Shadowgraph
TrendingAbout
Sign in

yanfeng98/paper-is-all-you-need

论文就是你所需要的。

TeX

2

151 commits

updated Sep 14, 2026

See the code

README

paper-is-all-you-need

论文就是你所需要的。

论文

OpenAI

论文年份论文单位笔记地址
Scaling Laws for Neural Language Models2020OpenAI./papers/00001-scaling-laws.pdf
Let's Verify Step by Step2023OpenAI./papers/00028-Verify-Step-by-Step.pdf
Efficient Training of Language Models to Fill in the Middle2022OpenAI./papers/00035-fim.pdf

DeepSeek-AI

论文年份论文单位笔记地址
DeepSeek-V3 Technical Report2024DeepSeek-AI./papers/00042-DeepSeek-V3.pdf
DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning2025DeepSeek-AI./papers/00045-DeepSeek_R1.pdf
DeepSeek-R1 incentivizes reasoning in LLMs through reinforcement learning2025DeepSeek-AI./papers/00095-DeepSeek_R1.pdf
Inference-Time Scaling for Generalist Reward Modeling2025DeepSeek-AI./papers/00056-DeepSeek-GRM.pdf
DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models2024DeepSeek-AI./papers/00057-GRPO.pdf
DeepSeek-OCR: Contexts Optical Compression2025DeepSeek-AI./papers/00116-DeepSeek-OCR.pdf
DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models2025DeepSeek-AI./papers/00133-DeepSeek-V3.2.pdf
DeepSeekMath-V2: Towards Self-Verifiable Mathematical Reasoning2025DeepSeek-AI./papers/00136-DeepSeekMath_V2.pdf
mHC: Manifold-Constrained Hyper-Connections2025DeepSeek-AI./papers/00148-mHC.pdf
Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models2026DeepSeek-AI./papers/00150-Engram.pdf
DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence2026DeepSeek-AI./papers/00172-DeepSeek_V4.pdf
DSpark: Confidence-Scheduled Speculative Decoding with Semi-Autoregressive Generation2026DeepSeek-AI./papers/00174-DSpark_paper.pdf
DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression2026DeepSeek-AI./papers/00191-DeepSeek_V41.pdf

KimiTeam

论文年份论文单位笔记地址
Kimi K2: Open Agentic Intelligence2025KimiTeam./papers/00083-Kimi-K2.pdf
Kimi Linear: An Expressive, Efficient Attention Architecture2025KimiTeam./papers/00132-Kimi-Linear.pdf
Kimi K2.5: Visual Agentic Intelligence2026KimiTeam./papers/00156-kimi-k2.5.pdf

MiniMax

论文年份论文单位笔记地址
MiniMax Sparse Attention2026MiniMax./papers/00179-MSA.pdf

Microsoft

论文年份论文单位笔记地址
ZeRO: Memory Optimizations Toward Training Trillion Parameter Models2020Microsoft./papers/00002-ZeRO.pdf
Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone2024Microsoft./papers/00004-Phi-3.pdf
DeepSpeed-Chat: Easy, Fast and Affordable RLHF Training of ChatGPT-like Models at All Scales2023Microsoft./papers/00013-DeepSpeed-Chat.pdf
ZeroQuant(4+2): Redefining LLMs Quantization with a New FP6-Centric Strategy for Diverse Generative Tasks2023Microsoft./papers/00014-ZeroQuant(4+2).pdf
DeepSpeed Inference: Enabling Efficient Inference of Transformer Models at Unprecedented Scale2022Microsoft./papers/00015-DeepSpeed-Inference.pdf
DeepSpeed Ulysses: System Optimizations for Enabling Training of Extreme Long Sequence Transformer Models2023Microsoft./papers/00016-DeepSpeed-Ulysses.pdf
ZeRO-Offload: Democratizing Billion-Scale Model Training2021Microsoft./papers/00017-ZeRO-Offload.pdf
1-bit Adam: Communication Efficient Large-Scale Training with Adam's Convergence Speed2021Microsoft./papers/00018-1-bit-Adam.pdf
ZeRO-Infinity: Breaking the GPU Memory Wall for Extreme Scale Deep Learning2021Microsoft./papers/00019-ZeRO-Infinity.pdf
1-bit LAMB: Communication Efficient Large-Scale Large-Batch Training with LAMB's Convergence Speed2021Microsoft./papers/00020-1-bit-LAMB.pdf
The Stability-Efficiency Dilemma: Investigating Sequence Length Warmup for Training GPT Models2022Microsoft./papers/00021-Sequence-Length-Warmup.pdf
Maximizing Communication Efficiency for Large-scale Training via 0/1 Adam2022Microsoft./papers/00023-0-1-Adam.pdf
DeepSpeed-MoE: Advancing Mixture-of-Experts Inference and Training to Power Next-Generation AI Scale2022Microsoft./papers/00023-DeepSpeed-MoE.pdf
Using DeepSpeed and Megatron to Train Megatron-Turing NLG 530B, A Large-Scale Generative Language Model2022Microsoft./papers/00024-Megatron-Turing.pdf
Extreme Compression for Pre-trained Transformers Made Simple and Efficient2022Microsoft./papers/00025-XTC.pdf
ZeroQuant: Efficient and Affordable Post-Training Quantization for Large-Scale Transformers2022Microsoft./papers/00026-ZeroQuant.pdf
DeepSpeed Data Efficiency: Improving Deep Learning Model Quality and Training Efficiency via Efficient Data Sampling and Routing2024Microsoft./papers/00027-DeepSpeed-Data-Efficiency.pdf
Understanding INT4 Quantization for Transformer Models: Latency Speedup, Composability, and Failure Cases2023Microsoft./papers/00029-INT4-Quantization.pdf
ZeroQuant-FP: A Leap Forward in LLMs Post-Training W4A8 Quantization Using Floating-Point Formats2023Microsoft./papers/00030-ZeroQuant-FP.pdf
ZeRO++: Extremely Efficient Collective Communication for Giant Model Training2023Microsoft./papers/00031-ZeRO++.pdf
ZeroQuant-HERO: Hardware-Enhanced Robust Optimized Post-Training Quantization Framework for W8A8 Transformers2023Microsoft./papers/00032-ZeroQuant-HERO.pdf
rStar-Math: Small LLMs Can Master Math Reasoning with Self-Evolved Deep Thinking2025Microsoft./papers/00044-rStar-Math.pdf
From Local to Global: A Graph RAG Approach to Query-Focused Summarization2024Microsoft./papers/00046-GraphRAG.pdf
Logic-RL: Unleashing LLM Reasoning with Rule-Based Reinforcement Learning2025Microsoft./papers/00050-Logic-RL.pdf
LongRoPE2: Near-Lossless LLM Context Window Scaling2025Microsoft./papers/00063-LongRoPE2.pdf
BitNet b1.58 2B4T Technical Report2025Microsoft./papers/00064-BitNet.pdf
1-bit AI Infra: Part 1.1, Fast and Lossless BitNet b1.58 Inference on CPUs2024Microsoft./papers/00065-1-bit.pdf
Bitnet.cpp: Efficient Edge Inference for Ternary LLMs2025Microsoft./papers/00066-Bitnet.cpp.pdf
MiniLLM: Knowledge Distillation of Large Language Models2023Microsoft./papers/00075-MiniLLM.pdf
rStar2-Agent: Agentic Reasoning Technical Report2025Microsoft./papers/00092-rStar.pdf
RPG: A Repository Planning Graph for Unified and Scalable Codebase Generation2025Microsoft./papers/00111-RPG.pdf
Agent Lightning: Train ANY AI Agents with Reinforcement Learning2025Microsoft./papers/00124-agent-lightning.pdf
X-Coder: Advancing Competitive Programming with Fully Synthetic Tasks, Solutions, and Tests2026Microsoft./papers/00161-X-Coder.pdf

