论文就是你所需要的。
「编号」是原文归档编号:来源非 arXiv 的论文,其 PDF 归档在本仓库
papers/;其余论文的原文 PDF 在归档仓库 paper-is-all-you-need。非论文条目(如博客导读、系统)同样占用编号列,但它们没有可归档的 PDF,编号单元格直接指向原文在线地址(例:00192 指向 Awesome RSI 站点的博客页,00215 指向 GitHub 仓库);上游归档里还没有的 arXiv 论文也暂指 arXiv 官方页,归档到上游后再改指 PDF。「笔记地址」指向notes/下由 read-paper-blog skill 生成的笔记。
| 编号 | 论文 | 年份 | 论文单位 | 笔记地址 |
|---|---|---|---|---|
| 00001 | Scaling Laws for Neural Language Models | 2020 | OpenAI | —(待生成笔记) |
| 00028 | Let's Verify Step by Step | 2023 | OpenAI | —(待生成笔记) |
| 00035 | Efficient Training of Language Models to Fill in the Middle | 2022 | OpenAI | —(待生成笔记) |
| 编号 | 论文 | 年份 | 论文单位 | 笔记地址 |
|---|---|---|---|---|
| 00083 | Kimi K2: Open Agentic Intelligence | 2025 | KimiTeam | —(待生成笔记) |
| 00132 | Kimi Linear: An Expressive, Efficient Attention Architecture | 2025 | KimiTeam | —(待生成笔记) |
| 00156 | Kimi K2.5: Visual Agentic Intelligence | 2026 | KimiTeam | 笔记 |
| 编号 | 论文 | 年份 | 论文单位 | 笔记地址 |
|---|---|---|---|---|
| 00008 | Chain-of-Thought Prompting Elicits Reasoning in Large Language Models | 2022 | —(待生成笔记) | |
| 00076 | Distilling the Knowledge in a Neural Network | 2015 | —(待生成笔记) | |
| 00077 | STaR: Bootstrapping Reasoning With Reasoning | 2022 | —(待生成笔记) | |
| 00078 | ReAct: Synergizing Reasoning and Acting in Language Models | 2022 | —(待生成笔记) | |
| 00080 | Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities | 2025 | —(待生成笔记) | |
| 00081 | Gemma 3 Technical Report | 2025 | —(待生成笔记) | |
| 00214 | Dream-RSI: Recursive Self-Improvement through Evolving Worlds | 2026 | 笔记 | |
| 00212 | RRSI: Regularized Recursive Self-Improvement of Agent Harnesses | 2026 | Google Cloud AI Research | 笔记 |
| 编号 | 论文 | 年份 | 论文单位 | 笔记地址 |
|---|---|---|---|---|
| 00006 | The Llama 3 Herd of Models | 2024 | Meta | —(待生成笔记) |
| 00084 | Deep Think with Confidence | 2025 | Meta | —(待生成笔记) |
| 00090 | REFRAG: Rethinking RAG based Decoding | 2025 | Meta | —(待生成笔记) |
| 00121 | The Art of Scaling Reinforcement Learning Compute for LLMs | 2025 | Meta | —(待生成笔记) |
| 00155 | Dr. Zero: Self-Evolving Search Agents without Training Data | 2026 | Meta | —(待生成笔记) |
| 编号 | 论文 | 年份 | 论文单位 | 笔记地址 |
|---|---|---|---|---|
| 00036 | Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters | 2024 | DeepMind | —(待生成笔记) |
| 00039 | Improve Mathematical Reasoning in Language Models by Automated Process Supervision | 2024 | DeepMind | —(待生成笔记) |
| 00126 | Extracting alignment data in open models | 2025 | DeepMind | —(待生成笔记) |
| 00139 | Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory | 2025 | DeepMind | —(待生成笔记) |
| 编号 | 论文 | 年份 | 论文单位 | 笔记地址 |
|---|---|---|---|---|
| 00012 | Reducing Activation Recomputation in Large Transformer Models | 2022 | NVIDIA | —(待生成笔记) |
| 00140 | ToolOrchestra: Elevating Intelligence via Efficient Model and Tool Orchestration | 2025 | NVIDIA | —(待生成笔记) |
| 00144 | GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization | 2026 | NVIDIA | —(待生成笔记) |
| 00158 | ACE-RTL: When Agentic Context Evolution Meets RTL-Specialized LLMs | 2026 | NVIDIA | —(待生成笔记) |
| 00168 | Autonomous Evolution of EDA Tools: Multi-Agent Self-Evolved ABC | 2026 | NVIDIA | —(待生成笔记) |
