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 947 篇，第 17 / 19 页

  1. ICML 2025The Sample Complexity of Online Strategic Decision Making with Information Asymmetry and Knowledge Transportability
  2. ICML 2025The Synergy of LLMs & RL Unlocks Offline Learning of Generalizable Language-Conditioned Policies with Low-fidelity Data
  3. ICML 2025Tokenized Bandit for LLM Decoding and Alignment
  4. ICML 2025Tool Unlearning for Tool-Augmented LLMs
  5. ICML 2025Towards Efficient Online Tuning of VLM Agents via Counterfactual Soft Reinforcement Learning
  6. ICML 2025Towards Practical Defect-Focused Automated Code Review
  7. ICML 2025Training a Generally Curious Agent
  8. ICML 2025Training Software Engineering Agents and Verifiers with SWE-Gym
  9. ICML 2025UDora: A Unified Red Teaming Framework against LLM Agents by Dynamically Hijacking Their Own Reasoning
  10. ICML 2025UI-Vision: A Desktop-centric GUI Benchmark for Visual Perception and Interaction
  11. ICML 2025Unbiased Evaluation of Large Language Models from a Causal Perspective
  12. ICML 2025Understanding Bias Reinforcement in LLM Agents Debate
  13. ICML 2025UP-VLA: A Unified Understanding and Prediction Model for Embodied Agent
  14. ICML 2025What Limits Virtual Agent Application? OmniBench: A Scalable Multi-Dimensional Benchmark for Essential Virtual Agent Capabilities
  15. ICML 2025Which Agent Causes Task Failures and When? On Automated Failure Attribution of LLM Multi-Agent Systems
  16. ICML 2025Windows Agent Arena: Evaluating Multi-Modal OS Agents at Scale
  17. ICML 2025Wolfpack Adversarial Attack for Robust Multi-Agent Reinforcement Learning
  18. ICML 2025µnit Scaling: Simple and Scalable FP8 LLM Training
  19. ICML 2024${\rm E}(3)$-Equivariant Actor-Critic Methods for Cooperative Multi-Agent Reinforcement Learning
  20. ICML 2024A Human-Inspired Reading Agent with Gist Memory of Very Long Contexts
  21. ICML 2024Advancing DRL Agents in Commercial Fighting Games: Training, Integration, and Agent-Human Alignment
  22. ICML 2024Agent Smith: A Single Image Can Jailbreak One Million Multimodal LLM Agents Exponentially Fast
  23. ICML 2024Agent-Specific Effects: A Causal Effect Propagation Analysis in Multi-Agent MDPs
  24. ICML 2024AnyTool: Self-Reflective, Hierarchical Agents for Large-Scale API Calls
  25. ICML 2024ArCHer: Training Language Model Agents via Hierarchical Multi-Turn RL
  26. ICML 2024Asymptotics of feature learning in two-layer networks after one gradient-step
  27. ICML 2024BAGEL: Bootstrapping Agents by Guiding Exploration with Language
  28. ICML 2024Break the Sequential Dependency of LLM Inference Using Lookahead Decoding
  29. ICML 2024Can Looped Transformers Learn to Implement Multi-step Gradient Descent for In-context Learning?
  30. ICML 2024CHAI: Clustered Head Attention for Efficient LLM Inference
  31. ICML 2024Characterizing Truthfulness in Large Language Model Generations with Local Intrinsic Dimension
  32. ICML 2024Collage: Light-Weight Low-Precision Strategy for LLM Training
  33. ICML 2024CompeteAI: Understanding the Competition Dynamics of Large Language Model-based Agents
  34. ICML 2024Configurable Mirror Descent: Towards a Unification of Decision Making
  35. ICML 2024Controlling Behavioral Diversity in Multi-Agent Reinforcement Learning
  36. ICML 2024Detecting Influence Structures in Multi-Agent Reinforcement Learning
  37. ICML 2024diff History for Neural Language Agents
  38. ICML 2024Disentanglement Learning via Topology
  39. ICML 2024Double-Step Alternating Extragradient with Increasing Timescale Separation for Finding Local Minimax Points: Provable Improvements
  40. ICML 2024DS-Agent: Automated Data Science by Empowering Large Language Models with Case-Based Reasoning
  41. ICML 2024Dynamic Evaluation of Large Language Models by Meta Probing Agents
  42. ICML 2024EE-LLM: Large-Scale Training and Inference of Early-Exit Large Language Models with 3D Parallelism
  43. ICML 2024Efficient Adaptation in Mixed-Motive Environments via Hierarchical Opponent Modeling and Planning
  44. ICML 2024Efficient PAC Learnability of Dynamical Systems Over Multilayer Networks
  45. ICML 2024Embodied CoT Distillation From LLM To Off-the-shelf Agents
  46. ICML 2024Eureka-Moments in Transformers: Multi-Step Tasks Reveal Softmax Induced Optimization Problems
  47. ICML 2024Executable Code Actions Elicit Better LLM Agents
  48. ICML 2024Fair Federated Learning via the Proportional Veto Core
  49. ICML 2024Fast Peer Adaptation with Context-aware Exploration
  50. ICML 2024Federated Combinatorial Multi-Agent Multi-Armed Bandits

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