Google

论文年份论文单位笔记地址
Chain-of-Thought Prompting Elicits Reasoning in Large Language Models2022Google./papers/00008-CoT.pdf
Distilling the Knowledge in a Neural Network2015Google./papers/00076-distill-model.pdf
STaR: Bootstrapping Reasoning With Reasoning2022Google./papers/00077-STaR.pdf
ReAct: Synergizing Reasoning and Acting in Language Models2022Google./papers/00078-ReAct.pdf
Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities2025Google./papers/00080-Gemini-2.5.pdf
Gemma 3 Technical Report2025Google./papers/00081-Gemma-3.pdf

Meta

论文年份论文单位笔记地址
The Llama 3 Herd of Models2024Meta./papers/00006-Llama3.pdf
Deep Think with Confidence2025Meta./papers/00084-DeepConf.pdf
REFRAG: Rethinking RAG based Decoding2025Meta./papers/00090-REFRAG.pdf
The Art of Scaling Reinforcement Learning Compute for LLMs2025Meta./papers/00121-ScaleRL.pdf
Dr. Zero: Self-Evolving Search Agents without Training Data2026Meta./papers/00155-Dr.Zero.pdf

DeepMind

论文年份论文单位笔记地址
Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters2024DeepMind./papers/00036-Scaling-LLM-Test-Time-Compute-Optimally.pdf
Improve Mathematical Reasoning in Language Models by Automated Process Supervision2024DeepMind./papers/00039-Automated-Process-Supervision.pdf
Extracting alignment data in open models2025DeepMind./papers/00126-extracting-alignment-data.pdf
Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory2025DeepMind./papers/00139-Evo-Memory.pdf

NVIDIA

论文年份论文单位笔记地址
Reducing Activation Recomputation in Large Transformer Models2022NVIDIA./papers/00012-selective-activation-recomputation.pdf
ToolOrchestra: Elevating Intelligence via Efficient Model and Tool Orchestration2025NVIDIA./papers/00140-ToolOrchestra.pdf
GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization2026NVIDIA./papers/00144-GDPO.pdf
ACE-RTL: When Agentic Context Evolution Meets RTL-Specialized LLMs2026NVIDIA./papers/00158-ACE-RTL.pdf
Autonomous Evolution of EDA Tools: Multi-Agent Self-Evolved ABC2026NVIDIA./papers/00168-self-evolving.pdf

Hugging Face

论文年份论文单位笔记地址
SmolLM2: When Smol Goes Big -- Data-Centric Training of a Small Language Model2025Hugging Face./papers/00159-SmolLM2.pdf

Alibaba Group

论文年份论文单位笔记地址
AlphaMath Almost Zero: process Supervision without process2024Alibaba Group./papers/00007-AlphaMath.pdf
Qwen2.5-Coder Technical Report2024Alibaba Group./papers/00033-Qwen2.5-Coder.pdf
Qwen3 Technical Report2025Alibaba Group./papers/00069-Qwen3_Technical_Report.pdf
Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models2025Alibaba Group./papers/00073-Qwen3-Embedding.pdf
WebWalker: Benchmarking LLMs in Web Traversal2025Alibaba Group./papers/00097-WebWalker.pdf
WebDancer: Towards Autonomous Information Seeking Agency2025Alibaba Group./papers/00098-WebDancer.pdf
WebSailor: Navigating Super-human Reasoning for Web Agent2025Alibaba Group./papers/00082-WebSailor.pdf
WebShaper: Agentically Data Synthesizing via Information-Seeking Formalization2025Alibaba Group./papers/00099-WebShaper.pdf
WebWatcher: Breaking New Frontier of Vision-Language Deep Research Agent2025Alibaba Group./papers/00100-WebWatcher.pdf
WebResearcher: Unleashing unbounded reasoning capability in Long-Horizon Agents2025Alibaba Group./papers/00101-WebResearcher.pdf
ReSum: Unlocking Long-Horizon Search Intelligence via Context Summarization2025Alibaba Group./papers/00102-ReSum.pdf
WebWeaver: Structuring Web-Scale Evidence with Dynamic Outlines for Open-Ended Deep Research2025Alibaba Group./papers/00103-WebWeaver.pdf
WebSailor-V2: Bridging the Chasm to Proprietary Agents via Synthetic Data and Scalable Reinforcement Learning2025Alibaba Group./papers/00104-WebSailor-V2.pdf
Scaling Agents via Continual Pre-training2025Alibaba Group./papers/00105-AgentFounder.pdf
Towards General Agentic Intelligence via Environment Scaling2025Alibaba Group./papers/00106-AgentScaler.pdf
On-Policy RL Meets Off-Policy Experts: Harmonizing Supervised Fine-Tuning and Reinforcement Learning via Dynamic Weighting2025Alibaba Group./papers/00094-CHORD.pdf
Group Sequence Policy Optimization2025Alibaba Group./papers/00107-GSPO.pdf
Tree Search for LLM Agent Reinforcement Learning2025Alibaba Group./papers/00127-Tree-GRPO.pdf
Search Self-play: Pushing the Frontier of Agent Capability without Supervision2025Alibaba Group./papers/00129-SSP.pdf
Soft Adaptive Policy Optimization2025Alibaba Group./papers/00134-SAPO.pdf
AgentEvolver: Towards Efficient Self-Evolving Agent System2025Alibaba Group./papers/00138-AgentEvolver.pdf
ArenaRL: Scaling RL for Open-Ended Agents via Tournament-based Relative Ranking2026Alibaba Group./papers/00143-ArenaRL.pdf
AMAP Agentic Planning Technical Report2025Alibaba Group./papers/00151-AMAP.pdf
Distribution-Aligned Sequence Distillation for Superior Long-CoT Reasoning2026Alibaba Group./papers/00153-DASD.pdf
Let It Flow: Agentic Crafting on Rock and Roll, Building the ROME Model within an Open Agentic Learning Ecosystem2025Alibaba Group./papers/00165-ALE.pdf
SkillClaw: Let Skills Evolve Collectively with Agentic Evolver2026Alibaba Group./papers/00167-SkillClaw.pdf
LongHorizon-Harness: Advancing Long-Horizon Agents for Real-World Tasks2026Alibaba Group./papers/00185-LongHorizon-Harness.pdf
Context as an Environment: Programmatic Context Management for Long-Horizon Agents2026Alibaba Group./papers/00186-Scroll.pdf

