A collection of awesome AI-for-research papers and projects, covering all stages of the research process and a wide range of scientific domains.
Python
130
39 commits
updated Aug 24, 2026
"Civilization advances by extending the number of important operations which we can perform without thinking about them." — Alfred North Whitehead
Use AI to improve research efficiency and expand the space of exploration.
From focused tools to agents that participate in and reshape the research pipeline.
This repository focuses on recent, high-signal work on AI-driven research itself: systems that participate in the research loop, optimize it, or redefine who drives the loop.
Start Here · By Research Stage · By Role · By Section · By Domain · Benchmarks · Taxonomy · Contributing
If you care about AI for Research systems
Start with End-to-End Research Systems and Benchmarks & Evaluation to compare what representative AI-for-research systems actually cover and how they are evaluated.
If you care about AI for Research in a vertical domain
Start with By Domain, then move to the relevant section pages and Benchmarks & Evaluation for the systems and evaluation anchors that matter in that discipline.
If you care about self-evolving systems
Start with Self-Evolving Systems, then use Experimentation & Agent Methods to compare explicit self-improvement loops, experiment-improve systems, and reusable agent methods.
Representative papers and systems that give a fast first read on the current AI4Research landscape.
Research Infrastructure & Frameworks L3
An environment-engineered autonomous discovery system that coordinates off-the-shelf CLI agents through permission-bounded execution, artifact memory, budget control, and human oversight. Paper · RepoExperimentation & Agent Methods L3
A self-improving AI research repo where agents iteratively rewrite a small training stack, run short experiments, and keep better variants. RepoExperimentation & Agent Methods L3
A test-time training system that uses reinforcement learning on a single target problem so the model can keep improving while searching for stronger scientific and algorithmic solutions. Paper · ProjectExperimentation & Agent Methods L3
A Gemini-powered evolutionary coding agent for discovering better algorithms and scientific solutions through repeated proposal, execution, and selection. Paper · BlogResearch Ideation L2
A Gemini-based multi-agent collaborator for generating literature-grounded hypotheses, overviews, and experimental protocols. Paper · BlogResearch Ideation L1
A large-scale blind human study comparing LLM-generated and expert-generated NLP ideas, with LLM ideas rated higher on novelty but slightly lower on feasibility. Paper · ProjectEnd-to-End Research Systems L3
A full-loop AI scientist for idea generation, code writing, experimentation, paper drafting, and simulated review. Paper · RepoExperimentation & Agent Methods L1
A biomolecular structure and interaction prediction system that extends AlphaFold from protein folding to complexes involving proteins, nucleic acids, ligands, and ions. Paper · Repo · ProjectUse this view when you want to find systems by the stage of research they most clearly serve.
Discover & Synthesize · 15 · Ideate · 20 · Plan & Design · 4 · Implement · 18
Execute & Experiment · 37 · Analyze & Visualize · 9 · Write & Review · 13
This ladder separates human-driven tools, human-in-the-loop collaborators, and AI-driven systems.
L1 Tools · 26 - Human drives the loop. The AI acts as a tool, local component, or narrow assistant rather than as a workflow owner.L2 Collaborators · 32 - Human in the loop. The AI can advance multi-step work, but humans still steer, gate, or validate important decisions.L3 Systems · 42 - AI drives the loop. The system owns substantial execution and iteration, while humans mainly provide goals, constraints, or downstream review.| Section | Focus | Count |
|---|---|---|
| 🔬 End-to-End Research Systems | Systems that cover multiple core stages of the research process and aim to complete a relatively full research loop with limited human intervention. | 14 |
| ⚙️ Experimentation & Agent Methods | Systems, methods, and specialized agents whose main contribution is iterative experimentation, optimization, search, reflection, or self-improving execution, rather than a full end-to-end research workflow. | 46 |
| 💡 Research Ideation | Systems focused on generating research questions, hypotheses, directions, or project ideas. | 14 |
| 📚 Literature Discovery & Synthesis | Systems focused on finding, organizing, comparing, and synthesizing prior work. | 6 |
| 📝 Survey / Review Automation | Systems designed to produce structured surveys, reviews, or systematic review-style outputs. | 10 |
| 🧱 Research Infrastructure & Frameworks | Frameworks, platforms, runtimes, and engineering environments for building and operating research agents. | 10 |
| 📏 Benchmarks & Evaluation | Benchmarks, datasets, metrics, and evaluation frameworks for research agents and AI-for-research systems. | 19 |
Use this view when you want to find systems through the disciplines where they are being applied, rather than through research stage or role in the loop.
