附录 C：100+ 篇论文索引与主题分类

下面给出一份按主题粗分类整理的论文索引。它不是严格学科 taxonomy，而是为了方便工程和方法论阅读。

#C.1 Foundation

1. Generative Agents: Interactive Simulacra of Human Behavior
2. A survey on large language model based autonomous agents
3. The Rise and Potential of Large Language Model Based Agents: A Survey
4. Large language models empowered agent-based modeling and simulation: a survey and perspectives
5. Agents: An Open-source Framework for Autonomous Language Agents
6. Large Language Models as Simulated Economic Agents: What Can We Learn from Homo Silicus?
7. Voyager: An Open-Ended Embodied Agent with Large Language Models
8. ChatEDA: A Large Language Model Powered Autonomous Agent for EDA
9. WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents
10. Towards Autonomous Testing Agents via Conversational Large Language Models
11. Generative Agent Simulations of 1,000 People
12. Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Security
13. AI Agents vs. Agentic AI: A Conceptual Taxonomy, Applications and Challenges
14. From language to action: a review of large language models as autonomous agents and tool users

#C.2 Tool Use

15. Toolformer: Language Models Can Teach Themselves to Use Tools
16. HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face
17. StructGPT: A General Framework for Large Language Model to Reason over Structured Data
18. ChemCrow: Augmenting large-language models with chemistry tools
19. GeneGPT: augmenting large language models with domain tools for improved access to biomedical information
20. GPT4Tools: Teaching Large Language Model to Use Tools via Self-instruction
21. ART: Automatic multi-step reasoning and tool-use for large language models
22. PrivacyAsst: Safeguarding User Privacy in Tool-Using Large Language Model Agents
23. RCAgent: Cloud Root Cause Analysis by Autonomous Agents with Tool-Augmented Large Language Models
24. Biomni: A General-Purpose Biomedical AI Agent
25. Large language model agents can use tools to perform clinical calculations
26. ReAcTable: Enhancing ReAct for Table Question Answering
27. Exploring LLM-Based Agents for Root Cause Analysis

#C.3 Planning

28. ReAct: Synergizing Reasoning and Acting in Language Models
29. Inner Monologue: Embodied Reasoning through Planning with Language Models
30. LLM-Planner: Few-Shot Grounded Planning for Embodied Agents with Large Language Models
31. LLM+P: Empowering Large Language Models with Optimal Planning Proficiency
32. Reasoning with Language Model is Planning with World Model
33. NavGPT: Explicit Reasoning in Vision-and-Language Navigation with Large Language Models
34. SMART-LLM: Smart Multi-Agent Robot Task Planning using Large Language Models
35. Budget-Constrained Agentic Large Language Models: Intention-Based Planning for Costly Tool Use
36. Enhancing AI Systems with Agentic Workflows Patterns in Large Language Model
37. Understanding the planning of LLM agents: A survey

#C.4 Memory

38. Reflexion: Language Agents with Verbal Reinforcement Learning
39. FinMem: A Performance-Enhanced LLM Trading Agent with Layered Memory and Character Design
40. Cognitive Architectures for Language Agents
41. A Survey on the Memory Mechanism of Large Language Model-based Agents
42. Adaptive Memory Admission Control for LLM Agents
43. Lifelong Learning of Large Language Model based Agents: A Roadmap
44. Self-Reflection in Large Language Model Agents: Effects on Problem-Solving Performance
45. AI and memory
46. SayNav: Grounding Large Language Models for Dynamic Planning to Navigation in New Environments
47. On Generative Agents in Recommendation

#C.5 Multi-Agent

48. AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation
49. CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society
50. MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework
51. SciAgents: Automating Scientific Discovery Through Bioinspired Multi-Agent Intelligent Graph Reasoning
52. ProtAgents: protein discovery via large language model multi-agent collaborations combining physics and machine learning
53. ReConcile: Round-Table Conference Improves Reasoning via Consensus among Diverse LLMs
54. Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate
55. Theory of Mind for Multi-Agent Collaboration via Large Language Models
56. Large Language Model based Multi-Agents: A Survey of Progress and Challenges
57. Rethinking the Value of Multi-Agent Workflow: A Strong Single Agent Baseline

