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 1,317 篇，第 24 / 27 页

  1. NeurIPS 2024JaxMARL: Multi-Agent RL Environments and Algorithms in JAX
  2. NeurIPS 2024Kaleidoscope: Learnable Masks for Heterogeneous Multi-agent Reinforcement Learning
  3. NeurIPS 2024KALM: Knowledgeable Agents by Offline Reinforcement Learning from Large Language Model Rollouts
  4. NeurIPS 2024LACIE: Listener-Aware Finetuning for Calibration in Large Language Models
  5. NeurIPS 2024Language Grounded Multi-agent Reinforcement Learning with Human-interpretable Communication
  6. NeurIPS 2024Large Language Models as Urban Residents: An LLM Agent Framework for Personal Mobility Generation
  7. NeurIPS 2024Large Language Models Play StarCraft II:Benchmarks and A Chain of Summarization Approach
  8. NeurIPS 2024Latent Learning Progress Drives Autonomous Goal Selection in Human Reinforcement Learning
  9. NeurIPS 2024Learning Distinguishable Trajectory Representation with Contrastive Loss
  10. NeurIPS 2024Learning Equilibria in Adversarial Team Markov Games: A Nonconvex-Hidden-Concave Min-Max Optimization Problem
  11. NeurIPS 2024Learning in Markov Games with Adaptive Adversaries: Policy Regret, Fundamental Barriers, and Efficient Algorithms
  12. NeurIPS 2024Learning to Balance Altruism and Self-interest Based on Empathy in Mixed-Motive Games
  13. NeurIPS 2024Learning to Cooperate with Humans using Generative Agents
  14. NeurIPS 2024Learning to Discuss Strategically: A Case Study on One Night Ultimate Werewolf
  15. NeurIPS 2024Leveraging Environment Interaction for Automated PDDL Translation and Planning with Large Language Models
  16. NeurIPS 2024LogiCity: Advancing Neuro-Symbolic AI with Abstract Urban Simulation
  17. NeurIPS 2024Long-form factuality in large language models
  18. NeurIPS 2024Long-Horizon Planning for Multi-Agent Robots in Partially Observable Environments
  19. NeurIPS 2024MACM: Utilizing a Multi-Agent System for Condition Mining in Solving Complex Mathematical Problems
  20. NeurIPS 2024MADiff: Offline Multi-agent Learning with Diffusion Models
  21. NeurIPS 2024MAGIS: LLM-Based Multi-Agent Framework for GitHub Issue Resolution
  22. NeurIPS 2024Maximizing utility in multi-agent environments by anticipating the behavior of other learners
  23. NeurIPS 2024MDAgents: An Adaptive Collaboration of LLMs for Medical Decision-Making
  24. NeurIPS 2024Measuring Mutual Policy Divergence for Multi-Agent Sequential Exploration
  25. NeurIPS 2024Melting Pot Contest: Charting the Future of Generalized Cooperative Intelligence
  26. NeurIPS 2024Mimicking To Dominate: Imitation Learning Strategies for Success in Multiagent Games
  27. NeurIPS 2024Mobile-Agent-v2: Mobile Device Operation Assistant with Effective Navigation via Multi-Agent Collaboration
  28. NeurIPS 2024Multi-Agent Coordination via Multi-Level Communication
  29. NeurIPS 2024Multi-Agent Domain Calibration with a Handful of Offline Data
  30. NeurIPS 2024Multi-Agent Imitation Learning: Value is Easy, Regret is Hard
  31. NeurIPS 2024Multi-LLM Debate: Framework, Principals, and Interventions
  32. NeurIPS 2024N-agent Ad Hoc Teamwork
  33. NeurIPS 2024No-Regret Learning for Fair Multi-Agent Social Welfare Optimization
  34. NeurIPS 2024No-regret Learning in Harmonic Games: Extrapolation in the Face of Conflicting Interests
  35. NeurIPS 2024NYU CTF Bench: A Scalable Open-Source Benchmark Dataset for Evaluating LLMs in Offensive Security
  36. NeurIPS 2024Observational Scaling Laws and the Predictability of Langauge Model Performance
  37. NeurIPS 2024OccamLLM: Fast and Exact Language Model Arithmetic in a Single Step
  38. NeurIPS 2024On the Effects of Data Scale on UI Control Agents
  39. NeurIPS 2024Online Relational Inference for Evolving Multi-agent Interacting Systems
  40. NeurIPS 2024Opponent Modeling based on Subgoal Inference
  41. NeurIPS 2024Opponent Modeling with In-context Search
  42. NeurIPS 2024Optimus-1: Hybrid Multimodal Memory Empowered Agents Excel in Long-Horizon Tasks
  43. NeurIPS 2024OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
  44. NeurIPS 2024Paths to Equilibrium in Games
  45. NeurIPS 2024Policy Learning from Tutorial Books via Understanding, Rehearsing and Introspecting
  46. NeurIPS 2024Predicting Future Actions of Reinforcement Learning Agents
  47. NeurIPS 2024PrivacyLens: Evaluating Privacy Norm Awareness of Language Models in Action
  48. NeurIPS 2024Randomized Exploration in Cooperative Multi-Agent Reinforcement Learning
  49. NeurIPS 2024Reasoning Multi-Agent Behavioral Topology for Interactive Autonomous Driving
  50. NeurIPS 2024Reciprocal Reward Influence Encourages Cooperation From Self-Interested Agents

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