Review Generation with LLM Reasoning and Multi-Objective Reinforcement Learning	arXiv '25	-	-
`ScholarPeer`	ScholarPeer: A Context-Aware Multi-Agent Framework for Automated Peer Review	arXiv '26	-	-
`ProReviewer`	From Passive Generation to Investigation: A Proactive Scientific Peer Review Agent	arXiv '26	-	-
`PeerCheck`	PeerCheck: Enhancing LLM-Generated Academic Reviews Towards Human-Level Quality	arXiv '26	-	-
`Local Pre-Screening`	Local AI pre-screening for human triple-blind peer review in health sciences	arXiv '26	-	-
`ReVoicer`	ReVoicer: Conversational Voice Annotation for Human-Centered, LLM-Assisted Peer Review	arXiv '26	-	-

Meta-Review & Reviewer Matching

Model	Paper	Venue	Website	GitHub
`Metag`	Metag: A dataset to build agentic meta-reviewing capabilities	arXiv '26	-	-

`AgentReview`	AgentReview: Exploring Peer Review Dynamics with LLM Agents	EMNLP '24	-	-
`Meta-Review LLMs`	Meta-Review LLMs	NAACL '25	-	-
`RATE`	RATE: Reviewer Profiling and Annotation-free Training for Expertise Ranking in Peer Review Systems	arXiv '26	-	-
`MERIT`	MERIT: Matching Expertise via Rubric-Informed Training for Reviewer Assignment	arXiv '26	-	-

Adversarial Attacks & Bias Analysis

Model	Paper	Venue	Website	GitHub

`Raina etal`	Raina etal	EMNLP '24	-	-
`AI Review Lottery`	The AI Review Lottery: Widespread AI-Assisted Peer Reviews Boost Paper Scores and Acceptance Rates	arXiv '24	-	-
`Ye etal`	Ye etal	arXiv '24	-	-
`Breaking the Reviewer`	Breaking the Reviewer: Assessing the Vulnerability of Large Language Models in Automated Peer Review Under Textual Adversarial Attacks	arXiv '25	-	-
`LLM Reviewer Bias`	LLM Reviewer Bias	arXiv '25	-	-
`Prompt Injection`	Prompt Injection Attacks on LLM Generated Reviews of Scientific Publications	arXiv '25	-	-
`Sahoo etal`	Sahoo etal	arXiv '25	-	-
`Zhou etal`	Zhou etal	arXiv '25	-	-
`Presentation Gaming`	No Hidden Prompts Needed! You Can Game AI Peer Review with Presentation-Only Revisions	arXiv '26	-	-
`LLMs Favor LLMs?`	Do LLMs Favor LLMs? Quantifying Interaction Effects in Peer Review	arXiv '26	-	-
`Gaming AI Reviews`	Gaming AI-Assisted Peer Reviews Poses New Risks to the Scientific Community	arXiv '26	-	-
`Phantom Refs`	Phantom References: Hallucinated Citations That Survive Peer Review at Top-Tier Conferences	arXiv '26	-	-
`Rhetorical Reward-Hacking`	How Can Rhetoric Reward-Hack AI Reviewers? Dissecting Rhetorical Sensitivity in AI-Based Peer Review	arXiv '26	-	-

Detection & Policy

Model	Paper	Venue	Website	GitHub

`AI Detection`	Is Your Paper Being Reviewed by an LLM? Benchmarking AI Text Detection in Peer Review	arXiv '25	-	-
`AI Use Rejects`	Major Conference Catches Illicit AI Use — and Rejects Hundreds of Papers	Nature '26	-	-
`Nature AI Survey`	More than Half of Researchers Now Use AI for Peer Review	Nature '26	-	-
`Policy Enforcement`	Policy Enforcement	arXiv '26	-	-
`Reviewer Feedback`	What Happens When Reviewers Receive AI Feedback in Their Reviews?	CHI '26	-	-
`AAAI-26 Pilot`	AI-Assisted Peer Review at Scale: The AAAI-26 AI Review Pilot	arXiv '26	-	-
`Reviewer AI Policies`	AI-Assisted Peer Review Across Research Communities: From Reviewer AI Policies to LLM Review Quality	arXiv '26	-	-

Review Consistency and Bias Assessment

Model	Paper	Venue	Website	GitHub
`VERA-RL`	Not Just Reason, Not Just Scan: Reinforcement Learning for Proactive Scientific Error Verification over Academic Paper	EMNLP '26	-	-

