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 59 / 66 页

  1. ICML 2024Improving Sample Efficiency of Model-Free Algorithms for Zero-Sum Markov Games
  2. ICML 2024Individual Contributions as Intrinsic Exploration Scaffolds for Multi-agent Reinforcement Learning
  3. ICML 2024InfiAgent-DABench: Evaluating Agents on Data Analysis Tasks
  4. ICML 2024LAGMA: LAtent Goal-guided Multi-Agent Reinforcement Learning
  5. ICML 2024Language-guided Skill Learning with Temporal Variational Inference
  6. ICML 2024Learning Associative Memories with Gradient Descent
  7. ICML 2024Learning the Uncertainty Sets of Linear Control Systems via Set Membership: A Non-asymptotic Analysis
  8. ICML 2024Locally Interdependent Multi-Agent MDP: Theoretical Framework for Decentralized Agents with Dynamic Dependencies
  9. ICML 2024Lookbehind-SAM: k steps back, 1 step forward
  10. ICML 2024MAGDi: Structured Distillation of Multi-Agent Interaction Graphs Improves Reasoning in Smaller Language Models
  11. ICML 2024Major-Minor Mean Field Multi-Agent Reinforcement Learning
  12. ICML 2024Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads
  13. ICML 2024MLAgentBench: Evaluating Language Agents on Machine Learning Experimentation
  14. ICML 2024Multi-Agent Reinforcement Learning Meets Leaf Sequencing in Radiotherapy
  15. ICML 2024Multi-Agent Reinforcement Learning with Hierarchical Coordination for Emergency Responder Stationing
  16. ICML 2024Multi-Sender Persuasion: A Computational Perspective
  17. ICML 2024Multi-Track Message Passing: Tackling Oversmoothing and Oversquashing in Graph Learning via Preventing Heterophily Mixing
  18. ICML 2024Near-Optimal Reinforcement Learning with Self-Play under Adaptivity Constraints
  19. ICML 2024Nonlinear Filtering with Brenier Optimal Transport Maps
  20. ICML 2024Offline Training of Language Model Agents with Functions as Learnable Weights
  21. ICML 2024On the Identifiability of Switching Dynamical Systems
  22. ICML 2024Online Learning in Betting Markets: Profit versus Prediction
  23. ICML 2024Optimistic Multi-Agent Policy Gradient
  24. ICML 2024PGODE: Towards High-quality System Dynamics Modeling
  25. ICML 2024Position: AI-Powered Autonomous Weapons Risk Geopolitical Instability and Threaten AI Research
  26. ICML 2024Position: Enforced Amnesia as a Way to Mitigate the Potential Risk of Silent Suffering in the Conscious AI
  27. ICML 2024Position: Foundation Agents as the Paradigm Shift for Decision Making
  28. ICML 2024Position: Fundamental Limitations of LLM Censorship Necessitate New Approaches
  29. ICML 2024Position: Towards Unified Alignment Between Agents, Humans, and Environment
  30. ICML 2024QuIP$\#$: Even Better LLM Quantization with Hadamard Incoherence and Lattice Codebooks
  31. ICML 2024R2E: Turning any Github Repository into a Programming Agent Environment
  32. ICML 2024Reason for Future, Act for Now: A Principled Architecture for Autonomous LLM Agents
  33. ICML 2024Residual Quantization with Implicit Neural Codebooks
  34. ICML 2024Sample-Efficient Robust Multi-Agent Reinforcement Learning in the Face of Environmental Uncertainty
  35. ICML 2024Scalable Safe Policy Improvement for Factored Multi-Agent MDPs
  36. ICML 2024SceneCraft: An LLM Agent for Synthesizing 3D Scenes as Blender Code
  37. ICML 2024Self-Rewarding Language Models
  38. ICML 2024Sequential Asynchronous Action Coordination in Multi-Agent Systems: A Stackelberg Decision Transformer Approach
  39. ICML 2024Should we be going MAD? A Look at Multi-Agent Debate Strategies for LLMs
  40. ICML 2024Socialized Learning: Making Each Other Better Through Multi-Agent Collaboration
  41. ICML 2024STEER: Assessing the Economic Rationality of Large Language Models
  42. ICML 2024Towards Resource-friendly, Extensible and Stable Incomplete Multi-view Clustering
  43. ICML 2024TravelPlanner: A Benchmark for Real-World Planning with Language Agents
  44. ICML 2024Two-sided Competing Matching Recommendation Markets With Quota and Complementary Preferences Constraints
  45. ICML 2024WorkArena: How Capable are Web Agents at Solving Common Knowledge Work Tasks?
  46. ICML 2024Zero-Sum Positional Differential Games as a Framework for Robust Reinforcement Learning: Deep Q-Learning Approach
  47. NeurIPS 2024A Decision-Language Model (DLM) for Dynamic Restless Multi-Armed Bandit Tasks in Public Health
  48. NeurIPS 2024A Synthetic Dataset for Personal Attribute Inference
  49. NeurIPS 2024AdaSociety: An Adaptive Environment with Social Structures for Multi-Agent Decision-Making
  50. NeurIPS 2024Agent Planning with World Knowledge Model

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