LLM-Agents-Papers

:writing_hand: 描述

最后更新时间：2025/7/12

这是一个整理了与基于 LLM 的 Agent（智能体）相关论文的仓库。涵盖范围包括：

• 综述 (Survey)
• 增强技术 (Technique For Enhancement)
  • 规划 (Planning)
  • 记忆机制 (Memory Mechanism)
  • 反馈与反思 (Feedback & Reflection)
  • RAG
  • 搜索 (Search)
• 交互 (Interaction)
  • 角色扮演 (Role Playing)
  • 对话 (Conversation)
  • 游戏博弈 (Game Playing)
  • 人机交互 (Human-Agent Interaction)
  • 工具使用 (Tool Usage)
  • 模拟 (Simulation)
• 应用 (Application)
  • 数学 (Math)
  • 化学 (Chemistry)
  • 生物学 (Biology)
  • 物理学 (Physics)
  • 地理学 (Geography)
  • 艺术 (Art)
  • 医学 (Medicine)
  • 金融 (Finance)
  • 软件工程 (Software Engineering)
  • 研究 (Research)
• 自动化 (Automation)
  • 工作流 (Workflow)
  • 自动化评估 (Automatic Evaluation)
• 训练 (Training)
  • 微调 (Fine tuning)
  • 强化学习 (RL)
  • DPO
• 扩展 (Scaling)
  • 单智能体框架 (Single-Agent Framework)
  • 多智能体系统 (Multi-Agent System)
• 稳定性 (Stability)
  • 安全性 (Safety)
  • 偏差 (Bias)
  • 幻觉 (Hallucination)
• 基础设施 (Infrastructure)
  • 基准与评估 (Benchmark & Evaluation)
  • 环境与平台 (Environment & Platform)
  • 数据集 (Dataset)
• 其他 (Others)

:yellow_heart: 推荐

为了获得更全面的阅读体验，我们也推荐以下论文列表：

• zjunlp/LLMAgentPapers: 大语言模型智能体必读论文。
• teacherpeterpan/self-correction-llm-papers: 关于大语言模型自动反馈自校正的研究论文合集。
• Paitesanshi/LLM-Agent-Survey: 基于 LLM 的自主智能体综述。
• woooodyy/llm-agent-paper-list: 基于 LLM 的智能体必读论文。
• git-disl/awesome-LLM-game-agent-papers: 基于 LLM 的游戏智能体必读论文。

:newspaper: 论文

综述

• [2025/06/10] Measuring Data Science Automation: A Survey of Evaluation Tools for AI Assistants and Agents | [paper] | [code]

• [2025/06/06] Evolutionary Perspectives on the Evaluation of LLM-Based AI Agents: A Comprehensive Survey | [paper] | [code]

• [2025/05/27] Creativity in LLM-based Multi-Agent Systems: A Survey | [paper] | [code]

• [2025/05/24] Multi-Party Conversational Agents: A Survey | [paper] | [code]

• [2025/05/16] A Survey on the Safety and Security Threats of Computer-Using Agents: JARVIS or Ultron? | [paper] | [code]

• [2025/05/02] AI agents may be worth the hype but not the resources (yet): An initial exploration of machine translation quality and costs in three language pairs in the legal and news domains | [paper] | [code]

• [2025/05/01] A Survey on Large Language Model based Human-Agent Systems | [paper] | [code]

• [2025/04/30] Humanizing LLMs: A Survey of Psychological Measurements with Tools, Datasets, and Human-Agent Applications | [paper] | [code]

• [2025/04/22] A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment | [paper] | [code]

• [2025/04/20] Meta-Thinking in LLMs via Multi-Agent Reinforcement Learning: A Survey | [paper] | [code]

• [2025/04/14] A Survey of Large Language Model-Powered Spatial Intelligence Across Scales: Advances in Embodied Agents, Smart Cities, and Earth Science | [paper] | [code]

• [2025/04/12] A Survey of Frontiers in LLM Reasoning: Inference Scaling, Learning to Reason, and Agentic Systems | [paper] | [code]

• [2025/03/28] Evaluating LLM-based Agents for Multi-Turn Conversations: A Survey | [paper] | [code]

• [2025/03/27] Large Language Model Agent: A Survey on Methodology, Applications and Challenges | [paper] | [code]

• [2025/03/27] A Survey on (M)LLM-Based GUI Agents | [paper] | [code]

• [2025/03/24] A Survey of Large Language Model Agents for Question Answering | [paper] | [code]