`Review Survey`	More than Half of Researchers Now Use AI for Peer Review — often Against Guidance	IF '25	-	-
`Stanford Agentic`	Stanford Agentic	Web '25	-	-
`ClaimCheck`	ClaimCheck: How Grounded are LLM Critiques of Scientific Papers?	EMNLP '25	-	-
`REFUTE`	REFUTE: A Benchmark for Scientific Critique and Epistemic Calibration in Language Models	HF '26	Website	-
`ReViewGraph`	Automatic Paper Reviewing with Heterogeneous Graph Reasoning over LLM-Simulated Reviewer-Author Debates	AAAI '26	-	-
`ReviewAgents`	ReviewAgents: Bridging the Gap Between Human and AI-Generated Paper Reviews	arXiv '25	-	-
`ICLR 2025 Study`	ICLR 2025 Study	NMI '26	-	-
`AI Reviewer Limits`	On the limits and opportunities of AI reviewers: Reviewing the reviews of Nature-family papers with 45 expert scientists	arXiv '26	-	-
`PRISM`	PRISM: A Multi-Dimensional Benchmark for Evaluating LLM Peer Reviewers	arXiv '26	-	-
`LLM-Human Alignment`	How Closely Do LLM Reviews Align with Human Peer Review?	arXiv '26	-	-
`Epistemic Reliability`	Articulate Intuition or Genuine Analysis? Benchmarking Epistemic Reliability in LLM-as-a-Judge Peer Reviews	arXiv '26	-	-
`SurveyReview`	SurveyReview: A Reviewer-Aligned Benchmark for Survey Evaluators	arXiv '26	-	-

7. Rebuttal

Reviewer Comment Analysis

Model	Paper	Venue	Website	GitHub

`ReviewMT`	Peer Review as A Multi-Turn and Long-Context Dialogue with Role-Based Interactions	arXiv '24	-	-
`ICLR Rebuttal Study`	ICLR Rebuttal Study	arXiv '25	-	-
`RbtAct`	RbtAct: Rebuttal as Supervision for Actionable Review Feedback Generation	arXiv '26	-	-
`GoodPoint`	GoodPoint: Learning Constructive Scientific Paper Feedback from Author Responses	arXiv '26	-	-

Automated Rebuttal Generation

Model	Paper	Venue	Website	GitHub

`ReviewerToo`	ReviewerToo: Should AI Join The Program Committee? A Look At The Future of Peer Review	arXiv '25	-	-
`RebuttalAgent`	RebuttalAgent: Strategic Persuasion in Academic Rebuttal via Theory of Mind	ICLR '26	-
`Author-in-the-Loop`	Author-in-the-Loop Response Generation and Evaluation: Integrating Author Expertise and Intent in Responses to Peer Review	ACL '26	-	-
`DRPG`	DRPG: An Agentic Framework for Academic Rebuttal	arXiv '26	-
`Paper2Rebuttal`	Paper2Rebuttal: A Multi-Agent Framework for Transparent Author Response Assistance	arXiv '26	-	-
`Defend`	Defend: Automated Rebuttals for Peer Review with Minimal Author Guidance	arXiv '26	-	-

Rebuttal Effectiveness Assessment

Model	Paper	Venue	Website	GitHub

`Re$^2$`	Re$^2$	arXiv '25	-	-
`Commitment Checklist`	Commitment Checklist: Auditing Author Commitments in Peer Review	arXiv '26	-	-
`Re$^3$Align`	Re$^3$Align	ACL '26	-	-
`Rebuttals Move`	Rebuttals Move Peer-Review Scores, but Initial-Review Structure Bounds the Movement	arXiv '26	-	-
`Trust AI Reviews`	To Trust or Not to Trust: Authors' Response to AI-based Reviews	arXiv '26	-	-