ByteDance

论文年份论文单位笔记地址
HybridFlow: A Flexible and Efficient RLHF Framework2024ByteDance./papers/00054-HybridFlow.pdf
DAPO: An Open-Source LLM Reinforcement Learning System at Scale2025ByteDance./papers/00055-DAPO.pdf
VAPO: Efficient and Reliable Reinforcement Learning for Advanced Reasoning Tasks2025ByteDance./papers/00067-VAPO.pdf
Seed1.5-Thinking: Advancing Superb Reasoning Models with Reinforcement Learning2025ByteDance./papers/00068-Seed1.5-Thinking.pdf
Seed-Coder: Let the Code Model Curate Data for Itself2025ByteDance./papers/00070-Seed-Coder.pdf
Seeing, Listening, Remembering, and Reasoning: A Multimodal Agent with Long-Term Memory2025ByteDance./papers/00091-M3-Agent.pdf
MemAgent: Reshaping Long-Context LLM with Multi-Conv RL-based Memory Agent2025ByteDance./papers/00109-MemAgent.pdf
Scaling Latent Reasoning via Looped Language Models2025ByteDance./papers/00122-Ouro.pdf
Scaling Long-Horizon LLM Agent via Context-Folding2025ByteDance./papers/00128-context-folding.pdf
HarnessDev: Can LLMs Create and Evolve Their Own Agent Harness?2026ByteDance./papers/00189-HarnessDev.pdf

Tencent

论文年份论文单位笔记地址
Training-Free Group Relative Policy Optimization2025Tencent./papers/00108-Training-Free-GRPO.pdf
HY-MT1.5 Technical Report2025Tencent./papers/00152-HY-MT1.5.pdf

Xiaomi

论文年份论文单位笔记地址
ThinkOmni: Lifting Textual Reasoning to Omni-modal Scenarios via Guidance Decoding2026Xiaomi./papers/00162-ThinkOmni.pdf

OPPO AI Agent Team

论文年份论文单位笔记地址
Chain-of-Agents: End-to-End Agent Foundation Models via Multi-Agent Distillation and Agentic RL2025OPPO AI Agent Team./papers/00118-Chain-of-Agents.pdf
O-Researcher: An Open Ended Deep Research Model via Multi-Agent Distillation and Agentic RL2026OPPO AI Agent Team./papers/00154-O-Researcher.pdf

Meituan LongCat Team

论文年份论文单位笔记地址
LongCat-Flash Technical Report2025Meituan LongCat Team./papers/00093-LongCat-Flash.pdf

Xiaohongshu

论文年份论文单位笔记地址
LongMagpie: A Self-synthesis Method for Generating Large-scale Long-context Instructions2025Xiaohongshu./papers/00117-LongMagpie.pdf
DeepAgent: A General Reasoning Agent with Scalable Toolsets2025Xiaohongshu./papers/00123-DeepAgent.pdf
PretrainZero: Reinforcement Active Pretraining2025Xiaohongshu./papers/00141-PretrainZero.pdf

Sina Weibo

论文年份论文单位笔记地址
Tiny Model, Big Logic: Diversity-Driven Optimization Elicits Large-Model Reasoning Ability in VibeThinker-1.5B2025Sina Weibo./papers/00137-VibeThinker-1.5B.pdf

Baidu

论文年份论文单位笔记地址
Unlimited OCR Works2026Baidu./papers/00176-Unlimited-OCR.pdf
PaddleOCR-VL-1.6: Expanding the Frontier of Document Parsing with Under-Optimized Region Refinement and Progressive Post-Training2026Baidu./papers/00181-PaddleOCR-VL-1.6.pdf

Shanghai Artificial Intelligence Laboratory

论文年份论文单位笔记地址
FlowSearch: Advancing deep research with dynamic structured knowledge flow2025Shanghai Artificial Intelligence Laboratory./papers/00142-FlowSearch.pdf
Harness-of-Harness: Multi-Day Autonomous Software Development with Continual Improvement2026Shanghai Artificial Intelligence Laboratory./papers/00188-Harness-of-Harness.pdf

EleutherAI

论文年份论文单位笔记地址
YaRN: Efficient Context Window Extension of Large Language Models2023EleutherAI./papers/00034-YaRN.pdf

Huawei Noah’s Ark Lab

论文年份论文单位笔记地址
Memento: Fine-tuning LLM Agents without Fine-tuning LLMs2025Huawei Noah’s Ark Lab./papers/00089-Memento.pdf

Tsinghua University

论文年份论文单位笔记地址
MiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategies2024Tsinghua University./papers/00003-MiniCPM.pdf
ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools2024Tsinghua University./papers/00005-ChatGLM.pdf
LongWriter: Unleashing 10,000+ Word Generation from Long Context LLMs2024Tsinghua University./papers/00038-LongWriter.pdf
ReST-MCTS*: LLM Self-Training via Process Reward Guided Tree Search2024Tsinghua University./papers/00043-ReST-MCTS.pdf
GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models2025Tsinghua University./papers/00113-GLM-4.5.pdf
GLM-5: from Vibe Coding to Agentic Engineering2026Tsinghua University./papers/00157-GLM-5.pdf
AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning2025Tsinghua University./papers/00160-AReaL.pdf

Peking University

论文年份论文单位笔记地址
Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations2024Peking University./papers/00040-Math-Shepherd.pdf
ChartMoE: Mixture of Diversely Aligned Expert Connector for Chart Understanding2024Peking University./papers/00049-ChartMoE.pdf

Carnegie Mellon University

论文年份论文单位笔记地址
Optimizing Test-Time Compute via Meta Reinforcement Fine-Tuning2025Carnegie Mellon University./papers/00053-MRT.pdf

University of California, Berkeley

论文年份论文单位笔记地址
Efficient Memory Management for Large Language Model Serving with PagedAttention2023University of California, Berkeley./papers/00086-vllm.pdf
SGLang: Efficient Execution of Structured Language Model Programs2024University of California, Berkeley./papers/00164-SGLang.pdf
Ring Attention with Blockwise Transformers for Near-Infinite Context2023University of California, Berkeley./papers/00087-RingAttention.pdf
Blockwise Parallel Transformer for Large Context Models2023University of California, Berkeley./papers/00088-BPT.pdf
RL Grokking Recipe: How Does RL Unlock and Transfer New Algorithms in LLMs?2025University of California, Berkeley./papers/00115-grokking.pdf
SimpleMem: Efficient Lifelong Memory for LLM Agents2026University of California, Berkeley./papers/00145-SimpleMem.pdf
From Model Scaling to System Scaling: Scaling the Harness in Agentic AI2026University of California, Berkeley./papers/00182-CheetahClaws.pdf

MIT

论文年份论文单位笔记地址
Striped Attention: Faster Ring Attention for Causal Transformers2023MIT./papers/00096-Striped-Attention.pdf

Stanford University

论文年份论文单位笔记地址
In-the-Flow Agentic System Optimization for Effective Planning and Tool Use2025Stanford University./papers/00125-in-the-flow.pdf

Princeton University

论文年份论文单位笔记地址
Skill-Targeted Adaptive Training2025Princeton University./papers/00119-STAT.pdf
OpenClaw-RL: Train Any Agent Simply by Talking2026Princeton University./papers/00171-OpenClaw-RL.pdf

National University of Singapore

论文年份论文单位笔记地址
Understanding R1-Zero-Like Training: A Critical Perspective2025National University of Singapore./papers/00048-understand-r1-zero.pdf

Fudan University

论文年份论文单位笔记地址
EvoSyn: Generalizable Evolutionary Data Synthesis for Verifiable Learning2025Fudan University./papers/00120-EvoSyn.pdf
AgentPRM: Process Reward Models for LLM Agents via Step-Wise Promise and Progress2025Fudan University./papers/00135-AgentPRM.pdf

