AI 智能体论文趋势 2023–2026

工具调用、多步决策与自主 LLM/VLM 智能体系统

统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 3,266 篇被归入该主题的论文。

主要结论

每年论文数

各会议论文数

按年份和会议统计

AI 智能体论文数，按年份和会议
年份NeurIPSICLRICMLCVPR合计
202376404113170
2024150738818329
202536220417840784
20267295006401141,983

代表论文

按年份和会议均匀挑选，方便快速看到每一届的样貌

全部AI 智能体论文

年份全部2023202420252026
会议全部NeurIPSICLRICMLCVPR

共 3,266 篇，第 57 / 66 页

  1. ICLR 2024Designing Skill-Compatible AI: Methodologies and Frameworks in Chess
  2. ICLR 2024DSPy: Compiling Declarative Language Model Calls into State-of-the-Art Pipelines
  3. ICLR 2024Efficient Episodic Memory Utilization of Cooperative Multi-Agent Reinforcement Learning
  4. ICLR 2024Efficient Multi-agent Reinforcement Learning by Planning
  5. ICLR 2024Enhancing Human-AI Collaboration Through Logic-Guided Reasoning
  6. ICLR 2024Evaluating Language Model Agency Through Negotiations
  7. ICLR 2024Expected flow networks in stochastic environments and two-player zero-sum games
  8. ICLR 2024GROOT: Learning to Follow Instructions by Watching Gameplay Videos
  9. ICLR 2024Identifying the Risks of LM Agents with an LM-Emulated Sandbox
  10. ICLR 2024L2MAC: Large Language Model Automatic Computer for Extensive Code Generation
  11. ICLR 2024Large Language Models as Tool Makers
  12. ICLR 2024Learning Decentralized Partially Observable Mean Field Control for Artificial Collective Behavior
  13. ICLR 2024Learning Mean Field Games on Sparse Graphs: A Hybrid Graphex Approach
  14. ICLR 2024Learning Multi-Agent Communication from Graph Modeling Perspective
  15. ICLR 2024Learning Multi-Agent Communication with Contrastive Learning
  16. ICLR 2024Learning Nash Equilibria in Rank-1 Games
  17. ICLR 2024Learning Optimal Contracts: How to Exploit Small Action Spaces
  18. ICLR 2024Learning to Jointly Understand Visual and Tactile Signals
  19. ICLR 2024Lemur: Harmonizing Natural Language and Code for Language Agents
  20. ICLR 2024Let Models Speak Ciphers: Multiagent Debate through Embeddings
  21. ICLR 2024LOQA: Learning with Opponent Q-Learning Awareness
  22. ICLR 2024LoTa-Bench: Benchmarking Language-oriented Task Planners for Embodied Agents
  23. ICLR 2024Maximum Entropy Heterogeneous-Agent Reinforcement Learning
  24. ICLR 2024MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework
  25. ICLR 2024MetaTool Benchmark for Large Language Models: Deciding Whether to Use Tools and Which to Use
  26. ICLR 2024Modeling Boundedly Rational Agents with Latent Inference Budgets
  27. ICLR 2024Neural Neighborhood Search for Multi-agent Path Finding
  28. ICLR 2024On the Hardness of Constrained Cooperative Multi-Agent Reinforcement Learning
  29. ICLR 2024Online Continual Learning for Interactive Instruction Following Agents
  30. ICLR 2024PB-LLM: Partially Binarized Large Language Models
  31. ICLR 2024Provable Memory Efficient Self-Play Algorithm for Model-free Reinforcement Learning
  32. ICLR 2024Rethinking Adversarial Policies: A Generalized Attack Formulation and Provable Defense in RL
  33. ICLR 2024Retroformer: Retrospective Large Language Agents with Policy Gradient Optimization
  34. ICLR 2024REValueD: Regularised Ensemble Value-Decomposition for Factorisable Markov Decision Processes
  35. ICLR 2024Reward Design for Justifiable Sequential Decision-Making
  36. ICLR 2024Sample-Efficient Multi-Agent RL: An Optimization Perspective
  37. ICLR 2024Select to Perfect: Imitating desired behavior from large multi-agent data
  38. ICLR 2024SKILL-MIX: a Flexible and Expandable Family of Evaluations for AI Models
  39. ICLR 2024SmartPlay : A Benchmark for LLMs as Intelligent Agents
  40. ICLR 2024SocioDojo: Building Lifelong Analytical Agents with Real-world Text and Time Series
  41. ICLR 2024Solving Homogeneous and Heterogeneous Cooperative Tasks with Greedy Sequential Execution
  42. ICLR 2024SOTOPIA: Interactive Evaluation for Social Intelligence in Language Agents
  43. ICLR 2024Steve-Eye: Equipping LLM-based Embodied Agents with Visual Perception in Open Worlds
  44. ICLR 2024Synapse: Trajectory-as-Exemplar Prompting with Memory for Computer Control
  45. ICLR 2024The LLM Surgeon
  46. ICLR 2024Think-on-Graph: Deep and Responsible Reasoning of Large Language Model on Knowledge Graph
  47. ICLR 2024THOUGHT PROPAGATION: AN ANALOGICAL APPROACH TO COMPLEX REASONING WITH LARGE LANGUAGE MODELS
  48. ICLR 2024ToolChain*: Efficient Action Space Navigation in Large Language Models with A* Search
  49. ICLR 2024ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs
  50. ICLR 2024ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving

在 Claude、Cursor 里直接问这个趋势

接上 Paperlist MCP 后，写综述、挑方向或准备投稿时，不用离开对话框就能拿到这页的数字：每年各会议的论文数、增长倍数、涨得最快的子方向和代表论文，AI 会按你的问题整理。

可以直接复制这句话问 AI

用 paperlist 查AI 智能体在 NeurIPS 2023–2026 的论文趋势，哪一年涨得最快？

AI 会调用的工具：get_topic_stats {"topic": "ai-agents"}

两分钟接入 Paperlist MCP（Claude Code、Cursor、Codex、ChatGPT）

常见问题

2023–2026 年四大会议一共有多少篇AI 智能体论文？
共 3,266 篇，按年份分别是 2023 年 170 篇、2024 年 329 篇、2025 年 784 篇、2026 年 1,983 篇。
NeurIPS 2026 有多少篇AI 智能体论文？
NeurIPS 2026 有 729 篇AI 智能体论文，上一届是 362 篇。
ICLR 2026 有多少篇AI 智能体论文？
ICLR 2026 有 500 篇AI 智能体论文，上一届是 204 篇。
ICML 2026 有多少篇AI 智能体论文？
ICML 2026 有 640 篇AI 智能体论文，上一届是 178 篇。
CVPR 2026 有多少篇AI 智能体论文？
CVPR 2026 有 114 篇AI 智能体论文，上一届是 40 篇。
哪个会议的AI 智能体论文最多？
NeurIPS，2023–2026 年共 1,317 篇。

「前沿系统」下的其他主题