8. Dissemination (Paper2X)

Paper2Poster

Model	Paper	Venue	Website	GitHub

`P2P`	P2P: Automated Paper-to-Poster Generation and Fine-Grained Benchmark	ICLR '26	-	-
`Paper2Poster`	Paper2Poster: Towards Multimodal Poster Automation from Scientific Papers	NeurIPS '25	-
`PosterForest`	PosterForest: Hierarchical Multi-Agent Collaboration for Scientific Poster Generation	arXiv '25	-	-
`PosterGen`	PosterGen: Aesthetic-Aware Paper-to-Poster Generation via Multi-Agent LLMs	arXiv '25	-	-
`APEX`	APEX: Academic Poster Editing Agentic Expert	arXiv '26	-
`PosterOmni`	PosterOmni: Generalized Artistic Poster Creation via Task Distillation and Unified Reward Feedback	arXiv '26	-	-
`Any2Poster`	Any2Poster: Any-Source Poster Generation Across Modalities and Domains	arXiv '26	-	-
`PosterMELD`	PosterMELD: Multi-Agent Paper-to-Poster Generation for Controllable Design Diversity with Editable Print-Ready Outputs	arXiv '26	-	-

Paper2Slides

Model	Paper	Venue	Website	GitHub

`DOC2PPT`	DOC2PPT: Automatic Presentation Slides Generation from Scientific Documents	AAAI '22	-	-
`PPTAgent`	PPTAgent: Generating and Evaluating Presentations Beyond Text-to-Slides	EMNLP '25	-
`AutoPresent`	AutoPresent: Designing Structured Visuals from Scratch	CVPR '25	-	-
`Paper2Slides`	Paper2Slides: From Paper to Presentation in One Click	GitHub '25	-
`Auto-Slides`	Auto-Slides: An Interactive Multi-Agent System for Creating and Customizing Research Presentations	arXiv '25	-	-
`PASS`	PASS: Presentation Automation for Slide Generation and Speech	arXiv '25	-	-
`SlideGen`	SlideGen: Collaborative Multimodal Agents for Scientific Slide Generation	arXiv '25	-	-
`Talk to Your Slides`	Talk to Your Slides: Efficient Slide Editing Agent	arXiv '25	-	-
`SlideTailor`	SlideTailor: Personalized Presentation Slide Generation for Scientific Papers	AAAI '26	-
`DeepPresenter`	DeepPresenter: Environment-Grounded Reflection for Agentic Presentation Generation	arXiv '26	-
`Office Raccoon`	Office Raccoon	Web '26	-	-
`X+Slides`	X+Slides: Benchmarking Audience-Conditioned Slide Generation	arXiv '26	-	-
`SeaSlides`	SeaSlides: Semantic Abstraction Layer for Agentic Slide Generation	arXiv '26	-	-

Paper2Video

Model	Paper	Venue	Website	GitHub

`Preacher`	Preacher: Paper-to-Video Agentic System	ICCV '25	-
`Paper2Video`	Paper2Video: Automatic Video Generation from Scientific Papers	arXiv '25	-
`PresentAgent`	PresentAgent: Multimodal Agent for Presentation Video Generation	EMNLP '25	-
`PresentAgent-2`	PresentAgent-2: Towards Generalist Multimodal Presentation Agents	arXiv '26	-	-
`Paper2Video Talks`	A Good Talk Does not Look Like a Summary, It Teaches You! Measuring Takeaways from Paper-to-Video Talks	arXiv '26	-	-

Model	Paper	Venue	Website	GitHub

`Paper2Web`	Paper2Web: Let's Make Your Paper Alive!	arXiv '25	-
`ResearchStudio-Reel`	ResearchStudio-Reel: Automate the Last Mile of Research from Paper to Poster, Video, and Blog	arXiv '26	-	-
`I-WebGenBench`	I-WebGenBench: Evaluating Interactivity in LLM-Generated Scientific Web Applications	arXiv '26	-	-
`SciForge`	SciForge: An AI-Native, Multimodal Workbench for Scientific Discovery	arXiv '26	-	-

Fidelity and Adoption Assessment

Model	Paper	Venue	Website	GitHub

`PPTEval`	PPTAgent: Generating and Evaluating Presentations Beyond Text-to-Slides	EMNLP '25	-
`PresentQuiz`	Paper2Video: Automatic Video Generation from Scientific Papers	arXiv '25	-
`PresentEval`	PresentAgent: Multimodal Agent for Presentation Video Generation	EMNLP '25	-
`Sci. Comm. Correspondence`	Unifying Scientific Communication: Fine-Grained Correspondence Across Scientific Media	arXiv '26	-	-