Shanghai Jiao Tong University

论文年份论文单位笔记地址
LIMO: Less is More for Reasoning2025Shanghai Jiao Tong University./papers/00051-LIMO.pdf
Context Engineering 2.0: The Context of Context Engineering2025Shanghai Jiao Tong University./papers/00131-Context-Engineering-2.0.pdf
Repo0: Design-Driven Zero-to-All Code Generation2026Shanghai Jiao Tong University./papers/00184-Repo0.pdf

Nanjing University

论文年份论文单位笔记地址
A Comprehensive Survey on Long Context Language Modeling2025Nanjing University./papers/00058-LCLM.pdf
DART: Diffusion-Inspired Speculative Decoding for Fast LLM Inference2026Nanjing University./papers/00175-DART.pdf

Renmin University of China

论文年份论文单位笔记地址
Imitate, Explore, and Self-Improve: A Reproduction Report on Slow-thinking Reasoning Systems2024Renmin University of China./papers/00037-o1-like.pdf
Search-o1: Agentic Search-Enhanced Large Reasoning Models2025Renmin University of China./papers/00059-Search-o1.pdf
WebThinker: Empowering Large Reasoning Models with Deep Research Capability2025Renmin University of China./papers/00074-WebThinker.pdf
R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning2025Renmin University of China./papers/00062-R1-Searcher.pdf
From Trial-and-Error to Improvement: A Systematic Analysis of LLM Exploration Mechanisms in RLVR2025Renmin University of China./papers/00085-RLVR.pdf
DeepCritic: Deliberate Critique with Large Language Models2025Renmin University of China./papers/00114-DeepCritic.pdf
ET-Agent: Incentivizing Effective Tool-Integrated Reasoning Agent via Behavior Calibration2026Renmin University of China./papers/00146-ET-Agent.pdf
SmartSearch: Process Reward-Guided Query Refinement for Search Agents2026Renmin University of China./papers/00147-SmartSearch.pdf
EnvScaler: Scaling Tool-Interactive Environments for LLM Agent via Programmatic Synthesis2026Renmin University of China./papers/00149-EnvScaler.pdf
Toward Generalist Autonomous Research via Hypothesis-Tree Refinement2026Renmin University of China./papers/00178-Arbor.pdf

University of Illinois Urbana-Champaign

论文年份论文单位笔记地址
DeepRetrieval: Hacking Real Search Engines and Retrievers with Large Language Models via Reinforcement Learning2025University of Illinois Urbana-Champaign./papers/00060-DeepRetrieval.pdf
Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning2025University of Illinois Urbana-Champaign./papers/00061-Search-R1.pdf
Executable Code Actions Elicit Better LLM Agents2024University of Illinois Urbana-Champaign./papers/00166-CodeAct.pdf
CoRNStack: High-Quality Contrastive Data for Better Code Retrieval and Reranking2024University of Illinois Urbana-Champaign./papers/00170-CoRNStack.pdf

Hong Kong University of Science and Technology

论文年份论文单位笔记地址
Dr. RTL: Autonomous Agentic RTL Optimization through Tool-Grounded Self-Improvement2026Hong Kong University of Science and Technology./papers/00169-Dr.RTL.pdf

Institute of Computing Technology, Chinese Academy of Sciences

论文年份论文单位笔记地址
AssertMiner: Module-Level Spec Generation and Assertion Mining using Static Analysis Guided LLMs2025Institute of Computing Technology, Chinese Academy of Sciences./papers/00173-AssertMiner.pdf
AssertMiner-pro: Enhanced module-level spec generation and assertion mining with LLM guided by top-down hierarchical strategies2026Institute of Computing Technology, Chinese Academy of Sciences./papers/00177-AssertMiner-pro.pdf

Columbia University

论文年份论文单位笔记地址
NoTB: Oracle-Free Triage of LLM-Generated RTL via Cross-Model Formal Consensus2026Columbia University./papers/00183-NoTB.pdf

其他

论文年份论文单位笔记地址
LightRAG: Simple and Fast Retrieval-Augmented Generation2024Beijing University of Posts and Telecommunications./papers/00047-LightRAG.pdf
HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Models2024The Ohio State University./papers/00071-HippoRAG.pdf
From RAG to Memory: Non-Parametric Continual Learning for Large Language Models2025The Ohio State University./papers/00072-HippoRAG2.pdf
Chinese Tiny LLM: Pretraining a Chinese-Centric Large Language Model2024University of Waterloo./papers/00011-Chinese-Tiny-LLM.pdf
OpenR: An Open Source Framework for Advanced Reasoning with Large Language Models2024University College London./papers/00041-OpenR.pdf
Retrieval-Augmented Generation with Graphs (GraphRAG)2025Michigan State University./papers/00052-GraphRAG-review.pdf
RoFormer: Enhanced Transformer with Rotary Position Embedding2021Zhuiyi Technology./papers/00009-RoPE.pdf
Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions2022Allen Institute for AI./papers/00079-IRCoT.pdf
Memory as Action: Autonomous Context Curation for Long-Horizon Agentic Tasks2025Beijing Jiaotong University./papers/00110-MemAct.pdf
Scientific Algorithm Discovery by Augmenting AlphaEvolve with Deep Research2025IBM Research./papers/00112-DeepEvolve.pdf
Liger-Kernel: Efficient Triton Kernels for LLM Training2025LinkedIn./papers/00130-Liger-Kernel.pdf
HyperRAG: Reasoning N-ary Facts over Hypergraphs for Retrieval Augmented Generation2026National Yang Ming Chiao Tung University./papers/00163-HyperRAG.pdf
Dive into Claude Code: The Design Space of Today's and Future AI Agent Systems2026VILA Lab./papers/00180-Dive-into-Claude-Code.pdf
Miles v0.1: Production-Level Post-Training2026Miles Team./papers/00187-Miles.pdf
MechMem-RTL: Reusing Verified Mechanism Memories for LLM-Based RTL Repair2026Hunan University./papers/00190-MechMem-RTL.pdf

书籍

  1. ./books/00001-Claude-Code-Harness-Engineering-Book.pdf

工具

  1. Overleaf

论文集

  1. huggingface daily papers
  2. arxiv

Contributors

yanfeng98

151 commits

Similar repos

0xPabloxx/llm-paper-notes

My reading notes on LLM/VLM research — post-training, pretraining, agents, multimodal,…

0

hijkzzz/Awesome-LLM-Strawberry

A collection of LLM papers, blogs, and projects, with a focus on OpenAI o1 🍓 and reasoning…

6,908

cycloarcane/Gathered-Paper-Resources

In this repo I will upload aggregated resources I get from my daily reading of academic papers.

14

gyunggyung/AGI-Papers

A curated archive of breakthroughs in Agents, Architecture, Training, RAG, and On-Device AI.

421

itsual/Notable-LLM-Research-Papers

Curated list of research papers published in 2024 related to Large Language Models (LLM)

50

Hannibal046/Awesome-LLM

Awesome-LLM: a curated list of Large Language Model

27,422

benjaminzwhite/reasoning-models

Experiments with reasoning models, training techniques, papers

30

ChenZiHong-Gavin/llm-tech-report

A summary of technical reports for various large language models (LLMs).

