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 4 / 8 页

  1. NeurIPS 2025InterMT: Multi-Turn Interleaved Preference Alignment with Human Feedback
  2. NeurIPS 2025IR3D-Bench: Evaluating Vision-Language Model Scene Understanding as Agentic Inverse Rendering
  3. NeurIPS 2025Iterative Self-Incentivization Empowers Large Language Models as Agentic Searchers
  4. NeurIPS 2025Iterative Tool Usage Exploration for Multimodal Agents via Step-wise Preference Tuning
  5. NeurIPS 2025JarvisArt: Liberating Human Artistic Creativity via an Intelligent Photo Retouching Agent
  6. NeurIPS 2025KARMA: Leveraging Multi-Agent LLMs for Automated Knowledge Graph Enrichment
  7. NeurIPS 2025Keeping an Eye on LLM Unlearning: The Hidden Risk and Remedy
  8. NeurIPS 2025Kinaema: a recurrent sequence model for memory and pose in motion
  9. NeurIPS 2025Knowledge Starts with Practice: Knowledge-Aware Exercise Generative Recommendation with Adaptive Multi-Agent Cooperation
  10. NeurIPS 2025KVCOMM: Online Cross-context KV-cache Communication for Efficient LLM-based Multi-agent Systems
  11. NeurIPS 2025KVFlow: Efficient Prefix Caching for Accelerating LLM-Based Multi-Agent Workflows
  12. NeurIPS 2025LabUtopia: High-Fidelity Simulation and Hierarchical Benchmark for Scientific Embodied Agents
  13. NeurIPS 2025Language Modeling by Language Models
  14. NeurIPS 2025Language Models can Self-Improve at State-Value Estimation for Better Search
  15. NeurIPS 2025Language Ranker: A Lightweight Ranking framework for LLM Decoding
  16. NeurIPS 2025Large Language Models Miss the Multi-agent Mark
  17. NeurIPS 2025LARGO: Latent Adversarial Reflection through Gradient Optimization for Jailbreaking LLMs
  18. NeurIPS 2025LayerCraft: Enhancing Text-to-Image Generation with CoT Reasoning and Layered Object Integration
  19. NeurIPS 2025LC-Opt: Benchmarking Reinforcement Learning and Agentic AI for End-to-End Liquid Cooling Optimization in Data Centers
  20. NeurIPS 2025Learning “Partner-Aware” Collaborators in Multi-Party Collaboration
  21. NeurIPS 2025Learning and Planning Multi-Agent Tasks via an MoE-based World Model
  22. NeurIPS 2025Learning Equilibria from Data: Provably Efficient Multi-Agent Imitation Learning
  23. NeurIPS 2025Learning in Stackelberg Mean Field Games: A Non-Asymptotic Analysis
  24. NeurIPS 2025Learning Individual Behavior in Agent-Based Models with Graph Diffusion Networks
  25. NeurIPS 2025Learning to Control Free-Form Soft Swimmers
  26. NeurIPS 2025Learning to Watermark: A Selective Watermarking Framework for Large Language Models via Multi-Objective Optimization
  27. NeurIPS 2025Lessons Learned: A Multi-Agent Framework for Code LLMs to Learn and Improve
  28. NeurIPS 2025Let the LLM Stick to Its Strengths: Learning to Route Economical LLM
  29. NeurIPS 2025LILO: Learning to Reason at the Frontier of Learnability
  30. NeurIPS 2025LLM Generated Persona is a Promise with a Catch
  31. NeurIPS 2025LLM Meeting Decision Trees on Tabular Data
  32. NeurIPS 2025LLM Query Scheduling with Prefix Reuse and Latency Constraints
  33. NeurIPS 2025LLM Strategic Reasoning: Agentic Study through Behavioral Game Theory
  34. NeurIPS 2025LLM Unlearning via Neural Activation Redirection
  35. NeurIPS 2025LLM-DAMVC: A Large Language Model Assisted Dynamic Agent for Multi-View Clustering
  36. NeurIPS 2025LLM-PySC2: Starcraft II learning environment for Large Language Models
  37. NeurIPS 2025Look Before You Leap: A GUI-Critic-R1 Model for Pre-Operative Error Diagnosis in GUI Automation
  38. NeurIPS 2025LOPT: Learning Optimal Pigovian Tax in Sequential Social Dilemmas
  39. NeurIPS 2025macOSWorld: A Multilingual Interactive Benchmark for GUI Agents
  40. NeurIPS 2025MACS: Multi-Agent Reinforcement Learning for Optimization of Crystal Structures
  41. NeurIPS 2025MAGNET: A Multi-agent Framework for Finding Audio-Visual Needles by Reasoning over Multi-Video Haystacks
  42. NeurIPS 2025MaintainCoder: Maintainable Code Generation Under Dynamic Requirements
  43. NeurIPS 2025MALinZero: Efficient Low-Dimensional Search for Mastering Complex Multi-Agent Planning
  44. NeurIPS 2025Many LLMs Are More Utilitarian Than One
  45. NeurIPS 2025Many Minds, One Goal: Time Series Forecasting via Sub-task Specialization and Inter-agent Cooperation
  46. NeurIPS 2025MASTER: Enhancing Large Language Model via Multi-Agent Simulated Teaching
  47. NeurIPS 2025MAT-Agent: Adaptive Multi-Agent Training Optimization
  48. NeurIPS 2025Mean-Field Sampling for Cooperative Multi-Agent Reinforcement Learning
  49. NeurIPS 2025Measuring Scientific Capabilities of Language Models with a Systems Biology Dry Lab
  50. NeurIPS 2025Mechanism Design via the Interim Relaxation

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