9. End-to-End Systems

Fully Automated Research Systems

Model	Paper	Venue	Website	GitHub
`Gemini Co-Scientist`	Accelerating Scientific Research with Gemini in the Real-World	arXiv 2026	-	-
`AutoResearch`	AutoResearch: Insight In, Hallucination Out	arXiv 2026	-	-
`Eureka`	Eureka: Task-Conditioned Meta-Agent Orchestration for Scientific Discovery	arXiv 2026	-	-
`AutoResearch Diagnosis`	How Do Agents Fail on AutoResearch: End-to-End Diagnostic Evaluation on 100 Real-World Frontier Research Tasks	arXiv 2026	-	-

`ResearchTown`	ResearchTown: Simulator of Human Research Community	ICML 2025
`Agent Laboratory`	Agent Laboratory: Using LLM Agents as Research Assistants	arXiv 2025	-	-
`AgentRxiv`	AgentRxiv: Towards Collaborative Autonomous Research	arXiv 2025	-	-
`ARIS`	-	GitHub 2025	-
`freephdlabor`	Build Your Personalized Research Group: A Multiagent Framework for Continual and Interactive Science Automation	arXiv 2025	-	-
`SciMaster`	SciMaster: Towards General-Purpose Scientific AI Agents	arXiv 2025	-
-	Towards End-to-End Automation of AI Research	Nature 2026
`Idea2Story`	Idea2Story: An Automated Pipeline for Transforming Research Concepts into Complete Scientific Narratives	arXiv 2026	-	-
`UniScientist`	-	Web 2026	-	-
`ASI-Evolve`	-	GitHub 2026	-
`FARS`	-	Web 2026	-	-
`AutoResearchClaw`	-	GitHub 2026	-
`CORAL`	CORAL: Towards Autonomous Multi-Agent Evolution for Open-Ended Discovery	arXiv 2026	-
`AutoSOTA`	AutoSOTA: An End-to-End Automated Research System for State-of-the-Art AI Model Discovery	arXiv 2026	-
`AiScientist-LH`	Toward Autonomous Long-Horizon Engineering for ML Research	arXiv 2026	-
`OpenResearcher (2026)`	OpenResearcher: A Fully Open Pipeline for Long-Horizon Deep Research Trajectory Synthesis	arXiv 2026	-
`Aletheia`	Towards Autonomous Mathematics Research	arXiv 2026	-
`AutoSci`	AutoSci: A Memory-Centric Agentic System for the Full Scientific Research Lifecycle	arXiv 2026	-	-
`ScientistOne`	ScientistOne: Towards Human-Level Autonomous Research via Chain-of-Evidence	arXiv 2026	-	-
`Arbor`	Toward Generalist Autonomous Research via Hypothesis-Tree Refinement	arXiv 2026	-	-
`Agon`	Agon: An Autonomous Large-Scale Omnidisciplinary Research System Built on Prompt Economy	arXiv 2026	-
`ResearchClawBench`	ResearchClawBench: A Benchmark for End-to-End Autonomous Scientific Research	arXiv 2026	-	-
`Act as Real Researcher`	Act As a Real Researcher: A Suite of Benchmarks Evaluating Frontier LLMs and Agentic Harnesses in Research Lifecycle	arXiv 2026	-	-
`ResearchArena`	How Far Are We From True Auto-Research?	arXiv 2026	-	-
`NVAITC AI Sci.`	NVAITC AI Scientist: A Governed End-to-End Research System -- A Hypertension GWAS Case Study	arXiv '26	-	-
`DeepResearch Agent Sys.`	DeepResearch Agent System	arXiv '26	-	-
`ScienceFlow`	ScienceFlow: A long-horizon agent for ML research, scientific discovery and beyond	arXiv '26	-	-
`Spark-to-Paper`	Spark-to-Paper: End-to-End Research Paper Generation as a Composable Skill	arXiv '26	-	-
`OmniScientist`	OmniScientist: An Omni-Modal Omni-Discipline AI Scientist	arXiv '26	-	-

Domain-Specific Systems

Model	Paper	Venue	Website	GitHub
`AutoSR`	AutoSR: Automatic Symbolic Regression by Searching Research States	arXiv 2026	-	-
`The AI Engineer`	Closed-loop AI achieves certifiable engineering design	arXiv 2026	-	-