39

Languages

TeX

88.6%

BibTeX Style

11.3%

yanfeng98/paper-is-all-you-need

论文就是你所需要的。

TeX

2

151 commits

updated Sep 14, 2026

See the code

README

paper-is-all-you-need

论文就是你所需要的。

论文

OpenAI

论文年份论文单位笔记地址
Scaling Laws for Neural Language Models2020OpenAI./papers/00001-scaling-laws.pdf
Let's Verify Step by Step2023OpenAI./papers/00028-Verify-Step-by-Step.pdf
Efficient Training of Language Models to Fill in the Middle2022OpenAI./papers/00035-fim.pdf

DeepSeek-AI

论文年份论文单位笔记地址
DeepSeek-V3 Technical Report2024DeepSeek-AI./papers/00042-DeepSeek-V3.pdf
DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning2025DeepSeek-AI./papers/00045-DeepSeek_R1.pdf
DeepSeek-R1 incentivizes reasoning in LLMs through reinforcement learning2025DeepSeek-AI./papers/00095-DeepSeek_R1.pdf
Inference-Time Scaling for Generalist Reward Modeling2025DeepSeek-AI./papers/00056-DeepSeek-GRM.pdf
DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models2024DeepSeek-AI./papers/00057-GRPO.pdf
DeepSeek-OCR: Contexts Optical Compression2025DeepSeek-AI./papers/00116-DeepSeek-OCR.pdf
DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models2025DeepSeek-AI./papers/00133-DeepSeek-V3.2.pdf
DeepSeekMath-V2: Towards Self-Verifiable Mathematical Reasoning2025DeepSeek-AI./papers/00136-DeepSeekMath_V2.pdf
mHC: Manifold-Constrained Hyper-Connections2025DeepSeek-AI./papers/00148-mHC.pdf
Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language Models2026DeepSeek-AI./papers/00150-Engram.pdf
DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence2026DeepSeek-AI./papers/00172-DeepSeek_V4.pdf
DSpark: Confidence-Scheduled Speculative Decoding with Semi-Autoregressive Generation2026DeepSeek-AI./papers/00174-DSpark_paper.pdf
DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression2026DeepSeek-AI./papers/00191-DeepSeek_V41.pdf

KimiTeam

论文年份论文单位笔记地址
Kimi K2: Open Agentic Intelligence2025KimiTeam./papers/00083-Kimi-K2.pdf
Kimi Linear: An Expressive, Efficient Attention Architecture2025KimiTeam./papers/00132-Kimi-Linear.pdf
Kimi K2.5: Visual Agentic Intelligence2026KimiTeam./papers/00156-kimi-k2.5.pdf

MiniMax

论文年份论文单位笔记地址
MiniMax Sparse Attention2026MiniMax./papers/00179-MSA.pdf

Microsoft

论文年份论文单位笔记地址
ZeRO: Memory Optimizations Toward Training Trillion Parameter Models2020Microsoft./papers/00002-ZeRO.pdf
Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone2024Microsoft./papers/00004-Phi-3.pdf
DeepSpeed-Chat: Easy, Fast and Affordable RLHF Training of ChatGPT-like Models at All Scales2023Microsoft./papers/00013-DeepSpeed-Chat.pdf
ZeroQuant(4+2): Redefining LLMs Quantization with a New FP6-Centric Strategy for Diverse Generative Tasks2023Microsoft./papers/00014-ZeroQuant(4+2).pdf
DeepSpeed Inference: Enabling Efficient Inference of Transformer Models at Unprecedented Scale2022Microsoft./papers/00015-DeepSpeed-Inference.pdf
DeepSpeed Ulysses: System Optimizations for Enabling Training of Extreme Long Sequence Transformer Models2023Microsoft./papers/00016-DeepSpeed-Ulysses.pdf
ZeRO-Offload: Democratizing Billion-Scale Model Training2021Microsoft./papers/00017-ZeRO-Offload.pdf
1-bit Adam: Communication Efficient Large-Scale Training with Adam's Convergence Speed2021Microsoft./papers/00018-1-bit-Adam.pdf
ZeRO-Infinity: Breaking the GPU Memory Wall for Extreme Scale Deep Learning2021Microsoft./papers/00019-ZeRO-Infinity.pdf
1-bit LAMB: Communication Efficient Large-Scale Large-Batch Training with LAMB's Convergence Speed2021Microsoft./papers/00020-1-bit-LAMB.pdf
The Stability-Efficiency Dilemma: Investigating Sequence Length Warmup for Training GPT Models2022Microsoft./papers/00021-Sequence-Length-Warmup.pdf
Maximizing Communication Efficiency for Large-scale Training via 0/1 Adam2022Microsoft./papers/00023-0-1-Adam.pdf
DeepSpeed-MoE: Advancing Mixture-of-Experts Inference and Training to Power Next-Generation AI Scale2022Microsoft./papers/00023-DeepSpeed-MoE.pdf
Using DeepSpeed and Megatron to Train Megatron-Turing NLG 530B, A Large-Scale Generative Language Model2022Microsoft./papers/00024-Megatron-Turing.pdf
Extreme Compression for Pre-trained Transformers Made Simple and Efficient2022Microsoft./papers/00025-XTC.pdf
ZeroQuant: Efficient and Affordable Post-Training Quantization for Large-Scale Transformers2022Microsoft./papers/00026-ZeroQuant.pdf
DeepSpeed Data Efficiency: Improving Deep Learning Model Quality and Training Efficiency via Efficient Data Sampling and Routing2024Microsoft./papers/00027-DeepSpeed-Data-Efficiency.pdf
Understanding INT4 Quantization for Transformer Models: Latency Speedup, Composability, and Failure Cases2023Microsoft./papers/00029-INT4-Quantization.pdf
ZeroQuant-FP: A Leap Forward in LLMs Post-Training W4A8 Quantization Using Floating-Point Formats2023Microsoft./papers/00030-ZeroQuant-FP.pdf
ZeRO++: Extremely Efficient Collective Communication for Giant Model Training2023Microsoft./papers/00031-ZeRO++.pdf
ZeroQuant-HERO: Hardware-Enhanced Robust Optimized Post-Training Quantization Framework for W8A8 Transformers2023Microsoft./papers/00032-ZeroQuant-HERO.pdf
rStar-Math: Small LLMs Can Master Math Reasoning with Self-Evolved Deep Thinking2025Microsoft./papers/00044-rStar-Math.pdf
From Local to Global: A Graph RAG Approach to Query-Focused Summarization2024Microsoft./papers/00046-GraphRAG.pdf
Logic-RL: Unleashing LLM Reasoning with Rule-Based Reinforcement Learning2025Microsoft./papers/00050-Logic-RL.pdf
LongRoPE2: Near-Lossless LLM Context Window Scaling2025Microsoft./papers/00063-LongRoPE2.pdf
BitNet b1.58 2B4T Technical Report2025Microsoft./papers/00064-BitNet.pdf
1-bit AI Infra: Part 1.1, Fast and Lossless BitNet b1.58 Inference on CPUs2024Microsoft./papers/00065-1-bit.pdf
Bitnet.cpp: Efficient Edge Inference for Ternary LLMs2025Microsoft./papers/00066-Bitnet.cpp.pdf
MiniLLM: Knowledge Distillation of Large Language Models2023Microsoft./papers/00075-MiniLLM.pdf
rStar2-Agent: Agentic Reasoning Technical Report2025Microsoft./papers/00092-rStar.pdf
RPG: A Repository Planning Graph for Unified and Scalable Codebase Generation2025Microsoft./papers/00111-RPG.pdf
Agent Lightning: Train ANY AI Agents with Reinforcement Learning2025Microsoft./papers/00124-agent-lightning.pdf
X-Coder: Advancing Competitive Programming with Fully Synthetic Tasks, Solutions, and Tests2026Microsoft./papers/00161-X-Coder.pdf