| Domain | Focus | Count |
|---|---|---|
| Artificial Intelligence | Applications in artificial intelligence research, machine learning research workflows, and AI-for-AI systems with explicit AI research targets or evaluation. | 52 |
| Biomedical | Applications in biology, medicine, drug discovery, and biomedical literature. | 5 |
| Chemistry | Applications in chemical reasoning, synthesis, and molecular discovery. | 2 |
| Computer Science | Applications in non-AI computer science research such as formal methods, programming systems, and algorithmic reasoning. | 6 |
| General | Cross-domain or discipline-agnostic systems for AI-driven research workflows, literature work, agent infrastructure, and research methodology that are not clearly anchored to one vertical field. | 32 |
| Materials Science | Applications in materials discovery, materials property reasoning, and experimental design. | 2 |
| Math | Applications in mathematical reasoning, theorem proving, and formal proof discovery. | 5 |
| Physics | Applications in physical science reasoning, modeling, and scientific analysis. | 2 |
| Social Science | Applications in social simulation, policy analysis, behavioral science, and computational social experiments. | 2 |
Benchmarks are a core surface of this repository rather than an appendix. They make it easier to separate promising demos from systems that are tested on realistic scientific or AI-research workloads.
The main benchmark hub lives at docs/benchmarks/index.md.
Scientific Reasoning
An expert-written benchmark for Olympiad-style and research-style scientific reasoning across physics, chemistry, and biology.System Benchmark · Ideation & Discovery
A benchmark surface introduced alongside AI-Researcher for assessing guided and open-ended autonomous AI research.System Benchmark
A benchmark built from Kaggle competitions to measure how well AI agents perform at machine learning engineering.System Benchmark · Scientific Reasoning
A task-level benchmark for evaluating language agents on authentic data-driven scientific discovery problems.System Benchmark - Measures end-to-end AI research systems or realistic multi-step workflows.Scientific Reasoning - Measures scientific problem solving, expert analysis, or domain reasoning quality.Ideation & Discovery - Measures hypothesis generation, novelty, or open-ended scientific discovery quality.The repository uses a lightweight taxonomy so entries can be read through research stage, role in the loop, application domain, and evidence quality without turning the README into a flat list.
self-evolving tracked as a tag.If you find this repository useful in your research, please cite:
@misc{awesome_ai_for_research_2026,
author = {Jing, Yi and Xin, Amy and Yao, Zijun},
title = {Awesome AI for Research},
year = {2026},
howpublished = {\url{https://github.com/THU-KEG/Awesome-AI-for-Research}},
note = {GitHub repository}
}
This repository is curated, and contributions are welcome when they improve the source data.
The most helpful contributions are:
Please keep the scope narrow: recent, high-signal AI4Research systems over historical completeness.
When contributing:
python3 tooling/build.py before submitting a pull request
189 followers · starred Apr 2026
149 followers · starred Apr 2026
A collection of awesome AI-for-research papers and projects, covering all stages of the research process and a wide range of scientific domains.
Python
130
39 commits
updated Aug 24, 2026
"Civilization advances by extending the number of important operations which we can perform without thinking about them." — Alfred North Whitehead
Use AI to improve research efficiency and expand the space of exploration.
From focused tools to agents that participate in and reshape the research pipeline.
This repository focuses on recent, high-signal work on AI-driven research itself: systems that participate in the research loop, optimize it, or redefine who drives the loop.
Start Here · By Research Stage · By Role · By Section · By Domain · Benchmarks · Taxonomy · Contributing
If you care about AI for Research systems
Start with End-to-End Research Systems and Benchmarks & Evaluation to compare what representative AI-for-research systems actually cover and how they are evaluated.
If you care about AI for Research in a vertical domain
Start with By Domain, then move to the relevant section pages and Benchmarks & Evaluation for the systems and evaluation anchors that matter in that discipline.
If you care about self-evolving systems
Start with Self-Evolving Systems, then use Experimentation & Agent Methods to compare explicit self-improvement loops, experiment-improve systems, and reusable agent methods.
Representative papers and systems that give a fast first read on the current AI4Research landscape.
Research Infrastructure & Frameworks L3
An environment-engineered autonomous discovery system that coordinates off-the-shelf CLI agents through permission-bounded execution, artifact memory, budget control, and human oversight. Paper · RepoExperimentation & Agent Methods L3
A self-improving AI research repo where agents iteratively rewrite a small training stack, run short experiments, and keep better variants. RepoExperimentation & Agent Methods L3
A test-time training system that uses reinforcement learning on a single target problem so the model can keep improving while searching for stronger scientific and algorithmic solutions. Paper · ProjectExperimentation & Agent Methods L3
A Gemini-powered evolutionary coding agent for discovering better algorithms and scientific solutions through repeated proposal, execution, and selection. Paper · BlogResearch Ideation L2
A Gemini-based multi-agent collaborator for generating literature-grounded hypotheses, overviews, and experimental protocols. Paper · BlogResearch Ideation L1
A large-scale blind human study comparing LLM-generated and expert-generated NLP ideas, with LLM ideas rated higher on novelty but slightly lower on feasibility. Paper · ProjectEnd-to-End Research Systems L3
A full-loop AI scientist for idea generation, code writing, experimentation, paper drafting, and simulated review. Paper · RepoExperimentation & Agent Methods L1
A biomolecular structure and interaction prediction system that extends AlphaFold from protein folding to complexes involving proteins, nucleic acids, ligands, and ions. Paper · Repo · ProjectUse this view when you want to find systems by the stage of research they most clearly serve.
