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 640 篇，第 10 / 13 页

  1. ICML 2026Probabilistic Modeling of Latent Agentic Substructures in Deep Neural Networks
  2. ICML 2026Probing the Knowledge Boundary: An Interactive Agentic Framework for Deep Knowledge Extraction
  3. ICML 2026Procedural Generation Of Algorithm Discovery Tasks in Machine Learning
  4. ICML 2026Profiling the Irrational Agent: Cognitive Modeling of LLM Behaviors in Sequential Jailbreaks
  5. ICML 2026PromptPilot: Game-Theoretic Multi-Agent Prompt Optimization for Segment Anything
  6. ICML 2026Protein Design with Agent Rosetta: A Case Study for Specialized Scientific Agents
  7. ICML 2026ProtocolBench: Which LLM MultiAgent Protocol to Choose?
  8. ICML 2026Provably Convergent Actor-Critic for MARL through Risk-aversion
  9. ICML 2026PSBench: Editing Image via GUI Agents in Photoshop
  10. ICML 2026Pushing Forward Pareto Frontiers of Proactive Agents with Behavioral Agentic Optimization
  11. ICML 2026PyVision-RL: Forging Open Agentic Vision Models via RL
  12. ICML 2026QiMeng-ChipV-RTL: Exploiting Information Locality for IP-level Verilog Generation
  13. ICML 2026QiMeng-LibBench: Benchmarking LLM Agents for Library-Scale Cross-Architecture Migration
  14. ICML 2026Quantifying Frontier LLM Capabilities for Container Sandbox Escape
  15. ICML 2026Quartet II: Accurate LLM Pre-Training in NVFP4 by Improved Unbiased Gradient Estimation
  16. ICML 2026RADAR: Redundancy-Aware Diffusion for Multi-Agent Communication Structure Generation
  17. ICML 2026RAGEN-2: Reasoning Collapse in Agentic RL
  18. ICML 2026RE-TRAC: REcursive TRAjectory Compression for Deep Search Agents
  19. ICML 2026RealtimeTool: Parallel Decoding for Real-Time LLM Function Calling
  20. ICML 2026Recognize Your Orchestrator: An Entropy Dynamics Perspective for LLM Multi-Agent Systems
  21. ICML 2026Recovering Policy-Induced Errors: Benchmarking and Trajectory Synthesis for Robust GUI Agents
  22. ICML 2026Recursive Models for Long-Horizon Reasoning
  23. ICML 2026RedDebate: Safer Responses Through Multi-Agent Red Teaming Debates
  24. ICML 2026RefineEvo: Planning-Guided Heuristic Evolution with Bidirectional Experience
  25. ICML 2026Reinforcement Learning for Tool-Calling Agents in Fast Healthcare Interoperability Resources (FHIR)
  26. ICML 2026Reinforcement Learning with Discrete Diffusion Policies for Combinatorial Action Spaces
  27. ICML 2026ReJump: A Tree-Jump Representation for Analyzing and Improving LLM Reasoning
  28. ICML 2026RelayCaching: Accelerating LLM Collaboration via Decoding KV Cache Reuse
  29. ICML 2026Representational Similarity and Model Behavior in Multi-Agent Interaction
  30. ICML 2026ReSeek: A Self-Correcting Framework for Search Agents with Instructive Rewards
  31. ICML 2026Rethinking LLM Ensembling from the Perspective of Mixture Models
  32. ICML 2026RetrOrchestrator: A Multi-Step Retrosynthesis Agent Dynamically Orchestrating Single-Step Transition Models
  33. ICML 2026Reward Hacking Benchmark: Measuring Exploits in LLM Agents with Tool Use
  34. ICML 2026RGMem: Renormalization Group–inspired Memory Evolution for Language Agents
  35. ICML 2026RLAnything: Forge Environment, Policy, and Reward Model in Completely Dynamic RL System
  36. ICML 2026Role-Level Inductive Bias for Cross-Task Generalization in Multi-Agent Reinforcement Learning
  37. ICML 2026RSAgent: Learning to Reason and Act via Multi-Turn Tool Invocations for Text-Guided Segmentation
  38. ICML 2026RSF-GLLM: Bridging the Semantic Gap in Multi-Hop Knowledge Graph QA via Recurrent Soft-Flow and Decoupled LLM Generation
  39. ICML 2026Rule2DRC: Benchmarking LLM Agents for DRC Script Synthesis with Execution-Guided Test Generation
  40. ICML 2026Safe and Scalable Web Agent Learning via Recreated Websites
  41. ICML 2026SafeHarbor: Defining Precise Decision Boundaries via Hierarchical Memory-Augmented Guardrail for LLM Agent Safety
  42. ICML 2026SafeSearch: Automated Red-Teaming of LLM-Based Search Agents
  43. ICML 2026Safety Alignment of LMs via Non-cooperative Games
  44. ICML 2026Safety Game: Inference-Time Alignment of Black-Box LLMs via Constrained Optimization
  45. ICML 2026SAGE-NAS: Synergizing LLM-Based Semantic Agent with Graph-Based Evaluator for Neural Architecture Search
  46. ICML 2026SAGE: A Dataflow-Native Framework for Modular, Controllable, and Transparent LLM-Augmented Reasoning
  47. ICML 2026Salus: Strategic Diagnostic Testing for Complex Diagnosis via Multi-Agent Reinforcement Learning
  48. ICML 2026SARL: Structure-Aligned Reinforcement Learning for Bridging the Perception-Action Gap in Airspace
  49. ICML 2026Scalable Traffic Signal Control with Shared Policy Framework
  50. ICML 2026ScaleEnv: Scaling Environment Synthesis from Scratch for Generalist Interactive Tool-Use Agent 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