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 56 / 66 页

  1. NeurIPS 2025VAGEN: Reinforcing World Model Reasoning for Multi-Turn VLM Agents
  2. NeurIPS 2025VideoCAD: A Dataset and Model for Learning Long‑Horizon 3D CAD UI Interactions from Video
  3. NeurIPS 2025VIKI‑R: Coordinating Embodied Multi-Agent Cooperation via Reinforcement Learning
  4. NeurIPS 2025VLMLight: Safety-Critical Traffic Signal Control via Vision-Language Meta-Control and Dual-Branch Reasoning Architecture
  5. NeurIPS 2025VolleyBots: A Testbed for Multi-Drone Volleyball Game Combining Motion Control and Strategic Play
  6. NeurIPS 2025WALL-E: World Alignment by NeuroSymbolic Learning improves World Model-based LLM Agents
  7. NeurIPS 2025WASP: Benchmarking Web Agent Security Against Prompt Injection Attacks
  8. NeurIPS 2025Web-Shepherd: Advancing PRMs for Reinforcing Web Agents
  9. NeurIPS 2025WebDancer: Towards Autonomous Information Seeking Agency
  10. NeurIPS 2025WebGen-Bench: Evaluating LLMs on Generating Interactive and Functional Websites from Scratch
  11. NeurIPS 2025What is Your Data Worth to GPT? LLM-Scale Data Valuation with Influence Functions
  12. NeurIPS 2025Who You Are Matters: Bridging Interests and Social Roles via LLM-Enhanced Logic Recommendation
  13. NeurIPS 2025Why Do Multi-Agent LLM Systems Fail?
  14. NeurIPS 2025Wide-Horizon Thinking and Simulation-Based Evaluation for Real-World LLM Planning with Multifaceted Constraints
  15. NeurIPS 2025Win Fast or Lose Slow: Balancing Speed and Accuracy in Latency-Sensitive Decisions of LLMs
  16. NeurIPS 2025Wonder Wins Ways: Curiosity-Driven Exploration through Multi-Agent Contextual Calibration
  17. NeurIPS 2025Yggdrasil: Bridging Dynamic Speculation and Static Runtime for Latency-Optimal Tree-Based LLM Decoding
  18. CVPR 2024Adaptive Fusion of Single-View and Multi-View Depth for Autonomous Driving
  19. CVPR 2024AnySkill: Learning Open-Vocabulary Physical Skill for Interactive Agents
  20. CVPR 2024AssistGUI: Task-Oriented PC Graphical User Interface Automation
  21. CVPR 2024Bridging the Gap Between End-to-End and Two-Step Text Spotting
  22. CVPR 2024Density-Adaptive Model Based on Motif Matrix for Multi-Agent Trajectory Prediction
  23. CVPR 2024DiffAgent: Fast and Accurate Text-to-Image API Selection with Large Language Model
  24. CVPR 2024Draw Step by Step: Reconstructing CAD Construction Sequences from Point Clouds via Multimodal Diffusion.
  25. CVPR 2024Editable Scene Simulation for Autonomous Driving via Collaborative LLM-Agents
  26. CVPR 2024Embodied Multi-Modal Agent trained by an LLM from a Parallel TextWorld
  27. CVPR 2024Feedback-Guided Autonomous Driving
  28. CVPR 2024LASIL: Learner-Aware Supervised Imitation Learning For Long-term Microscopic Traffic Simulation
  29. CVPR 2024Multi-agent Collaborative Perception via Motion-aware Robust Communication Network
  30. CVPR 2024Multi-agent Long-term 3D Human Pose Forecasting via Interaction-aware Trajectory Conditioning
  31. CVPR 2024MultiPLY: A Multisensory Object-Centric Embodied Large Language Model in 3D World
  32. CVPR 2024OPERA: Alleviating Hallucination in Multi-Modal Large Language Models via Over-Trust Penalty and Retrospection-Allocation
  33. CVPR 2024PerceptionGPT: Effectively Fusing Visual Perception into LLM
  34. CVPR 2024Suppress and Rebalance: Towards Generalized Multi-Modal Face Anti-Spoofing
  35. CVPR 2024Unsupervised Learning of Category-Level 3D Pose from Object-Centric Videos
  36. ICLR 2024A Black-box Approach for Non-stationary Multi-agent Reinforcement Learning
  37. ICLR 2024A Real-World WebAgent with Planning, Long Context Understanding, and Program Synthesis
  38. ICLR 2024Achieving Fairness in Multi-Agent MDP Using Reinforcement Learning
  39. ICLR 2024AgentBench: Evaluating LLMs as Agents
  40. ICLR 2024AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors
  41. ICLR 2024An LLM can Fool Itself: A Prompt-Based Adversarial Attack
  42. ICLR 2024Attention-Guided Contrastive Role Representations for Multi-agent Reinforcement Learning
  43. ICLR 2024Building Cooperative Embodied Agents Modularly with Large Language Models
  44. ICLR 2024Byzantine Robust Cooperative Multi-Agent Reinforcement Learning as a Bayesian Game
  45. ICLR 2024Can LLM-Generated Misinformation Be Detected?
  46. ICLR 2024Causal Modelling Agents: Causal Graph Discovery through Synergising Metadata- and Data-driven Reasoning
  47. ICLR 2024Chain-of-Experts: When LLMs Meet Complex Operations Research Problems
  48. ICLR 2024ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate
  49. ICLR 2024CivRealm: A Learning and Reasoning Odyssey in Civilization for Decision-Making Agents
  50. ICLR 2024Copula Conformal prediction for multi-step time series prediction

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