Discover & Synthesize · 15 · Ideate · 20 · Plan & Design · 4 · Implement · 18
Execute & Experiment · 37 · Analyze & Visualize · 9 · Write & Review · 13
This ladder separates human-driven tools, human-in-the-loop collaborators, and AI-driven systems.
L1 Tools · 26 - Human drives the loop. The AI acts as a tool, local component, or narrow assistant rather than as a workflow owner.L2 Collaborators · 32 - Human in the loop. The AI can advance multi-step work, but humans still steer, gate, or validate important decisions.L3 Systems · 42 - AI drives the loop. The system owns substantial execution and iteration, while humans mainly provide goals, constraints, or downstream review.| Section | Focus | Count |
|---|---|---|
| 🔬 End-to-End Research Systems | Systems that cover multiple core stages of the research process and aim to complete a relatively full research loop with limited human intervention. | 14 |
| ⚙️ Experimentation & Agent Methods | Systems, methods, and specialized agents whose main contribution is iterative experimentation, optimization, search, reflection, or self-improving execution, rather than a full end-to-end research workflow. | 46 |
| 💡 Research Ideation | Systems focused on generating research questions, hypotheses, directions, or project ideas. | 14 |
| 📚 Literature Discovery & Synthesis | Systems focused on finding, organizing, comparing, and synthesizing prior work. | 6 |
| 📝 Survey / Review Automation | Systems designed to produce structured surveys, reviews, or systematic review-style outputs. | 10 |
| 🧱 Research Infrastructure & Frameworks | Frameworks, platforms, runtimes, and engineering environments for building and operating research agents. | 10 |
| 📏 Benchmarks & Evaluation | Benchmarks, datasets, metrics, and evaluation frameworks for research agents and AI-for-research systems. | 19 |
Use this view when you want to find systems through the disciplines where they are being applied, rather than through research stage or role in the loop.
| Domain | Focus | Count |
|---|---|---|
| Artificial Intelligence | Applications in artificial intelligence research, machine learning research workflows, and AI-for-AI systems with explicit AI research targets or evaluation. | 52 |
| Biomedical | Applications in biology, medicine, drug discovery, and biomedical literature. | 5 |
| Chemistry | Applications in chemical reasoning, synthesis, and molecular discovery. | 2 |
| Computer Science | Applications in non-AI computer science research such as formal methods, programming systems, and algorithmic reasoning. | 6 |
| General | Cross-domain or discipline-agnostic systems for AI-driven research workflows, literature work, agent infrastructure, and research methodology that are not clearly anchored to one vertical field. | 32 |
| Materials Science | Applications in materials discovery, materials property reasoning, and experimental design. | 2 |
| Math | Applications in mathematical reasoning, theorem proving, and formal proof discovery. | 5 |
| Physics | Applications in physical science reasoning, modeling, and scientific analysis. | 2 |
| Social Science | Applications in social simulation, policy analysis, behavioral science, and computational social experiments. | 2 |
Benchmarks are a core surface of this repository rather than an appendix. They make it easier to separate promising demos from systems that are tested on realistic scientific or AI-research workloads.
The main benchmark hub lives at docs/benchmarks/index.md.
Scientific Reasoning
An expert-written benchmark for Olympiad-style and research-style scientific reasoning across physics, chemistry, and biology.System Benchmark · Ideation & Discovery
A benchmark surface introduced alongside AI-Researcher for assessing guided and open-ended autonomous AI research.System Benchmark
A benchmark built from Kaggle competitions to measure how well AI agents perform at machine learning engineering.System Benchmark · Scientific Reasoning
A task-level benchmark for evaluating language agents on authentic data-driven scientific discovery problems.System Benchmark - Measures end-to-end AI research systems or realistic multi-step workflows.Scientific Reasoning - Measures scientific problem solving, expert analysis, or domain reasoning quality.Ideation & Discovery - Measures hypothesis generation, novelty, or open-ended scientific discovery quality.The repository uses a lightweight taxonomy so entries can be read through research stage, role in the loop, application domain, and evidence quality without turning the README into a flat list.
self-evolving tracked as a tag.If you find this repository useful in your research, please cite:
@misc{awesome_ai_for_research_2026,
author = {Jing, Yi and Xin, Amy and Yao, Zijun},
title = {Awesome AI for Research},
year = {2026},
howpublished = {\url{https://github.com/THU-KEG/Awesome-AI-for-Research}},
note = {GitHub repository}
}
This repository is curated, and contributions are welcome when they improve the source data.
The most helpful contributions are:
Please keep the scope narrow: recent, high-signal AI4Research systems over historical completeness.
When contributing:
python3 tooling/build.py before submitting a pull request
189 followers · starred Apr 2026
149 followers · starred Apr 2026