`AlphaFold 3`	Accurate Structure Prediction of Biomolecular Interactions with AlphaFold 3	Nature 2024		-
`Medical AI Scientist`	Towards a Medical AI Scientist	arXiv 2026	-	-
`Cognitive Scientist`	Closing the Loop to Discover Psychological Theories with an Automated Cognitive Scientist	arXiv '26	-	-
`Molecular Closed-Loop`	Closed-loop Auto Research for Molecular Property Prediction: Discovering and Certifying Generalizable Improvements	arXiv '26	-	-
`Auto Research (Materials)`	Auto Research for Materials: Auditable AI-Scientist Workflows with Held-Out Transfer	arXiv '26	-	-
`OmniQEC`	OmniQEC: discovering practical quantum error-correcting codes by an AI scientist	arXiv '26	-	-
`Andy`	Andy: A Mathematical Agent for Rigorous Proof and Autonomous Research	arXiv '26	-	-
`BaT`	BaT: Towards Self-Evolving Medical Research Agent with Stage Rubrics	arXiv '26	-	-
`Agentic Sci. Community`	An Agentic AI Scientific Community for Automated Neural Operator Discovery	arXiv '26	-	-
`WARA`	WARA: A Closed-Loop Multi-Agent Framework for Wireless Optimization Autoresearch	ICCC '26	-	-

Evolutionary & Self-Improving Systems

Model	Paper	Venue	Website	GitHub

`ShinkaEvolve`	ShinkaEvolve: Towards Open-Ended and Sample-Efficient Program Evolution	arXiv 2025	-
`Darwin Godel Machine`	Darwin Godel Machine: Open-Ended Evolution of Self-Improving Agents	arXiv 2025	-
`EvoMaster`	EvoMaster: A Foundational Evolving Agent Framework for Agentic Science at Scale	arXiv 2026	-	-
`Self-Driving Lab`	Compressing the Validation Bottleneck: An Agentic Self-Driving Lab for Scientific Discovery	arXiv '26	-	-
`Meta-Reflection`	Autonomous Scientific Discovery via Iterative Meta-Reflection	arXiv '26	-	-
`Project2Task`	Project2Task: Graph-Guided Project-Level Planning for Autonomous Research	arXiv '26	-	-
`Adaptive Inquiry`	Beyond Solution-Centric Search: Adaptive Inquiry and Knowledge Revision for Autonomous ML Engineering	arXiv '26	-	-
`CausalForge`	CausalForge: A Formally Grounded, Self-Improving Agentic Framework for Automated Research in Causal Inference	arXiv '26	-	-
`World-Model Scaling`	Scaling Automatic Research Agents via World Models	arXiv '26	-	-
`Research Preference Models`	AI Research Preference Models	arXiv '26	-	-

Research Platforms & Infrastructure

Model	Paper	Venue	Website	GitHub
`Symposium`	Symposium: Trust via Auditable Records for Communities of AI Scientist Agents	arXiv 2026	-	-

`Towards an AI co-scientist`	Towards an AI co-scientist	arXiv 2025	-	-
`PiFlow`	PiFlow: Principle-aware Scientific Discovery with Multi-Agent Collaboration	arXiv 2025	-	-
`LabClaw`	-	Web 2026	-	-
-	OpenAI Is Throwing Everything into Building a Fully Automated Researcher	MIT TR 2026		-
`XScientist`	XScientist: A Git-Like Research Protocol for Long-Running Autonomous Scientific Discovery	arXiv '26	-	-
`Auditable Records`	From Trajectories to Evidence: Auditable Experimental Records for Industrial Research Agents	arXiv '26	-	-
`PEARL`	PEARL: Auditable Repair for Scientific Reasoning Graph Extraction	arXiv '26	-	-
`IdeaTrail`	IdeaTrail: Full-Process Agent Trajectories for Scientific Ideation	arXiv '26	-	-
`EviGraph`	EviGraph: Evidence-Guided Autonomous Research Agents	arXiv '26	-	-
`Discovery Environments`	Scaling Scientific Discovery Environments for Turn-Level Agentic RL	arXiv '26	-	-
`Quantum Theorem Bench`	Benchmarking Agents for Proving Theorems in Quantum Algorithms and Quantum Information	arXiv '26	-	-
`SciDiscovery Readiness`	Are LLMs Ready for Scientific Discovery? A Capability-Oriented Benchmark for AI Scientists	arXiv '26	-	-
`ARAC`	ARAC: Benchmarking Auto-Research's Alignment and Completeness on End-to-End Researchs	arXiv '26	-	-
`Beyond Final Scores`	Beyond Final Scores: A Systematic Evaluation of Agents for Long-Horizon AI Research and Development	arXiv '26	-	-
`Replication Training`	Training AI Scientists to Replicate Research	arXiv '26	-	-
`Rubric Meta-Eval`	Can LLMs Write Reliable Rubrics? A Meta-Evaluation for Experiment Reproduction	arXiv '26	-	-
`Fast-Moving Domains`	Adversarial Fast-Moving Real-World Domains as Test Beds for Benchmarking AI Scientist Capabilities	arXiv '26	-	-
`AutoWorldModel-Bench`	AutoWorldModel-Bench: A State-Centric Benchmark for Automated World-Model Research	arXiv '26	-	-
`Scientific Memory`	Beyond Memory Leaderboards: Evaluating Scientific Memory as Budgeted Context Restoration	arXiv '26	-	-
`SciHazard`	SciHazard: A Benchmark for Measuring Scientific Safety Risks with Decomposed Harm Scoring	arXiv '26	-	-
`Science Edge Eval.`	Science Edge Evaluation: SEE the Missing Step Toward Real Scientific Discovery	arXiv '26	-	-

