Shunyu Yao Paper Map

Identity Guard

• ysymyth papers cluster around language agents, tool use, software-engineering agents, and agent benchmarks.
• alfredyao papers cluster around quantum physics, non-Hermitian topology, quantum chaos/gravity, and physics-to-AI transition.

Papers, Theses, Talks, And Scholarly Pointers

• CV - alfredyao, Physics-to-AI research transition
• LAMIC: Layout-Aware Multi-Image Composition via Scalability of Multimodal Diffusion Transformer - alfredyao, Reinforcement learning and reasoning
• Notes on solvable models of many-body quantum chaos - alfredyao, Quantum chaos / quantum gravity
• Physics3D: Learning Physical Properties of 3D Gaussians via Video Diffusion - alfredyao, Reinforcement learning and reasoning
• Quantum Energy Teleportation versus Information Teleportation - alfredyao, Quantum chaos / quantum gravity
• Shunyu Yao CV - alfredyao, Reinforcement learning and reasoning
• [[sources/shunyu-yao/ysymyth/paper-bench-a-benchmark-for-tool-agent-user-interaction-in-real-world-domains-b95f346da4|$\tau$-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains]] - ysymyth, Language agents / agent architectures
• Can Language Models Solve Olympiad Programming? - ysymyth, Evaluation / benchmark design
• CL-bench Life: Can Language Models Learn from Real-Life Context? - ysymyth, Evaluation / benchmark design
• CL-bench: A Benchmark for Context Learning - ysymyth, Evaluation / benchmark design
• Cognitive Architectures for Language Agents - ysymyth, Language agents / agent architectures
• Computer-Using Agent system card - ysymyth, Language agents / agent architectures
• Contextual Experience Replay for Self-Improvement of Language Agents - ysymyth, Language agents / agent architectures
• Controllable Text Generation for Large Language Models: A Survey - ysymyth, Tool use / computer use / digital automation
• HY-Embodied-0.5: Embodied Foundation Models for Real-World Agents - ysymyth, Language agents / agent architectures
• InterCode: Standardizing and Benchmarking Interactive Coding with Execution Feedback - ysymyth, Software engineering agents and benchmarks
• Multi-objective Evolution of Heuristic Using Large Language Model - ysymyth, Software engineering agents and benchmarks
• On Formulating and Evaluating Language Agents - ysymyth, Language agents / agent architectures
• OS-Copilot: Towards Generalist Computer Agents with Self-Improvement - ysymyth, Language agents / agent architectures
• paper Dissertation finalized - ysymyth, Language agents / agent architectures
• paper fpo - ysymyth, Language agents / agent architectures
• Prompting Large Language Models to Tackle the Full Software Development Lifecycle: A Case Study - ysymyth, Software engineering agents and benchmarks
• Provable Limitations of Acquiring Meaning from Ungrounded Form: What Will Future Language Models Understand? - ysymyth, Reinforcement learning and reasoning
• ReAct: Synergizing Reasoning and Acting in Language Models - ysymyth, Language agents / agent architectures
• Reflexion: Language Agents with Verbal Reinforcement Learning - ysymyth, Language agents / agent architectures
• Re-thinking Reinforcement Learning in the Era of Large Language Models - ysymyth, Reinforcement learning and reasoning
• SEAL: Self-Evolving Agentic Learning for Conversational Question Answering over Knowledge Graphs - ysymyth, Software engineering agents and benchmarks
• SWE-agent paper - ysymyth, Software engineering agents and benchmarks
• SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering - ysymyth, Software engineering agents and benchmarks
• SWE-bench: Can Language Models Resolve Real-World GitHub Issues? - ysymyth, Software engineering agents and benchmarks
• talk watch - ysymyth, Language agents / agent architectures
• Tree of Thoughts: Deliberate Problem Solving with Large Language Models - ysymyth, Language agents / agent architectures
• WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents - ysymyth, Language agents / agent architectures
• When a language model is optimized for reasoning, does it still show embers of autoregression? An analysis of OpenAI o1 - ysymyth, Reinforcement learning and reasoning
• 从语言模型到语言智能体 - ysymyth, Language agents / agent architectures

Categories

• Evaluation / benchmark design: 3
• Language agents / agent architectures: 15
• Physics-to-AI research transition: 1
• Quantum chaos / quantum gravity: 2
• Reinforcement learning and reasoning: 6
• Software engineering agents and benchmarks: 7
• Tool use / computer use / digital automation: 1

Related

• yao-shunyu-ysymyth
• yao-shunyu-alfred
• shunyu-yao-public-corpora
• shunyu-yao-project-taxonomy

Counterpoints And Gaps

• Some homepage PDF links use generic labels; arXiv metadata is used when available to strengthen titles.
• Non-arXiv PDFs are indexed by URL and summary policy rather than mirrored as full public text.