| 编号 | 论文 | 年份 | 论文单位 | 笔记地址 |
|---|---|---|---|---|
| 00054 | HybridFlow: A Flexible and Efficient RLHF Framework | 2024 | ByteDance | —(待生成笔记) |
| 00055 | DAPO: An Open-Source LLM Reinforcement Learning System at Scale | 2025 | ByteDance | —(待生成笔记) |
| 00067 | VAPO: Efficient and Reliable Reinforcement Learning for Advanced Reasoning Tasks | 2025 | ByteDance | —(待生成笔记) |
| 00068 | Seed1.5-Thinking: Advancing Superb Reasoning Models with Reinforcement Learning | 2025 | ByteDance | —(待生成笔记) |
| 00070 | Seed-Coder: Let the Code Model Curate Data for Itself | 2025 | ByteDance | —(待生成笔记) |
| 00091 | Seeing, Listening, Remembering, and Reasoning: A Multimodal Agent with Long-Term Memory | 2025 | ByteDance | —(待生成笔记) |
| 00109 | MemAgent: Reshaping Long-Context LLM with Multi-Conv RL-based Memory Agent | 2025 | ByteDance | —(待生成笔记) |
| 00122 | Scaling Latent Reasoning via Looped Language Models | 2025 | ByteDance | —(待生成笔记) |
| 00128 | Scaling Long-Horizon LLM Agent via Context-Folding | 2025 | ByteDance | —(待生成笔记) |
| 00189 | HarnessDev: Can LLMs Create and Evolve Their Own Agent Harness? | 2026 | ByteDance | 笔记 |
| 编号 | 论文 | 年份 | 论文单位 | 笔记地址 |
|---|---|---|---|---|
| 00108 | Training-Free Group Relative Policy Optimization | 2025 | Tencent | —(待生成笔记) |
| 00152 | HY-MT1.5 Technical Report | 2025 | Tencent | —(待生成笔记) |
| 编号 | 论文 | 年份 | 论文单位 | 笔记地址 |
|---|---|---|---|---|
| 00162 | ThinkOmni: Lifting Textual Reasoning to Omni-modal Scenarios via Guidance Decoding | 2026 | Xiaomi | —(待生成笔记) |
| 00204 | TRACE: A Self-Evolving Skill Bank for Consistent, Limit-Aware LLM Agents | 2026 | Xiaomi | —(待生成笔记) |
| 00213 | HarnessPAI: An Evolving Harness for Physical AI | 2026 | Xiaomi | —(待生成笔记) |
| 编号 | 论文 | 年份 | 论文单位 | 笔记地址 |
|---|---|---|---|---|
| 00118 | Chain-of-Agents: End-to-End Agent Foundation Models via Multi-Agent Distillation and Agentic RL | 2025 | OPPO AI Agent Team | —(待生成笔记) |
| 00154 | O-Researcher: An Open Ended Deep Research Model via Multi-Agent Distillation and Agentic RL | 2026 | OPPO AI Agent Team | —(待生成笔记) |
| 编号 | 论文 | 年份 | 论文单位 | 笔记地址 |
|---|---|---|---|---|
| 00093 | LongCat-Flash Technical Report | 2025 | Meituan LongCat Team | —(待生成笔记) |
| 编号 | 论文 | 年份 | 论文单位 | 笔记地址 |
|---|---|---|---|---|
| 00117 | LongMagpie: A Self-synthesis Method for Generating Large-scale Long-context Instructions | 2025 | Xiaohongshu | —(待生成笔记) |
| 00123 | DeepAgent: A General Reasoning Agent with Scalable Toolsets | 2025 | Xiaohongshu | —(待生成笔记) |
| 00141 | PretrainZero: Reinforcement Active Pretraining | 2025 | Xiaohongshu | —(待生成笔记) |
| 编号 | 论文 | 年份 | 论文单位 | 笔记地址 |
|---|---|---|---|---|
| 00176 | Unlimited OCR Works | 2026 | Baidu | —(待生成笔记) |
| 00181 | PaddleOCR-VL-1.6: Expanding the Frontier of Document Parsing with Under-Optimized Region Refinement and Progressive Post-Training | 2026 | Baidu | —(待生成笔记) |
| 编号 | 论文 | 年份 | 论文单位 | 笔记地址 |
|---|---|---|---|---|
| 00142 | FlowSearch: Advancing deep research with dynamic structured knowledge flow | 2025 | Shanghai Artificial Intelligence Laboratory | —(待生成笔记) |