#C.6 Evaluation and Safety

58. AgentBench: Evaluating LLMs as Agents
59. AgentBoard: An Analytical Evaluation Board of Multi-turn LLM Agents
60. WebArena: A Realistic Web Environment for Building Autonomous Agents
61. OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
62. SWE-bench: Can Language Models Resolve Real-World GitHub Issues?
63. InjecAgent: Benchmarking Indirect Prompt Injections in Tool-Integrated Large Language Model Agents
64. Prompt Injection Attacks in Large Language Models and AI Agent Systems: A Comprehensive Review of Vulnerabilities, Attack Vectors, and Defense Mechanisms
65. CodeAgent: Enhancing Code Generation with Tool-Integrated Agent Systems for Real-World Repo-level Coding Challenges
66. Plug in the Safety Chip: Enforcing Constraints for LLM-driven Robot Agents
67. Evaluating large language models as agents in the clinic

#C.7 Domain Agents

68. Autonomous chemical research with large language models
69. Augmenting large language models with chemistry tools
70. Evaluating large language model workflows in clinical decision support for triage and referral and diagnosis
71. An autonomous agentic workflow for clinical detection of cognitive concerns using large language models
72. Language agents achieve superhuman synthesis of scientific knowledge
73. Empowering biomedical discovery with AI agents
74. Agent Hospital: A Simulacrum of Hospital with Evolvable Medical Agents
75. Development and validation of an autonomous artificial intelligence agent for clinical decision-making in oncology
76. GeneAgent: self-verification language agent for gene-set analysis using domain databases
77. EconAgent: Large Language Model-Empowered Agents for Simulating Macroeconomic Activities

#C.8 Extended Corpus

以下保留其余扩展论文索引，作为这本书方法论形成的语料背景：

78. A review of large language models and autonomous agents in chemistry
79. Large Language Model Enhanced Multi-Agent Systems for 6G Communications
80. Augmenting large language models with chemistry tools
81. PaperQA: Retrieval-Augmented Generative Agent for Scientific Research
82. AutoTQA: Towards Autonomous Tabular Question Answering through Multi-Agent Large Language Models
83. A feasibility study of automating radiotherapy planning with large language model agents
84. Igniting Language Intelligence: The Hitchhiker’s Guide from Chain-of-Thought Reasoning to Language Agents
85. MotionLM: Multi-Agent Motion Forecasting as Language Modeling
86. Language Models as Agent Models
87. When Large Language Model Agents Meet 6G Networks: Perception, Grounding, and Alignment
88. Generation of Asset Administration Shell With Large Language Model Agents: Toward Semantic Interoperability in Digital Twins in the Context of Industry 4.0
89. Unleashing the Emergent Cognitive Synergy in Large Language Models: A Task-Solving Agent through Multi-Persona Self-Collaboration
90. Exploring Large Language Model based Intelligent Agents: Definitions, Methods, and Prospects
91. Use of artificial intelligence large language models as a clinical tool in rehabilitation medicine: a comparative test case
92. Use of large language models as artificial intelligence tools in academic research and publishing among global clinical researchers
93. Towards autonomous system: flexible modular production system enhanced with large language model agents
94. Chatlaw: A Multi-Agent Collaborative Legal Assistant with Knowledge Graph Enhanced Mixture-of-Experts Large Language Model
95. Receive, Reason, and React: Drive as You Say, With Large Language Models in Autonomous Vehicles
96. ChatScene: Knowledge-Enabled Safety-Critical Scenario Generation for Autonomous Vehicles
97. Integrating Belief-Desire-Intention agents with large language models for reliable human-robot interaction and explainable Artificial Intelligence
98. ProsocialDialog: A Prosocial Backbone for Conversational Agents
99. Generative agent-based modeling: an introduction and tutorial
100. Large language model based autonomous agents: workflow, infrastructure, and challenges
101. Emergent autonomous scientific research capabilities of large language models
102. MM-REACT: Prompting ChatGPT for Multimodal Reasoning and Action
103. SwiftSage: A Generative Agent with Fast and Slow Thinking for Complex Interactive Tasks
104. RTLFixer: Automatically Fixing RTL Syntax Errors with Large Language Model
105. Large language model based intelligent agents in engineering and science applications