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 63 / 66 页

  1. CVPR 2023FJMP: Factorized Joint Multi-Agent Motion Prediction Over Learned Directed Acyclic Interaction Graphs
  2. CVPR 2023IPCC-TP: Utilizing Incremental Pearson Correlation Coefficient for Joint Multi-Agent Trajectory Prediction
  3. CVPR 2023MotionDiffuser: Controllable Multi-Agent Motion Prediction Using Diffusion
  4. CVPR 2023Multi-Agent Automated Machine Learning
  5. CVPR 2023PoseExaminer: Automated Testing of Out-of-Distribution Robustness in Human Pose and Shape Estimation
  6. CVPR 2023Query-Centric Trajectory Prediction
  7. CVPR 2023Revisiting the P3P Problem
  8. CVPR 2023StarCraftImage: A Dataset for Prototyping Spatial Reasoning Methods for Multi-Agent Environments
  9. CVPR 2023ViP3D: End-to-End Visual Trajectory Prediction via 3D Agent Queries
  10. ICLR 2023$O(T^{-1})$ Convergence of Optimistic-Follow-the-Regularized-Leader in Two-Player Zero-Sum Markov Games
  11. ICLR 2023Achieving Near-Optimal Individual Regret & Low Communications in Multi-Agent Bandits
  12. ICLR 2023Adversarial Diversity in Hanabi
  13. ICLR 2023Asynchronous Gradient Play in Zero-Sum Multi-agent Games
  14. ICLR 2023Broken Neural Scaling Laws
  15. ICLR 2023Can We Find Nash Equilibria at a Linear Rate in Markov Games?
  16. ICLR 2023Certifiably Robust Policy Learning against Adversarial Multi-Agent Communication
  17. ICLR 2023Cheap Talk Discovery and Utilization in Multi-Agent Reinforcement Learning
  18. ICLR 2023Collaborative Pure Exploration in Kernel Bandit
  19. ICLR 2023Competitive Physics Informed Networks
  20. ICLR 2023Discovering Generalizable Multi-agent Coordination Skills from Multi-task Offline Data
  21. ICLR 2023Does Zero-Shot Reinforcement Learning Exist?
  22. ICLR 2023Efficiently Computing Nash Equilibria in Adversarial Team Markov Games
  23. ICLR 2023Faster Last-iterate Convergence of Policy Optimization in Zero-Sum Markov Games
  24. ICLR 2023Generating Diverse Cooperative Agents by Learning Incompatible Policies
  25. ICLR 2023GoBigger: A Scalable Platform for Cooperative-Competitive Multi-Agent Interactive Simulation
  26. ICLR 2023Implicit regularization in Heavy-ball momentum accelerated stochastic gradient descent
  27. ICLR 2023Learning Rationalizable Equilibria in Multiplayer Games
  28. ICLR 2023Learning to Extrapolate: A Transductive Approach
  29. ICLR 2023Learning Zero-Shot Cooperation with Humans, Assuming Humans Are Biased
  30. ICLR 2023MACTA: A Multi-agent Reinforcement Learning Approach for Cache Timing Attacks and Detection
  31. ICLR 2023MAESTRO: Open-Ended Environment Design for Multi-Agent Reinforcement Learning
  32. ICLR 2023Mastering the Game of No-Press Diplomacy via Human-Regularized Reinforcement Learning and Planning
  33. ICLR 2023Minimax Optimal Kernel Operator Learning via Multilevel Training
  34. ICLR 2023More Centralized Training, Still Decentralized Execution: Multi-Agent Conditional Policy Factorization
  35. ICLR 2023Neural Agents Struggle to Take Turns in Bidirectional Emergent Communication
  36. ICLR 2023Offline Congestion Games: How Feedback Type Affects Data Coverage Requirement
  37. ICLR 2023Order Matters: Agent-by-agent Policy Optimization
  38. ICLR 2023Proactive Multi-Camera Collaboration for 3D Human Pose Estimation
  39. ICLR 2023ReAct: Synergizing Reasoning and Acting in Language Models
  40. ICLR 2023Representation Learning for Low-rank General-sum Markov Games
  41. ICLR 2023Revisiting Populations in multi-agent Communication
  42. ICLR 2023RPM: Generalizable Multi-Agent Policies for Multi-Agent Reinforcement Learning
  43. ICLR 2023Scaling Laws for a Multi-Agent Reinforcement Learning Model
  44. ICLR 2023Solving Continuous Control via Q-learning
  45. ICLR 2023Stateful Active Facilitator: Coordination and Environmental Heterogeneity in Cooperative Multi-Agent Reinforcement Learning
  46. ICLR 2023Taking a Step Back with KCal: Multi-Class Kernel-Based Calibration for Deep Neural Networks
  47. ICLR 2023The Implicit Bias of Minima Stability in Multivariate Shallow ReLU Networks
  48. ICLR 2023Towards Effective and Interpretable Human-Agent Collaboration in MOBA Games: A Communication Perspective
  49. ICLR 2023Truthful Self-Play
  50. ICML 2023A Game-Theoretic Framework for Managing Risk in Multi-Agent Systems

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