| 00188 | Harness-of-Harness: Multi-Day Autonomous Software Development with Continual Improvement | 2026 | Shanghai Artificial Intelligence Laboratory | —(待生成笔记) |
| 00198 | Self-Harness: Harnesses That Improve Themselves | 2026 | Shanghai Artificial Intelligence Laboratory | —(待生成笔记) |
| 编号 | 论文 | 年份 | 论文单位 | 笔记地址 |
|---|---|---|---|---|
| 00089 | Memento: Fine-tuning LLM Agents without Fine-tuning LLMs | 2025 | Huawei Noah’s Ark Lab | —(待生成笔记) |
| 编号 | 论文 | 年份 | 论文单位 | 笔记地址 |
|---|---|---|---|---|
| 00003 | MiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategies | 2024 | Tsinghua University | —(待生成笔记) |
| 00005 | ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools | 2024 | Tsinghua University | —(待生成笔记) |
| 00038 | LongWriter: Unleashing 10,000+ Word Generation from Long Context LLMs | 2024 | Tsinghua University | —(待生成笔记) |
| 00043 | ReST-MCTS*: LLM Self-Training via Process Reward Guided Tree Search | 2024 | Tsinghua University | —(待生成笔记) |
| 00113 | GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models | 2025 | Tsinghua University | —(待生成笔记) |
| 00157 | GLM-5: from Vibe Coding to Agentic Engineering | 2026 | Tsinghua University | —(待生成笔记) |
| 00160 | AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning | 2025 | Tsinghua University | —(待生成笔记) |
| 编号 | 论文 | 年份 | 论文单位 | 笔记地址 |
|---|---|---|---|---|
| 00040 | Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations | 2024 | Peking University | —(待生成笔记) |
| 00049 | ChartMoE: Mixture of Diversely Aligned Expert Connector for Chart Understanding | 2024 | Peking University | —(待生成笔记) |
| 编号 | 论文 | 年份 | 论文单位 | 笔记地址 |
|---|---|---|---|---|
| 00086 | Efficient Memory Management for Large Language Model Serving with PagedAttention | 2023 | University of California, Berkeley | —(待生成笔记) |
| 00164 | SGLang: Efficient Execution of Structured Language Model Programs | 2024 | University of California, Berkeley | —(待生成笔记) |
| 00087 | Ring Attention with Blockwise Transformers for Near-Infinite Context | 2023 | University of California, Berkeley | —(待生成笔记) |
| 00088 | Blockwise Parallel Transformer for Large Context Models | 2023 | University of California, Berkeley | —(待生成笔记) |
| 00115 | RL Grokking Recipe: How Does RL Unlock and Transfer New Algorithms in LLMs? | 2025 | University of California, Berkeley | —(待生成笔记) |
| 00145 | SimpleMem: Efficient Lifelong Memory for LLM Agents | 2026 | University of California, Berkeley | —(待生成笔记) |
| 00182 | From Model Scaling to System Scaling: Scaling the Harness in Agentic AI | 2026 | University of California, Berkeley | —(待生成笔记) |
| 编号 | 论文 | 年份 | 论文单位 | 笔记地址 |
|---|---|---|---|---|
| 00119 | Skill-Targeted Adaptive Training | 2025 | Princeton University | —(待生成笔记) |
| 00171 | OpenClaw-RL: Train Any Agent Simply by Talking | 2026 | Princeton University | —(待生成笔记) |
| 00205 | Prime Agent: A Self-Improving RLM Harness | 2026 | Princeton University | 笔记 |
| 编号 | 论文 | 年份 | 论文单位 | 笔记地址 |
|---|---|---|---|---|
| 00048 | Understanding R1-Zero-Like Training: A Critical Perspective | 2025 | National University of Singapore | —(待生成笔记) |
| 00206 | Recursive Experiential-Working Memory Evolution for Long-Horizon Agent Harnesses | 2026 | National University of Singapore | —(待生成笔记) |