10. Societal & Critical Perspectives

Model	Paper	Venue	Website	GitHub
-	Science Done on a Machine by a Machine: AI Agents in Computational Chemistry	arXiv 2026	-	-
-	Bayesian Optimization for Self-Driving Materials Laboratories: From Algorithms to Physics-Informed Workflows	arXiv 2026	-	-
-	LLM assisted writing deserves empirical evaluation	arXiv 2026	-	-
-	A Metric with Positive Sectional Curvature on $S^2\times S^3$	arXiv 2026	-	-
-	Weak-Type Bounds for Convolution on the Boolean Hypercube	arXiv 2026	-	-
-	Quo Vadis? Scientific Discovery in the Age of Artificial Intelligence	Theory of Science	-	-
-	Are LLMs becoming similarly creative? Evidence from three years of models	arXiv 2026	-	-

-	Navigating the Jagged Technological Frontier	Org. Sci. 2025		-
-	Reassessing Academic Integrity in the Age of AI	SSH Open 2025		-
`The AI Deskilling Paradox`	The AI Deskilling Paradox	CACM 2025		-
`Hidden Pitfalls of AI Scientist Systems`	The More You Automate, the Less You See: Hidden Pitfalls of AI Scientist Systems	arXiv 2025	-	-
`Rethinking Science in the Age of AI`	Rethinking Science in the Age of Artificial Intelligence	arXiv 2025	-	-
-	Measuring AI Ability to Complete Long Tasks	METR 2025		-
-	Towards a Science of Scaling Agent Systems	arXiv 2025	-	-
-	Artificial Intelligence Tools Expand Scientists' Impact but Contract Science's Focus	Nature 2026		-
-	[](https://www.cell.com/patterns/fulltext/S2666-3899(25) AI for Scientific Discovery is a Social Problem	Patterns 2026	[](https://www.cell.com/patterns/fulltext/S2666-3899(25)	-
`Research Integrity in the Age of AI`	Research Integrity and Academic Authority in the Age of Artificial Intelligence: From Discovery to Curation?	arXiv 2026	-	-
`SciSciGPT`	SciSciGPT: Advancing Human-AI Collaboration in the Science of Science	Nature CS 2026		-
`SimStep`	SimStep: Chain-of-Abstractions for Incremental Specification and Debugging of AI-Generated Interactive Simulations	arXiv 2025	-	-
`ConvoLearn`	ConvoLearn: A Learning Sciences Grounded Dataset for Fine-Tuning Dialogic AI Tutors	arXiv 2026	-	-
`AFIM: Academic Fraud Inclination Metric`	AFIM: Academic Fraud Inclination Metric	Web 2026		-
-	AI Researchers' Views on Automating AI R&D and Intelligence Explosions	arXiv 2026	-	-
-	AI Scientists Are Changing Research	Nature 2026		-
`Learning by Creating (Talk)`	Learning by Creating: A Human-Centered Vision for AI in Education	Talk 2026		-
`AI Sci. No Reasoning`	AI scientists produce results without reasoning scientifically	arXiv 2026	-	-
`Not Built for Autonomy`	Agentic AI Scientists Are Not Built For Autonomous Scientific Discovery	arXiv 2026	-	-
`Workflow != Closure`	Workflow Closure Is Not Scientific Closure in Auto-Research Systems	arXiv 2026	-	-
`PseudoBench`	PseudoBench: Measuring How Agentic Auto-Research Fuels Pseudoscience	arXiv 2026	-	-
`SciIntegrity-Bench`	SciIntegrity-Bench: A Benchmark for Evaluating Academic Integrity in AI Scientist Systems	arXiv 2026	-	-
-	Abduction Without a Body? Representational Grounding and the Abduction Loop for Scientific Hypothesis Generation	arXiv '26	-	-
-	Visualizing Graph-to-Answer Mechanism Recovery in Materials-Science Hypothesis Generation	arXiv '26	-	-
-	Generative AI use in Statistical Research: A Literature Review and Code Generation Case Study	arXiv '26	-	-
-	AI's Capability in Assisting Scientific Research in Physics, Astrophysics, and Cosmology I: Literature Review	arXiv '26	-	-
-	Scientific Knowledge Discovery in the Age of Large Language Models	arXiv '26	-	-
-	Is Deep Research Reliable? Misleading Knowledge Induces False Conclusions	arXiv '26	-	-
-	Diagnosing Search Behavior and Failure Modes in Long-Horizon Search Agents	arXiv '26	-	-
-	A Pathway to General-Purpose Scientific AI: Multimodal Comprehension of Scientific Images	arXiv '26	-	-
-	Position: AI Agents in Scientific Teams Should Be Studied as Human-Agent Systems	arXiv '26	-	-
-	The Past and Future of AI Scientists	arXiv '26	-	-
-	Efficiency Matters in Autonomous Research	arXiv '26	-	-
-	Agentic Auto-Research is Fuzz Testing	arXiv '26	-	-
-	Mechanist: AI as a Scientific Instrument for Discovering the Mechanisms of Intelligence	arXiv '26	-	-
-	An AI Scientist that Doesn't Drift: Taste, Structure, and Falsifiable Findings in a Quadruped Navigation Research Loop	arXiv '26	-	-
-	Long-Horizon Autonomous Architecture Research with a Language-Model Agent: A Behavioural Case Study	arXiv '26	-	-
-	Stress-testing large language model agents in a robotic chemistry laboratory	arXiv '26	-	-

