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 51 / 66 页

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

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