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 62 / 66 页

  1. NeurIPS 2024Predicting Future Actions of Reinforcement Learning Agents
  2. NeurIPS 2024PrivacyLens: Evaluating Privacy Norm Awareness of Language Models in Action
  3. NeurIPS 2024Randomized Exploration in Cooperative Multi-Agent Reinforcement Learning
  4. NeurIPS 2024Reasoning Multi-Agent Behavioral Topology for Interactive Autonomous Driving
  5. NeurIPS 2024Reciprocal Reward Influence Encourages Cooperation From Self-Interested Agents
  6. NeurIPS 2024Recursive Introspection: Teaching Language Model Agents How to Self-Improve
  7. NeurIPS 2024RedCode: Multi-dimensional Safety Benchmark for Code Agents
  8. NeurIPS 2024RedCode: Risky Code Execution and Generation Benchmark for Code Agents
  9. NeurIPS 2024Reflective Multi-Agent Collaboration based on Large Language Models
  10. NeurIPS 2024Reinforcing LLM Agents via Policy Optimization with Action Decomposition
  11. NeurIPS 2024RestoreAgent: Autonomous Image Restoration Agent via Multimodal Large Language Models
  12. NeurIPS 2024RGMDT: Return-Gap-Minimizing Decision Tree Extraction in Non-Euclidean Metric Space
  13. NeurIPS 2024Richelieu: Self-Evolving LLM-Based Agents for AI Diplomacy
  14. NeurIPS 2024RL-GPT: Integrating Reinforcement Learning and Code-as-policy
  15. NeurIPS 2024RoleAgent: Building, Interacting, and Benchmarking High-quality Role-Playing Agents from Scripts
  16. NeurIPS 2024Scalable Constrained Policy Optimization for Safe Multi-agent Reinforcement Learning
  17. NeurIPS 2024Secret Collusion among AI Agents: Multi-Agent Deception via Steganography
  18. NeurIPS 2024Self-Healing Machine Learning: A Framework for Autonomous Adaptation in Real-World Environments
  19. NeurIPS 2024SMART: Scalable Multi-agent Real-time Motion Generation via Next-token Prediction
  20. NeurIPS 2024SocraticLM: Exploring Socratic Personalized Teaching with Large Language Models
  21. NeurIPS 2024Spider2-V: How Far Are Multimodal Agents From Automating Data Science and Engineering Workflows?
  22. NeurIPS 2024Star-Agents: Automatic Data Optimization with LLM Agents for Instruction Tuning
  23. NeurIPS 2024StreamBench: Towards Benchmarking Continuous Improvement of Language Agents
  24. NeurIPS 2024SustainDC: Benchmarking for Sustainable Data Center Control
  25. NeurIPS 2024SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering
  26. NeurIPS 2024SWT-Bench: Testing and Validating Real-World Bug-Fixes with Code Agents
  27. NeurIPS 2024Synatra: Turning Indirect Knowledge into Direct Demonstrations for Digital Agents at Scale
  28. NeurIPS 2024T2Vs Meet VLMs: A Scalable Multimodal Dataset for Visual Harmfulness Recognition
  29. NeurIPS 2024TaskBench: Benchmarking Large Language Models for Task Automation
  30. NeurIPS 2024Team-Fictitious Play for Reaching Team-Nash Equilibrium in Multi-team Games
  31. NeurIPS 2024The Dormant Neuron Phenomenon in Multi-Agent Reinforcement Learning Value Factorization
  32. NeurIPS 2024Transformers as Game Players: Provable In-context Game-playing Capabilities of Pre-trained Models
  33. NeurIPS 2024Understanding Model Selection for Learning in Strategic Environments
  34. NeurIPS 2024UrbanKGent: A Unified Large Language Model Agent Framework for Urban Knowledge Graph Construction
  35. NeurIPS 2024Using Unity to Help Solve Reinforcement Learning
  36. NeurIPS 2024Value-Based Deep Multi-Agent Reinforcement Learning with Dynamic Sparse Training
  37. NeurIPS 2024VideoGUI: A Benchmark for GUI Automation from Instructional Videos
  38. NeurIPS 2024VLM Agents Generate Their Own Memories: Distilling Experience into Embodied Programs of Thought
  39. NeurIPS 2024Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents
  40. NeurIPS 2024WFCRL: A Multi-Agent Reinforcement Learning Benchmark for Wind Farm Control
  41. NeurIPS 2024Who’s Gaming the System? A Causally-Motivated Approach for Detecting Strategic Adaptation
  42. NeurIPS 2024WhodunitBench: Evaluating Large Multimodal Agents via Murder Mystery Games
  43. NeurIPS 2024WorkArena++: Towards Compositional Planning and Reasoning-based Common Knowledge Work Tasks
  44. NeurIPS 2024WorldCoder, a Model-Based LLM Agent: Building World Models by Writing Code and Interacting with the Environment
  45. NeurIPS 2024YouDream: Generating Anatomically Controllable Consistent Text-to-3D Animals
  46. NeurIPS 2024ZSC-Eval: An Evaluation Toolkit and Benchmark for Multi-agent Zero-shot Coordination
  47. CVPR 2023Behavioral Analysis of Vision-and-Language Navigation Agents
  48. CVPR 2023Collaboration Helps Camera Overtake LiDAR in 3D Detection
  49. CVPR 2023D2Former: Jointly Learning Hierarchical Detectors and Contextual Descriptors via Agent-Based Transformers
  50. CVPR 2023EqMotion: Equivariant Multi-Agent Motion Prediction With Invariant Interaction Reasoning

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