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 58 / 66 页

  1. ICLR 2024Towards Robust Multi-Modal Reasoning via Model Selection
  2. ICLR 2024Trajeglish: Traffic Modeling as Next-Token Prediction
  3. ICLR 2024Tree-Planner: Efficient Close-loop Task Planning with Large Language Models
  4. ICLR 2024Tuning LayerNorm in Attention: Towards Efficient Multi-Modal LLM Finetuning
  5. ICLR 2024Two-stage LLM Fine-tuning with Less Specialization and More Generalization
  6. ICLR 2024Variance Reduced Halpern Iteration for Finite-Sum Monotone Inclusions
  7. ICLR 2024WebArena: A Realistic Web Environment for Building Autonomous Agents
  8. ICLR 2024Whittle Index with Multiple Actions and State Constraint for Inventory Management
  9. ICML 2024${\rm E}(3)$-Equivariant Actor-Critic Methods for Cooperative Multi-Agent Reinforcement Learning
  10. ICML 2024A Human-Inspired Reading Agent with Gist Memory of Very Long Contexts
  11. ICML 2024Advancing DRL Agents in Commercial Fighting Games: Training, Integration, and Agent-Human Alignment
  12. ICML 2024Agent Smith: A Single Image Can Jailbreak One Million Multimodal LLM Agents Exponentially Fast
  13. ICML 2024Agent-Specific Effects: A Causal Effect Propagation Analysis in Multi-Agent MDPs
  14. ICML 2024AnyTool: Self-Reflective, Hierarchical Agents for Large-Scale API Calls
  15. ICML 2024ArCHer: Training Language Model Agents via Hierarchical Multi-Turn RL
  16. ICML 2024Asymptotics of feature learning in two-layer networks after one gradient-step
  17. ICML 2024BAGEL: Bootstrapping Agents by Guiding Exploration with Language
  18. ICML 2024Break the Sequential Dependency of LLM Inference Using Lookahead Decoding
  19. ICML 2024Can Looped Transformers Learn to Implement Multi-step Gradient Descent for In-context Learning?
  20. ICML 2024CHAI: Clustered Head Attention for Efficient LLM Inference
  21. ICML 2024Characterizing Truthfulness in Large Language Model Generations with Local Intrinsic Dimension
  22. ICML 2024Collage: Light-Weight Low-Precision Strategy for LLM Training
  23. ICML 2024CompeteAI: Understanding the Competition Dynamics of Large Language Model-based Agents
  24. ICML 2024Configurable Mirror Descent: Towards a Unification of Decision Making
  25. ICML 2024Controlling Behavioral Diversity in Multi-Agent Reinforcement Learning
  26. ICML 2024Detecting Influence Structures in Multi-Agent Reinforcement Learning
  27. ICML 2024diff History for Neural Language Agents
  28. ICML 2024Disentanglement Learning via Topology
  29. ICML 2024Double-Step Alternating Extragradient with Increasing Timescale Separation for Finding Local Minimax Points: Provable Improvements
  30. ICML 2024DS-Agent: Automated Data Science by Empowering Large Language Models with Case-Based Reasoning
  31. ICML 2024Dynamic Evaluation of Large Language Models by Meta Probing Agents
  32. ICML 2024EE-LLM: Large-Scale Training and Inference of Early-Exit Large Language Models with 3D Parallelism
  33. ICML 2024Efficient Adaptation in Mixed-Motive Environments via Hierarchical Opponent Modeling and Planning
  34. ICML 2024Efficient PAC Learnability of Dynamical Systems Over Multilayer Networks
  35. ICML 2024Embodied CoT Distillation From LLM To Off-the-shelf Agents
  36. ICML 2024Eureka-Moments in Transformers: Multi-Step Tasks Reveal Softmax Induced Optimization Problems
  37. ICML 2024Executable Code Actions Elicit Better LLM Agents
  38. ICML 2024Fair Federated Learning via the Proportional Veto Core
  39. ICML 2024Fast Peer Adaptation with Context-aware Exploration
  40. ICML 2024Federated Combinatorial Multi-Agent Multi-Armed Bandits
  41. ICML 2024Feedback Loops With Language Models Drive In-Context Reward Hacking
  42. ICML 2024FightLadder: A Benchmark for Competitive Multi-Agent Reinforcement Learning
  43. ICML 2024From Words to Actions: Unveiling the Theoretical Underpinnings of LLM-Driven Autonomous Systems
  44. ICML 2024Generalized Smooth Variational Inequalities: Methods with Adaptive Stepsizes
  45. ICML 2024GLoRe: When, Where, and How to Improve LLM Reasoning via Global and Local Refinements
  46. ICML 2024GPT-4V(ision) is a Generalist Web Agent, if Grounded
  47. ICML 2024GPTSwarm: Language Agents as Optimizable Graphs
  48. ICML 2024HGAP: Boosting Permutation Invariant and Permutation Equivariant in Multi-Agent Reinforcement Learning via Graph Attention Network
  49. ICML 2024How Well Can LLMs Negotiate? NegotiationArena Platform and Analysis
  50. ICML 2024Impact of Decentralized Learning on Player Utilities in Stackelberg Games

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