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 784 篇，第 13 / 16 页

  1. NeurIPS 2025LILO: Learning to Reason at the Frontier of Learnability
  2. NeurIPS 2025LLM Generated Persona is a Promise with a Catch
  3. NeurIPS 2025LLM Meeting Decision Trees on Tabular Data
  4. NeurIPS 2025LLM Query Scheduling with Prefix Reuse and Latency Constraints
  5. NeurIPS 2025LLM Strategic Reasoning: Agentic Study through Behavioral Game Theory
  6. NeurIPS 2025LLM Unlearning via Neural Activation Redirection
  7. NeurIPS 2025LLM-DAMVC: A Large Language Model Assisted Dynamic Agent for Multi-View Clustering
  8. NeurIPS 2025LLM-PySC2: Starcraft II learning environment for Large Language Models
  9. NeurIPS 2025Look Before You Leap: A GUI-Critic-R1 Model for Pre-Operative Error Diagnosis in GUI Automation
  10. NeurIPS 2025LOPT: Learning Optimal Pigovian Tax in Sequential Social Dilemmas
  11. NeurIPS 2025macOSWorld: A Multilingual Interactive Benchmark for GUI Agents
  12. NeurIPS 2025MACS: Multi-Agent Reinforcement Learning for Optimization of Crystal Structures
  13. NeurIPS 2025MAGNET: A Multi-agent Framework for Finding Audio-Visual Needles by Reasoning over Multi-Video Haystacks
  14. NeurIPS 2025MaintainCoder: Maintainable Code Generation Under Dynamic Requirements
  15. NeurIPS 2025MALinZero: Efficient Low-Dimensional Search for Mastering Complex Multi-Agent Planning
  16. NeurIPS 2025Many LLMs Are More Utilitarian Than One
  17. NeurIPS 2025Many Minds, One Goal: Time Series Forecasting via Sub-task Specialization and Inter-agent Cooperation
  18. NeurIPS 2025MASTER: Enhancing Large Language Model via Multi-Agent Simulated Teaching
  19. NeurIPS 2025MAT-Agent: Adaptive Multi-Agent Training Optimization
  20. NeurIPS 2025Mean-Field Sampling for Cooperative Multi-Agent Reinforcement Learning
  21. NeurIPS 2025Measuring Scientific Capabilities of Language Models with a Systems Biology Dry Lab
  22. NeurIPS 2025Mechanism Design via the Interim Relaxation
  23. NeurIPS 2025MedAgentBoard: Benchmarking Multi-Agent Collaboration with Conventional Methods for Diverse Medical Tasks
  24. NeurIPS 2025MedChain: Bridging the Gap Between LLM Agents and Clinical Practice with Interactive Sequence
  25. NeurIPS 2025Memory Injection Attacks on LLM Agents via Query-Only Interaction
  26. NeurIPS 2025MemSim: A Bayesian Simulator for Evaluating Memory of LLM-based Personal Assistants
  27. NeurIPS 2025MetaMind: Modeling Human Social Thoughts with Metacognitive Multi-Agent Systems
  28. NeurIPS 2025metaTextGrad: Automatically optimizing language model optimizers
  29. NeurIPS 2025Mind2Web 2: Evaluating Agentic Search with Agent-as-a-Judge
  30. NeurIPS 2025MindForge: Empowering Embodied Agents with Theory of Mind for Lifelong Cultural Learning
  31. NeurIPS 2025MineAnyBuild: Benchmarking Spatial Planning for Open-world AI Agents
  32. NeurIPS 2025MIP against Agent: Malicious Image Patches Hijacking Multimodal OS Agents
  33. NeurIPS 2025MisoDICE: Multi-Agent Imitation from Mixed-Quality Demonstrations
  34. NeurIPS 2025MLE-Dojo: Interactive Environments for Empowering LLM Agents in Machine Learning Engineering
  35. NeurIPS 2025MLE-STAR: Machine Learning Engineering Agent via Search and Targeted Refinement
  36. NeurIPS 2025MLR-Bench: Evaluating AI Agents on Open-Ended Machine Learning Research
  37. NeurIPS 2025MLRC-Bench: Can Language Agents Solve Machine Learning Research Challenges?
  38. NeurIPS 2025MLZero: A Multi-Agent System for End-to-end Machine Learning Automation
  39. NeurIPS 2025MM-Agent: LLM as Agents for Real-world Mathematical Modeling Problem
  40. NeurIPS 2025MobileUse: A Hierarchical Reflection-Driven GUI Agent for Autonomous Mobile Operation
  41. NeurIPS 2025MoodAngels: A Retrieval-augmented Multi-agent Framework for Psychiatry Diagnosis
  42. NeurIPS 2025MOSDT: Self-Distillation-Based Decision Transformer for Multi-Agent Offline Safe Reinforcement Learning
  43. NeurIPS 2025MPCache: MPC-Friendly KV Cache Eviction for Efficient Private LLM Inference
  44. NeurIPS 2025MR. Video: MapReduce as an Effective Principle for Long Video Understanding
  45. NeurIPS 2025MTBBench: A Multimodal Sequential Clinical Decision-Making Benchmark in Oncology
  46. NeurIPS 2025Multi-Agent Collaboration via Evolving Orchestration
  47. NeurIPS 2025Multi-Agent Debate for LLM Judges with Adaptive Stability Detection
  48. NeurIPS 2025Multi-Agent Imitation by Learning and Sampling from Factorized Soft Q-Function
  49. NeurIPS 2025Multi-agent KTO: Enhancing Strategic Interactions of Large Language Model in Language Game
  50. NeurIPS 2025Multi-Agent Learning under Uncertainty: Recurrence vs. Concentration

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