| 编号 | 论文 | 年份 | 论文单位 | 笔记地址 |
|---|---|---|---|---|
| 00120 | EvoSyn: Generalizable Evolutionary Data Synthesis for Verifiable Learning | 2025 | Fudan University | —(待生成笔记) |
| 00135 | AgentPRM: Process Reward Models for LLM Agents via Step-Wise Promise and Progress | 2025 | Fudan University | —(待生成笔记) |
| 编号 | 论文 | 年份 | 论文单位 | 笔记地址 |
|---|---|---|---|---|
| 00051 | LIMO: Less is More for Reasoning | 2025 | Shanghai Jiao Tong University | —(待生成笔记) |
| 00131 | Context Engineering 2.0: The Context of Context Engineering | 2025 | Shanghai Jiao Tong University | —(待生成笔记) |
| 00184 | Repo0: Design-Driven Zero-to-All Code Generation | 2026 | Shanghai Jiao Tong University | —(待生成笔记) |
| 编号 | 论文 | 年份 | 论文单位 | 笔记地址 |
|---|---|---|---|---|
| 00058 | A Comprehensive Survey on Long Context Language Modeling | 2025 | Nanjing University | —(待生成笔记) |
| 00175 | DART: Diffusion-Inspired Speculative Decoding for Fast LLM Inference | 2026 | Nanjing University | —(待生成笔记) |
| 编号 | 论文 | 年份 | 论文单位 | 笔记地址 |
|---|---|---|---|---|
| 00060 | DeepRetrieval: Hacking Real Search Engines and Retrievers with Large Language Models via Reinforcement Learning | 2025 | University of Illinois Urbana-Champaign | —(待生成笔记) |
| 00061 | Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning | 2025 | University of Illinois Urbana-Champaign | —(待生成笔记) |
| 00166 | Executable Code Actions Elicit Better LLM Agents | 2024 | University of Illinois Urbana-Champaign | —(待生成笔记) |
| 00170 | CoRNStack: High-Quality Contrastive Data for Better Code Retrieval and Reranking | 2024 | University of Illinois Urbana-Champaign | —(待生成笔记) |
| 00202 | Evo-Harness: Context-to-Harness Skill Compilation for Self-Evolving Agents | 2026 | University of Illinois Urbana-Champaign | —(待生成笔记) |
| 编号 | 论文 | 年份 | 论文单位 | 笔记地址 |
|---|---|---|---|---|
| 00169 | Dr. RTL: Autonomous Agentic RTL Optimization through Tool-Grounded Self-Improvement | 2026 | Hong Kong University of Science and Technology | —(待生成笔记) |
| 00196 | SkillRevise: Improving LLM-Authored Agent Skills via Trace-Conditioned Skill Revision | 2026 | Hong Kong University of Science and Technology | —(待生成笔记) |
| 00194 | HeLa-Mem: Hebbian Learning and Associative Memory for LLM Agents | 2026 | Hong Kong University of Science and Technology (Guangzhou) | —(待生成笔记) |
| 编号 | 论文 | 年份 | 论文单位 | 笔记地址 |
|---|---|---|---|---|
| 00173 | AssertMiner: Module-Level Spec Generation and Assertion Mining using Static Analysis Guided LLMs | 2025 | Institute of Computing Technology, Chinese Academy of Sciences | —(待生成笔记) |
| 00177 | AssertMiner-pro: Enhanced module-level spec generation and assertion mining with LLM guided by top-down hierarchical strategies | 2026 | Institute of Computing Technology, Chinese Academy of Sciences | —(待生成笔记) |
| 编号 | 论文 | 年份 | 论文单位 | 笔记地址 |
|---|---|---|---|---|
| 00203 | ForeDreamer: A Self-Evolving Dual-Agent Memory Architecture for Future Event Prediction | 2026 | Zhejiang University | —(待生成笔记) |
| 00211 | Reflect, Revise, Reuse: Training-Free Skill Evolution for GUI Agents | 2026 | Zhejiang University | —(待生成笔记) |