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 817 篇，第 16 / 17 页

  1. ICLR 2024Rethinking Adversarial Policies: A Generalized Attack Formulation and Provable Defense in RL
  2. ICLR 2024Retroformer: Retrospective Large Language Agents with Policy Gradient Optimization
  3. ICLR 2024REValueD: Regularised Ensemble Value-Decomposition for Factorisable Markov Decision Processes
  4. ICLR 2024Reward Design for Justifiable Sequential Decision-Making
  5. ICLR 2024Sample-Efficient Multi-Agent RL: An Optimization Perspective
  6. ICLR 2024Select to Perfect: Imitating desired behavior from large multi-agent data
  7. ICLR 2024SKILL-MIX: a Flexible and Expandable Family of Evaluations for AI Models
  8. ICLR 2024SmartPlay : A Benchmark for LLMs as Intelligent Agents
  9. ICLR 2024SocioDojo: Building Lifelong Analytical Agents with Real-world Text and Time Series
  10. ICLR 2024Solving Homogeneous and Heterogeneous Cooperative Tasks with Greedy Sequential Execution
  11. ICLR 2024SOTOPIA: Interactive Evaluation for Social Intelligence in Language Agents
  12. ICLR 2024Steve-Eye: Equipping LLM-based Embodied Agents with Visual Perception in Open Worlds
  13. ICLR 2024Synapse: Trajectory-as-Exemplar Prompting with Memory for Computer Control
  14. ICLR 2024The LLM Surgeon
  15. ICLR 2024Think-on-Graph: Deep and Responsible Reasoning of Large Language Model on Knowledge Graph
  16. ICLR 2024THOUGHT PROPAGATION: AN ANALOGICAL APPROACH TO COMPLEX REASONING WITH LARGE LANGUAGE MODELS
  17. ICLR 2024ToolChain*: Efficient Action Space Navigation in Large Language Models with A* Search
  18. ICLR 2024ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs
  19. ICLR 2024ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving
  20. ICLR 2024Towards Robust Multi-Modal Reasoning via Model Selection
  21. ICLR 2024Trajeglish: Traffic Modeling as Next-Token Prediction
  22. ICLR 2024Tree-Planner: Efficient Close-loop Task Planning with Large Language Models
  23. ICLR 2024Tuning LayerNorm in Attention: Towards Efficient Multi-Modal LLM Finetuning
  24. ICLR 2024Two-stage LLM Fine-tuning with Less Specialization and More Generalization
  25. ICLR 2024Variance Reduced Halpern Iteration for Finite-Sum Monotone Inclusions
  26. ICLR 2024WebArena: A Realistic Web Environment for Building Autonomous Agents
  27. ICLR 2024Whittle Index with Multiple Actions and State Constraint for Inventory Management
  28. ICLR 2023$O(T^{-1})$ Convergence of Optimistic-Follow-the-Regularized-Leader in Two-Player Zero-Sum Markov Games
  29. ICLR 2023Achieving Near-Optimal Individual Regret & Low Communications in Multi-Agent Bandits
  30. ICLR 2023Adversarial Diversity in Hanabi
  31. ICLR 2023Asynchronous Gradient Play in Zero-Sum Multi-agent Games
  32. ICLR 2023Broken Neural Scaling Laws
  33. ICLR 2023Can We Find Nash Equilibria at a Linear Rate in Markov Games?
  34. ICLR 2023Certifiably Robust Policy Learning against Adversarial Multi-Agent Communication
  35. ICLR 2023Cheap Talk Discovery and Utilization in Multi-Agent Reinforcement Learning
  36. ICLR 2023Collaborative Pure Exploration in Kernel Bandit
  37. ICLR 2023Competitive Physics Informed Networks
  38. ICLR 2023Discovering Generalizable Multi-agent Coordination Skills from Multi-task Offline Data
  39. ICLR 2023Does Zero-Shot Reinforcement Learning Exist?
  40. ICLR 2023Efficiently Computing Nash Equilibria in Adversarial Team Markov Games
  41. ICLR 2023Faster Last-iterate Convergence of Policy Optimization in Zero-Sum Markov Games
  42. ICLR 2023Generating Diverse Cooperative Agents by Learning Incompatible Policies
  43. ICLR 2023GoBigger: A Scalable Platform for Cooperative-Competitive Multi-Agent Interactive Simulation
  44. ICLR 2023Implicit regularization in Heavy-ball momentum accelerated stochastic gradient descent
  45. ICLR 2023Learning Rationalizable Equilibria in Multiplayer Games
  46. ICLR 2023Learning to Extrapolate: A Transductive Approach
  47. ICLR 2023Learning Zero-Shot Cooperation with Humans, Assuming Humans Are Biased
  48. ICLR 2023MACTA: A Multi-agent Reinforcement Learning Approach for Cache Timing Attacks and Detection
  49. ICLR 2023MAESTRO: Open-Ended Environment Design for Multi-Agent Reinforcement Learning
  50. ICLR 2023Mastering the Game of No-Press Diplomacy via Human-Regularized Reinforcement Learning and Planning

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