11. Surveys & Curated Lists

Model	Paper	Venue	Website	GitHub

`LLM4SR`	LLM4SR: A Survey on Large Language Models for Scientific Research	arXiv 2025	-	-
`From Automation to Autonomy`	From Automation to Autonomy: A Survey on Large Language Models for Scientific Discovery	arXiv 2025	-	-
`AI4Research`	AI4Research: A Survey of Artificial Intelligence for Scientific Research	arXiv 2025	-	-
`A Survey of AI Scientists`	A Survey of AI Scientists	arXiv 2025	-	-
-	Large Language Models for Scientific Idea Generation: A Creativity-Centered Survey	arXiv 2025	-	-
-	Large Language Models for Automated Scholarly Paper Review: A Survey	Inf. Fusion 2025		-
`AutoResearch Survey`	What's Missing in Autonomous Research? A Systematization of Systems, Benchmarks, and Verification	Web 2026		-

12. Tools & GitHub Repos

Curated Lists

Repository	Stars	Description
Awesome-Deep-Research		Up-to-date collection of agentic deep research resources
Awesome-Scientific-Language-Models		Survey of scientific LLMs (EMNLP'24)
Awesome-LLM-Scientific-Discovery		Three-level autonomy framework (EMNLP'25)
Awesome-AI-Scientist-Papers		Resources on AI Scientist systems
Awesome-Auto-Research-Tools		Automated research tools catalog
awesome-autoresearch		Autonomous improvement loops and research agents
awesome-ai-research-writing		Prompt templates and agent skills for AI-assisted writing

Idea Generation

Repository	Stars	Description
Virtual-Scientists		VirSci: multi-agent collaborative idea generation (ACL'25)
ResearchAgent		Iterative idea proposal with reviewing agents

Literature Review

Repository	Stars	Description
paper-qa		PaperQA2: superhuman RAG for scientific Q&A
local-deep-research		Fully local deep research
researchgpt		Conversational interaction with research papers
gpt-researcher		Autonomous agent for comprehensive online research
AutoSurvey		Automated comprehensive literature surveys
storm		Wikipedia-style article generation (STORM)
lune-mcp-server		MCP client for the hosted Lune Research corpus: paper search, citation traversal, evidence extraction, quote-backed claim verification (API key required)

