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 17 / 27 页

  1. NeurIPS 2025Cooperative Bargaining Games Without Utilities: Mediated Solutions from Direction Oracles
  2. NeurIPS 2025CoP: Agentic Red-teaming for Large Language Models using Composition of Principles
  3. NeurIPS 2025CORE: Reducing UI Exposure in Mobile Agents via Collaboration Between Cloud and Local LLMs
  4. NeurIPS 2025CPathAgent: An Agent-based Foundation Model for Interpretable High-Resolution Pathology Image Analysis Mimicking Pathologists' Diagnostic Logic
  5. NeurIPS 2025CREA: A Collaborative Multi-Agent Framework for Creative Image Editing and Generation
  6. NeurIPS 2025Crucible: Quantifying the Potential of Control Algorithms through LLM Agents
  7. NeurIPS 2025CURE: Co-Evolving Coders and Unit Testers via Reinforcement Learning
  8. NeurIPS 2025Curriculum Design for Trajectory-Constrained Agent: Compressing Chain-of-Thought Tokens in LLMs
  9. NeurIPS 2025DanmakuTPPBench: A Multi-modal Benchmark for Temporal Point Process Modeling and Understanding
  10. NeurIPS 2025Datasets, Documents, and Repetitions: The Practicalities of Unequal Data Quality
  11. NeurIPS 2025Debate or Vote: Which Yields Better Decisions in Multi-Agent Large Language Models?
  12. NeurIPS 2025Deep Video Discovery: Agentic Search with Tool Use for Long-form Video Understanding
  13. NeurIPS 2025DeepDiver: Adaptive Web-Search Intensity Scaling via Reinforcement Learning
  14. NeurIPS 2025Delta Attention: Fast and Accurate Sparse Attention Inference by Delta Correction
  15. NeurIPS 2025DISC: Dynamic Decomposition Improves LLM Inference Scaling
  16. NeurIPS 2025Distilling LLM Agent into Small Models with Retrieval and Code Tools
  17. NeurIPS 2025Distilling LLM Prior to Flow Model for Generalizable Agent’s Imagination in Object Goal Navigation
  18. NeurIPS 2025Distributed Multi-Agent Bandits Over Erdős-Rényi Random Networks
  19. NeurIPS 2025Do Language Models Use Their Depth Efficiently?
  20. NeurIPS 2025Don't be lazy: CompleteP enables compute-efficient deep transformers
  21. NeurIPS 2025DRIFT: Dynamic Rule-Based Defense with Injection Isolation for Securing LLM Agents
  22. NeurIPS 2025DyFlow: Dynamic Workflow Framework for Agentic Reasoning
  23. NeurIPS 2025Dynamic Risk Assessments for Offensive Cybersecurity Agents
  24. NeurIPS 2025EconGym: A Scalable AI Testbed with Diverse Economic Tasks
  25. NeurIPS 2025Effective Policy Learning for Multi-Agent Online Coordination Beyond Submodular Objectives
  26. NeurIPS 2025Eliciting Reasoning in Language Models with Cognitive Tools
  27. NeurIPS 2025Embodied Web Agents: Bridging Physical-Digital Realms for Integrated Agent Intelligence
  28. NeurIPS 2025Embracing Trustworthy Brain-Agent Collaboration as Paradigm Extension for Intelligent Assistive Technologies
  29. NeurIPS 2025Emergent Risk Awareness in Rational Agents under Resource Constraints
  30. NeurIPS 2025Empirical Study on Robustness and Resilience in Cooperative Multi-Agent Reinforcement Learning
  31. NeurIPS 2025EnCompass: Enhancing Agent Programming with Search Over Program Execution Paths
  32. NeurIPS 2025Enhancing GUI Agent with Uncertainty-Aware Self-Trained Evaluator
  33. NeurIPS 2025Enhancing Personalized Multi-Turn Dialogue with Curiosity Reward
  34. NeurIPS 2025ESCA: Contextualizing Embodied Agents via Scene-Graph Generation
  35. NeurIPS 2025Establishing Best Practices in Building Rigorous Agentic Benchmarks
  36. NeurIPS 2025EVAAA: A Virtual Environment Platform for Essential Variables in Autonomous and Adaptive Agents
  37. NeurIPS 2025Evaluating Generalization Capabilities of LLM-Based Agents in Mixed-Motive Scenarios Using Concordia
  38. NeurIPS 2025Evaluating LLMs in Open-Source Games
  39. NeurIPS 2025Eyes Wide Open: Ego Proactive Video-LLM for Streaming Video
  40. NeurIPS 2025FACE: A General Framework for Mapping Collaborative Filtering Embeddings into LLM Tokens
  41. NeurIPS 2025Factorio Learning Environment
  42. NeurIPS 2025Fair Cooperation in Mixed-Motive Games via Conflict-Aware Gradient Adjustment
  43. NeurIPS 2025From Euler to AI: Unifying Formulas for Mathematical Constants
  44. NeurIPS 2025From Replication to Redesign: Exploring Pairwise Comparisons for LLM-Based Peer Review
  45. NeurIPS 2025From Self-Check to Consensus: Bayesian Strategic Decoding in Large Language Models
  46. NeurIPS 2025G-Memory: Tracing Hierarchical Memory for Multi-Agent Systems
  47. NeurIPS 2025GAM-Agent: Game-Theoretic and Uncertainty-Aware Collaboration for Complex Visual Reasoning
  48. NeurIPS 2025Generalizing Experience for Language Agents with Hierarchical MetaFlows
  49. NeurIPS 2025Generative Caching for Structurally Similar Prompts and Responses
  50. NeurIPS 2025Gradient Multi-Normalization for Efficient LLM Training

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