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 362 篇，第 3 / 8 页

  1. NeurIPS 2025Empirical Study on Robustness and Resilience in Cooperative Multi-Agent Reinforcement Learning
  2. NeurIPS 2025EnCompass: Enhancing Agent Programming with Search Over Program Execution Paths
  3. NeurIPS 2025Enhancing GUI Agent with Uncertainty-Aware Self-Trained Evaluator
  4. NeurIPS 2025Enhancing Personalized Multi-Turn Dialogue with Curiosity Reward
  5. NeurIPS 2025ESCA: Contextualizing Embodied Agents via Scene-Graph Generation
  6. NeurIPS 2025Establishing Best Practices in Building Rigorous Agentic Benchmarks
  7. NeurIPS 2025EVAAA: A Virtual Environment Platform for Essential Variables in Autonomous and Adaptive Agents
  8. NeurIPS 2025Evaluating Generalization Capabilities of LLM-Based Agents in Mixed-Motive Scenarios Using Concordia
  9. NeurIPS 2025Evaluating LLMs in Open-Source Games
  10. NeurIPS 2025Eyes Wide Open: Ego Proactive Video-LLM for Streaming Video
  11. NeurIPS 2025FACE: A General Framework for Mapping Collaborative Filtering Embeddings into LLM Tokens
  12. NeurIPS 2025Factorio Learning Environment
  13. NeurIPS 2025Fair Cooperation in Mixed-Motive Games via Conflict-Aware Gradient Adjustment
  14. NeurIPS 2025From Euler to AI: Unifying Formulas for Mathematical Constants
  15. NeurIPS 2025From Replication to Redesign: Exploring Pairwise Comparisons for LLM-Based Peer Review
  16. NeurIPS 2025From Self-Check to Consensus: Bayesian Strategic Decoding in Large Language Models
  17. NeurIPS 2025G-Memory: Tracing Hierarchical Memory for Multi-Agent Systems
  18. NeurIPS 2025GAM-Agent: Game-Theoretic and Uncertainty-Aware Collaboration for Complex Visual Reasoning
  19. NeurIPS 2025Generalizing Experience for Language Agents with Hierarchical MetaFlows
  20. NeurIPS 2025Generative Caching for Structurally Similar Prompts and Responses
  21. NeurIPS 2025Gradient Multi-Normalization for Efficient LLM Training
  22. NeurIPS 2025GRAPE: Optimize Data Mixture for Group Robust Multi-target Adaptive Pretraining
  23. NeurIPS 2025GraphMaster: Automated Graph Synthesis via LLM Agents in Data-Limited Environments
  24. NeurIPS 2025Graphs Help Graphs: Multi-Agent Graph Socialized Learning
  25. NeurIPS 2025Ground-Compose-Reinforce: Grounding Language in Agentic Behaviours using Limited Data
  26. NeurIPS 2025Group-in-Group Policy Optimization for LLM Agent Training
  27. NeurIPS 2025GSO: Challenging Software Optimization Tasks for Evaluating SWE-Agents
  28. NeurIPS 2025GUARDIAN: Safeguarding LLM Multi-Agent Collaborations with Temporal Graph Modeling
  29. NeurIPS 2025GUI Exploration Lab: Enhancing Screen Navigation in Agents via Multi-Turn Reinforcement Learning
  30. NeurIPS 2025GUI-Actor: Coordinate-Free Visual Grounding for GUI Agents
  31. NeurIPS 2025GUI-Reflection: Empowering Multimodal GUI Models with Self-Reflection Behavior
  32. NeurIPS 2025HeavyWater and SimplexWater: Distortion-free LLM Watermarks for Low-Entropy Distributions
  33. NeurIPS 2025Heterogeneous Graph Transformers for Simultaneous Mobile Multi-Robot Task Allocation and Scheduling under Temporal Constraints
  34. NeurIPS 2025Heterogeneous Swarms: Jointly Optimizing Model Roles and Weights for Multi-LLM Systems
  35. NeurIPS 2025Hi3DEval: Advancing 3D Generation Evaluation with Hierarchical Validity
  36. NeurIPS 2025High-order Interactions Modeling for Interpretable Multi-Agent Q-Learning
  37. NeurIPS 2025HMARL-CBF – Hierarchical Multi-Agent Reinforcement Learning with Control Barrier Functions for Safety-Critical Autonomous Systems
  38. NeurIPS 2025How to Train Your LLM Web Agent: A Statistical Diagnosis
  39. NeurIPS 2025Human Texts Are Outliers: Detecting LLM-generated Texts via Out-of-distribution Detection
  40. NeurIPS 2025HyperMARL: Adaptive Hypernetworks for Multi-Agent RL
  41. NeurIPS 2025HYPRL: Reinforcement Learning of Control Policies for Hyperproperties
  42. NeurIPS 2025Impartial Selection with Predictions
  43. NeurIPS 2025Improving Retrieval-Augmented Generation through Multi-Agent Reinforcement Learning
  44. NeurIPS 2025In-Context Fully Decentralized Cooperative Multi-Agent Reinforcement Learning
  45. NeurIPS 2025In-context Learning of Linear Dynamical Systems with Transformers: Approximation Bounds and Depth-separation
  46. NeurIPS 2025Incentive-Aware Dynamic Resource Allocation under Long-Term Cost Constraints
  47. NeurIPS 2025Individual Regret in Cooperative Stochastic Multi-Armed Bandits
  48. NeurIPS 2025InfantAgent-Next: A Multimodal Generalist Agent for Automated Computer Interaction
  49. NeurIPS 2025Information Retrieval Induced Safety Degradation in AI Agents
  50. NeurIPS 2025InstructFlow: Adaptive Symbolic Constraint-Guided Code Generation for Long-Horizon Planning

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