Google

论文年份论文单位笔记地址
Chain-of-Thought Prompting Elicits Reasoning in Large Language Models2022Google./papers/00008-CoT.pdf
Distilling the Knowledge in a Neural Network2015Google./papers/00076-distill-model.pdf
STaR: Bootstrapping Reasoning With Reasoning2022Google./papers/00077-STaR.pdf
ReAct: Synergizing Reasoning and Acting in Language Models2022Google./papers/00078-ReAct.pdf
Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities2025Google./papers/00080-Gemini-2.5.pdf
Gemma 3 Technical Report2025Google./papers/00081-Gemma-3.pdf

Meta

论文年份论文单位笔记地址
The Llama 3 Herd of Models2024Meta./papers/00006-Llama3.pdf
Deep Think with Confidence2025Meta./papers/00084-DeepConf.pdf
REFRAG: Rethinking RAG based Decoding2025Meta./papers/00090-REFRAG.pdf
The Art of Scaling Reinforcement Learning Compute for LLMs2025Meta./papers/00121-ScaleRL.pdf
Dr. Zero: Self-Evolving Search Agents without Training Data2026Meta./papers/00155-Dr.Zero.pdf

DeepMind

论文年份论文单位笔记地址
Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters2024DeepMind./papers/00036-Scaling-LLM-Test-Time-Compute-Optimally.pdf
Improve Mathematical Reasoning in Language Models by Automated Process Supervision2024DeepMind./papers/00039-Automated-Process-Supervision.pdf
Extracting alignment data in open models2025DeepMind./papers/00126-extracting-alignment-data.pdf
Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory2025DeepMind./papers/00139-Evo-Memory.pdf

NVIDIA

论文年份论文单位笔记地址
Reducing Activation Recomputation in Large Transformer Models2022NVIDIA./papers/00012-selective-activation-recomputation.pdf
ToolOrchestra: Elevating Intelligence via Efficient Model and Tool Orchestration2025NVIDIA./papers/00140-ToolOrchestra.pdf
GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization2026NVIDIA./papers/00144-GDPO.pdf
ACE-RTL: When Agentic Context Evolution Meets RTL-Specialized LLMs2026NVIDIA./papers/00158-ACE-RTL.pdf
Autonomous Evolution of EDA Tools: Multi-Agent Self-Evolved ABC2026NVIDIA./papers/00168-self-evolving.pdf

Hugging Face

论文年份论文单位笔记地址
SmolLM2: When Smol Goes Big -- Data-Centric Training of a Small Language Model2025Hugging Face./papers/00159-SmolLM2.pdf

Alibaba Group

论文年份论文单位笔记地址
AlphaMath Almost Zero: process Supervision without process2024Alibaba Group./papers/00007-AlphaMath.pdf
Qwen2.5-Coder Technical Report2024Alibaba Group./papers/00033-Qwen2.5-Coder.pdf
Qwen3 Technical Report2025Alibaba Group./papers/00069-Qwen3_Technical_Report.pdf
Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models2025Alibaba Group./papers/00073-Qwen3-Embedding.pdf
WebWalker: Benchmarking LLMs in Web Traversal2025Alibaba Group./papers/00097-WebWalker.pdf
WebDancer: Towards Autonomous Information Seeking Agency2025Alibaba Group./papers/00098-WebDancer.pdf
WebSailor: Navigating Super-human Reasoning for Web Agent2025Alibaba Group./papers/00082-WebSailor.pdf
WebShaper: Agentically Data Synthesizing via Information-Seeking Formalization2025Alibaba Group./papers/00099-WebShaper.pdf
WebWatcher: Breaking New Frontier of Vision-Language Deep Research Agent2025Alibaba Group./papers/00100-WebWatcher.pdf
WebResearcher: Unleashing unbounded reasoning capability in Long-Horizon Agents2025Alibaba Group./papers/00101-WebResearcher.pdf
ReSum: Unlocking Long-Horizon Search Intelligence via Context Summarization2025Alibaba Group./papers/00102-ReSum.pdf
WebWeaver: Structuring Web-Scale Evidence with Dynamic Outlines for Open-Ended Deep Research2025Alibaba Group./papers/00103-WebWeaver.pdf
WebSailor-V2: Bridging the Chasm to Proprietary Agents via Synthetic Data and Scalable Reinforcement Learning2025Alibaba Group./papers/00104-WebSailor-V2.pdf
Scaling Agents via Continual Pre-training2025Alibaba Group./papers/00105-AgentFounder.pdf
Towards General Agentic Intelligence via Environment Scaling2025Alibaba Group./papers/00106-AgentScaler.pdf
On-Policy RL Meets Off-Policy Experts: Harmonizing Supervised Fine-Tuning and Reinforcement Learning via Dynamic Weighting2025Alibaba Group./papers/00094-CHORD.pdf
Group Sequence Policy Optimization2025Alibaba Group./papers/00107-GSPO.pdf
Tree Search for LLM Agent Reinforcement Learning2025Alibaba Group./papers/00127-Tree-GRPO.pdf
Search Self-play: Pushing the Frontier of Agent Capability without Supervision2025Alibaba Group./papers/00129-SSP.pdf
Soft Adaptive Policy Optimization2025Alibaba Group./papers/00134-SAPO.pdf
AgentEvolver: Towards Efficient Self-Evolving Agent System2025Alibaba Group./papers/00138-AgentEvolver.pdf
ArenaRL: Scaling RL for Open-Ended Agents via Tournament-based Relative Ranking2026Alibaba Group./papers/00143-ArenaRL.pdf
AMAP Agentic Planning Technical Report2025Alibaba Group./papers/00151-AMAP.pdf
Distribution-Aligned Sequence Distillation for Superior Long-CoT Reasoning2026Alibaba Group./papers/00153-DASD.pdf
Let It Flow: Agentic Crafting on Rock and Roll, Building the ROME Model within an Open Agentic Learning Ecosystem2025Alibaba Group./papers/00165-ALE.pdf
SkillClaw: Let Skills Evolve Collectively with Agentic Evolver2026Alibaba Group./papers/00167-SkillClaw.pdf
LongHorizon-Harness: Advancing Long-Horizon Agents for Real-World Tasks2026Alibaba Group./papers/00185-LongHorizon-Harness.pdf
Context as an Environment: Programmatic Context Management for Long-Horizon Agents2026Alibaba Group./papers/00186-Scroll.pdf