Coding & Experiments

Repository	Stars	Description
autoresearch (Karpathy)		Autonomous ML experiments, ~12 exp/hour overnight
Paper2Code		Multi-agent ML paper to code transformation
RD-Agent		Microsoft's LLM framework for autonomous data science
MLAgentBench		13 end-to-end ML experimentation tasks
SWE-bench		Real-world GitHub issue resolution benchmark
Thoth		Dashboard-first Claude Code and Codex runtime for durable autoresearch runs, work-item locks, ledgers, and reviewable verdicts

Peer Review

Repository	Stars	Description
paper-reviewer		arXiv paper reviews + blog posts
ai-peer-review		Multi-LLM reviews + meta-review synthesis
openreviewer		Llama-8B fine-tuned on 79K expert reviews

⬆ Back to Top

Last updated: 2026-08-31 · Maintained by WorldBench

agent

agentic-ai

ai-research

ai-scientist

auto-research

large-language-models

llm

multi-agent-system

rag

Similar repos

ResearAI/Awesome-AI-Scientist

This is a survey of research on AI scientists, AI researchers, AI engineers, and a series of…

314

du-nlp-lab/LLM4SR

LLM for Scientific Research Survey

133

aiming-lab/AutoResearchClaw

Fully autonomous & self-evolving research from idea to paper. Chat an Idea. Get a Paper. 🦞

14,506

Omni-Scientist/Awesome-AI-Scientist

🧪 Awesome list of AI Scientist papers, systems, benchmarks, datasets and open-source platforms.

100

OSU-NLP-Group/awesome-agents4science

A curated list of papers on LLMs and agents for scientific research and development

GeminiLight/awesome-agentic-artifact-creation

A curated paper list on agentic artifact creation, an emerging paradigm in which AI agents…

alvinunreal/awesome-autoresearch

A curated list of autonomous improvement loops, research agents, and autoresearch-style systems…

2,539

EvoMap/AutoResearch

AI/ML research agents from idea to paper-ready evidence. An EvoMap open-source project.

3,187

Contributors

20 commits

1 commits

1 commits

1 commits

Languages

HTML

100.0%

worldbench/awesome-ai-auto-research

README

:sunglasses: Awesome AI Auto-Research

:robot: AI Auto-Research

:books: Citation

Table of Contents

1. Idea Generation

LLM Internal Knowledge-Based Generation

External Signal-Driven Generation

Multi-Agent Collaborative Generation

Novelty and Feasibility Assessment

2. Literature Review & Paper Search

Literature Retrieval

Survey & Related Work Generation

Deep Research Agents

Retrieval and Synthesis Quality Assessment

3. Coding & Experimentation

Code Generation

Paper-to-Code

Experiment Execution & Orchestration

Code Correctness and Reproducibility Assessment

4. Tables & Figures

Scientific Figure Generation

Table Understanding & Generation

Mathematical Formulas & TikZ

Visual Fidelity and Scientific Accuracy Assessment

5. Paper Writing

Semi-Automated Writing Assistance

Fully Automated Paper Generation

Societal Analysis

Writing Quality and AI Detection Assessment

6. Peer Review

Automated Review Generation

Meta-Review & Reviewer Matching

Adversarial Attacks & Bias Analysis

Detection & Policy

Review Consistency and Bias Assessment

7. Rebuttal

Reviewer Comment Analysis

Automated Rebuttal Generation

Rebuttal Effectiveness Assessment

8. Dissemination (Paper2X)

Paper2Poster

Paper2Slides

Paper2Video

Paper2Web & Social Media

Fidelity and Adoption Assessment

9. End-to-End Systems

Fully Automated Research Systems

Domain-Specific Systems

Evolutionary & Self-Improving Systems

Research Platforms & Infrastructure

10. Societal & Critical Perspectives

11. Surveys & Curated Lists

12. Tools & GitHub Repos

Curated Lists

Idea Generation

Literature Review

Coding & Experiments

Peer Review

Contributors

Similar repos

Languages

worldbench/awesome-ai-auto-research

README

:sunglasses: Awesome AI Auto-Research

:robot: AI Auto-Research

:books: Citation

Table of Contents

1. Idea Generation

LLM Internal Knowledge-Based Generation

External Signal-Driven Generation

Multi-Agent Collaborative Generation

Novelty and Feasibility Assessment

2. Literature Review & Paper Search

Literature Retrieval

Survey & Related Work Generation

Deep Research Agents

Retrieval and Synthesis Quality Assessment

3. Coding & Experimentation