ByteDance

论文年份论文单位笔记地址
HybridFlow: A Flexible and Efficient RLHF Framework2024ByteDance./papers/00054-HybridFlow.pdf
DAPO: An Open-Source LLM Reinforcement Learning System at Scale2025ByteDance./papers/00055-DAPO.pdf
VAPO: Efficient and Reliable Reinforcement Learning for Advanced Reasoning Tasks2025ByteDance./papers/00067-VAPO.pdf
Seed1.5-Thinking: Advancing Superb Reasoning Models with Reinforcement Learning2025ByteDance./papers/00068-Seed1.5-Thinking.pdf
Seed-Coder: Let the Code Model Curate Data for Itself2025ByteDance./papers/00070-Seed-Coder.pdf
Seeing, Listening, Remembering, and Reasoning: A Multimodal Agent with Long-Term Memory2025ByteDance./papers/00091-M3-Agent.pdf
MemAgent: Reshaping Long-Context LLM with Multi-Conv RL-based Memory Agent2025ByteDance./papers/00109-MemAgent.pdf
Scaling Latent Reasoning via Looped Language Models2025ByteDance./papers/00122-Ouro.pdf
Scaling Long-Horizon LLM Agent via Context-Folding2025ByteDance./papers/00128-context-folding.pdf
HarnessDev: Can LLMs Create and Evolve Their Own Agent Harness?2026ByteDance./papers/00189-HarnessDev.pdf

Tencent

论文年份论文单位笔记地址
Training-Free Group Relative Policy Optimization2025Tencent./papers/00108-Training-Free-GRPO.pdf
HY-MT1.5 Technical Report2025Tencent./papers/00152-HY-MT1.5.pdf

Xiaomi

论文年份论文单位笔记地址
ThinkOmni: Lifting Textual Reasoning to Omni-modal Scenarios via Guidance Decoding2026Xiaomi./papers/00162-ThinkOmni.pdf

OPPO AI Agent Team

论文年份论文单位笔记地址
Chain-of-Agents: End-to-End Agent Foundation Models via Multi-Agent Distillation and Agentic RL2025OPPO AI Agent Team./papers/00118-Chain-of-Agents.pdf
O-Researcher: An Open Ended Deep Research Model via Multi-Agent Distillation and Agentic RL2026OPPO AI Agent Team./papers/00154-O-Researcher.pdf

Meituan LongCat Team

论文年份论文单位笔记地址
LongCat-Flash Technical Report2025Meituan LongCat Team./papers/00093-LongCat-Flash.pdf

Xiaohongshu

论文年份论文单位笔记地址
LongMagpie: A Self-synthesis Method for Generating Large-scale Long-context Instructions2025Xiaohongshu./papers/00117-LongMagpie.pdf
DeepAgent: A General Reasoning Agent with Scalable Toolsets2025Xiaohongshu./papers/00123-DeepAgent.pdf
PretrainZero: Reinforcement Active Pretraining2025Xiaohongshu./papers/00141-PretrainZero.pdf

Sina Weibo

论文年份论文单位笔记地址
Tiny Model, Big Logic: Diversity-Driven Optimization Elicits Large-Model Reasoning Ability in VibeThinker-1.5B2025Sina Weibo./papers/00137-VibeThinker-1.5B.pdf

Baidu

论文年份论文单位笔记地址
Unlimited OCR Works2026Baidu./papers/00176-Unlimited-OCR.pdf
PaddleOCR-VL-1.6: Expanding the Frontier of Document Parsing with Under-Optimized Region Refinement and Progressive Post-Training2026Baidu./papers/00181-PaddleOCR-VL-1.6.pdf

Shanghai Artificial Intelligence Laboratory

论文年份论文单位笔记地址
FlowSearch: Advancing deep research with dynamic structured knowledge flow2025Shanghai Artificial Intelligence Laboratory./papers/00142-FlowSearch.pdf
Harness-of-Harness: Multi-Day Autonomous Software Development with Continual Improvement2026Shanghai Artificial Intelligence Laboratory./papers/00188-Harness-of-Harness.pdf

EleutherAI

论文年份论文单位笔记地址
YaRN: Efficient Context Window Extension of Large Language Models2023EleutherAI./papers/00034-YaRN.pdf

Huawei Noah’s Ark Lab

论文年份论文单位笔记地址
Memento: Fine-tuning LLM Agents without Fine-tuning LLMs2025Huawei Noah’s Ark Lab./papers/00089-Memento.pdf

Tsinghua University

论文年份论文单位笔记地址
MiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategies2024Tsinghua University./papers/00003-MiniCPM.pdf
ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools2024Tsinghua University./papers/00005-ChatGLM.pdf
LongWriter: Unleashing 10,000+ Word Generation from Long Context LLMs2024Tsinghua University./papers/00038-LongWriter.pdf
ReST-MCTS*: LLM Self-Training via Process Reward Guided Tree Search2024Tsinghua University./papers/00043-ReST-MCTS.pdf
GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models2025Tsinghua University./papers/00113-GLM-4.5.pdf
GLM-5: from Vibe Coding to Agentic Engineering2026Tsinghua University./papers/00157-GLM-5.pdf
AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning2025Tsinghua University./papers/00160-AReaL.pdf

Peking University

论文年份论文单位笔记地址
Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations2024Peking University./papers/00040-Math-Shepherd.pdf
ChartMoE: Mixture of Diversely Aligned Expert Connector for Chart Understanding2024Peking University./papers/00049-ChartMoE.pdf

Carnegie Mellon University

论文年份论文单位笔记地址
Optimizing Test-Time Compute via Meta Reinforcement Fine-Tuning2025Carnegie Mellon University./papers/00053-MRT.pdf

University of California, Berkeley

论文年份论文单位笔记地址
Efficient Memory Management for Large Language Model Serving with PagedAttention2023University of California, Berkeley./papers/00086-vllm.pdf
SGLang: Efficient Execution of Structured Language Model Programs2024University of California, Berkeley./papers/00164-SGLang.pdf
Ring Attention with Blockwise Transformers for Near-Infinite Context2023University of California, Berkeley./papers/00087-RingAttention.pdf
Blockwise Parallel Transformer for Large Context Models2023University of California, Berkeley./papers/00088-BPT.pdf
RL Grokking Recipe: How Does RL Unlock and Transfer New Algorithms in LLMs?2025University of California, Berkeley./papers/00115-grokking.pdf
SimpleMem: Efficient Lifelong Memory for LLM Agents2026University of California, Berkeley./papers/00145-SimpleMem.pdf
From Model Scaling to System Scaling: Scaling the Harness in Agentic AI2026University of California, Berkeley./papers/00182-CheetahClaws.pdf

MIT

论文年份论文单位笔记地址
Striped Attention: Faster Ring Attention for Causal Transformers2023MIT./papers/00096-Striped-Attention.pdf

Stanford University

论文年份论文单位笔记地址
In-the-Flow Agentic System Optimization for Effective Planning and Tool Use2025Stanford University./papers/00125-in-the-flow.pdf

Princeton University

论文年份论文单位笔记地址
Skill-Targeted Adaptive Training2025Princeton University./papers/00119-STAT.pdf
OpenClaw-RL: Train Any Agent Simply by Talking2026Princeton University./papers/00171-OpenClaw-RL.pdf

National University of Singapore

论文年份论文单位笔记地址
Understanding R1-Zero-Like Training: A Critical Perspective2025National University of Singapore./papers/00048-understand-r1-zero.pdf

Fudan University

论文年份论文单位笔记地址
EvoSyn: Generalizable Evolutionary Data Synthesis for Verifiable Learning2025Fudan University./papers/00120-EvoSyn.pdf
AgentPRM: Process Reward Models for LLM Agents via Step-Wise Promise and Progress2025Fudan University./papers/00135-AgentPRM.pdf

Shanghai Jiao Tong University

论文年份论文单位笔记地址
LIMO: Less is More for Reasoning2025Shanghai Jiao Tong University./papers/00051-LIMO.pdf
Context Engineering 2.0: The Context of Context Engineering2025Shanghai Jiao Tong University./papers/00131-Context-Engineering-2.0.pdf
Repo0: Design-Driven Zero-to-All Code Generation2026Shanghai Jiao Tong University./papers/00184-Repo0.pdf

Nanjing University

论文年份论文单位笔记地址
A Comprehensive Survey on Long Context Language Modeling2025Nanjing University./papers/00058-LCLM.pdf
DART: Diffusion-Inspired Speculative Decoding for Fast LLM Inference2026Nanjing University./papers/00175-DART.pdf

Renmin University of China

论文年份论文单位笔记地址
Imitate, Explore, and Self-Improve: A Reproduction Report on Slow-thinking Reasoning Systems2024Renmin University of China./papers/00037-o1-like.pdf
Search-o1: Agentic Search-Enhanced Large Reasoning Models2025Renmin University of China./papers/00059-Search-o1.pdf
WebThinker: Empowering Large Reasoning Models with Deep Research Capability2025Renmin University of China./papers/00074-WebThinker.pdf
R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning2025Renmin University of China./papers/00062-R1-Searcher.pdf
From Trial-and-Error to Improvement: A Systematic Analysis of LLM Exploration Mechanisms in RLVR2025Renmin University of China./papers/00085-RLVR.pdf
DeepCritic: Deliberate Critique with Large Language Models2025Renmin University of China./papers/00114-DeepCritic.pdf
ET-Agent: Incentivizing Effective Tool-Integrated Reasoning Agent via Behavior Calibration2026Renmin University of China./papers/00146-ET-Agent.pdf
SmartSearch: Process Reward-Guided Query Refinement for Search Agents2026Renmin University of China./papers/00147-SmartSearch.pdf
EnvScaler: Scaling Tool-Interactive Environments for LLM Agent via Programmatic Synthesis2026Renmin University of China./papers/00149-EnvScaler.pdf
Toward Generalist Autonomous Research via Hypothesis-Tree Refinement2026Renmin University of China./papers/00178-Arbor.pdf

University of Illinois Urbana-Champaign

论文年份论文单位笔记地址
DeepRetrieval: Hacking Real Search Engines and Retrievers with Large Language Models via Reinforcement Learning2025University of Illinois Urbana-Champaign./papers/00060-DeepRetrieval.pdf
Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning2025University of Illinois Urbana-Champaign./papers/00061-Search-R1.pdf
Executable Code Actions Elicit Better LLM Agents2024University of Illinois Urbana-Champaign./papers/00166-CodeAct.pdf
CoRNStack: High-Quality Contrastive Data for Better Code Retrieval and Reranking2024University of Illinois Urbana-Champaign./papers/00170-CoRNStack.pdf

Hong Kong University of Science and Technology

论文年份论文单位笔记地址
Dr. RTL: Autonomous Agentic RTL Optimization through Tool-Grounded Self-Improvement2026Hong Kong University of Science and Technology./papers/00169-Dr.RTL.pdf

Institute of Computing Technology, Chinese Academy of Sciences

论文年份论文单位笔记地址
AssertMiner: Module-Level Spec Generation and Assertion Mining using Static Analysis Guided LLMs2025Institute of Computing Technology, Chinese Academy of Sciences./papers/00173-AssertMiner.pdf
AssertMiner-pro: Enhanced module-level spec generation and assertion mining with LLM guided by top-down hierarchical strategies2026Institute of Computing Technology, Chinese Academy of Sciences./papers/00177-AssertMiner-pro.pdf

Columbia University

论文年份论文单位笔记地址
NoTB: Oracle-Free Triage of LLM-Generated RTL via Cross-Model Formal Consensus2026Columbia University./papers/00183-NoTB.pdf

其他

论文年份论文单位笔记地址
LightRAG: Simple and Fast Retrieval-Augmented Generation2024Beijing University of Posts and Telecommunications./papers/00047-LightRAG.pdf
HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Models2024The Ohio State University./papers/00071-HippoRAG.pdf
From RAG to Memory: Non-Parametric Continual Learning for Large Language Models2025The Ohio State University./papers/00072-HippoRAG2.pdf
Chinese Tiny LLM: Pretraining a Chinese-Centric Large Language Model2024University of Waterloo./papers/00011-Chinese-Tiny-LLM.pdf
OpenR: An Open Source Framework for Advanced Reasoning with Large Language Models2024University College London./papers/00041-OpenR.pdf
Retrieval-Augmented Generation with Graphs (GraphRAG)2025Michigan State University./papers/00052-GraphRAG-review.pdf
RoFormer: Enhanced Transformer with Rotary Position Embedding2021Zhuiyi Technology./papers/00009-RoPE.pdf
Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions2022Allen Institute for AI./papers/00079-IRCoT.pdf
Memory as Action: Autonomous Context Curation for Long-Horizon Agentic Tasks2025Beijing Jiaotong University./papers/00110-MemAct.pdf
Scientific Algorithm Discovery by Augmenting AlphaEvolve with Deep Research2025IBM Research./papers/00112-DeepEvolve.pdf
Liger-Kernel: Efficient Triton Kernels for LLM Training2025LinkedIn./papers/00130-Liger-Kernel.pdf
HyperRAG: Reasoning N-ary Facts over Hypergraphs for Retrieval Augmented Generation2026National Yang Ming Chiao Tung University./papers/00163-HyperRAG.pdf
Dive into Claude Code: The Design Space of Today's and Future AI Agent Systems2026VILA Lab./papers/00180-Dive-into-Claude-Code.pdf
Miles v0.1: Production-Level Post-Training2026Miles Team./papers/00187-Miles.pdf
MechMem-RTL: Reusing Verified Mechanism Memories for LLM-Based RTL Repair2026Hunan University./papers/00190-MechMem-RTL.pdf

书籍

  1. ./books/00001-Claude-Code-Harness-Engineering-Book.pdf

工具

  1. Overleaf

论文集

  1. huggingface daily papers
  2. arxiv

Similar repos

0xPabloxx/llm-paper-notes

My reading notes on LLM/VLM research — post-training, pretraining, agents, multimodal,…

0

hijkzzz/Awesome-LLM-Strawberry

A collection of LLM papers, blogs, and projects, with a focus on OpenAI o1 🍓 and reasoning…

6,908

cycloarcane/Gathered-Paper-Resources

In this repo I will upload aggregated resources I get from my daily reading of academic papers.

14

gyunggyung/AGI-Papers

A curated archive of breakthroughs in Agents, Architecture, Training, RAG, and On-Device AI.

421

itsual/Notable-LLM-Research-Papers

Curated list of research papers published in 2024 related to Large Language Models (LLM)

50

Hannibal046/Awesome-LLM

Awesome-LLM: a curated list of Large Language Model

27,422

benjaminzwhite/reasoning-models

Experiments with reasoning models, training techniques, papers

30

ChenZiHong-Gavin/llm-tech-report

A summary of technical reports for various large language models (LLMs).

39

Contributors

yanfeng98

151 commits

Languages

TeX

88.6%

BibTeX Style

11.3%