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 65 / 66 页

  1. NeurIPS 2023BIRD: Generalizable Backdoor Detection and Removal for Deep Reinforcement Learning
  2. NeurIPS 2023Calibrated Stackelberg Games: Learning Optimal Commitments Against Calibrated Agents
  3. NeurIPS 2023CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society
  4. NeurIPS 2023Collaboratively Learning Linear Models with Structured Missing Data
  5. NeurIPS 2023Combinatorial Group Testing with Selfish Agents
  6. NeurIPS 2023Cross-Episodic Curriculum for Transformer Agents
  7. NeurIPS 2023De novo Drug Design using Reinforcement Learning with Multiple GPT Agents
  8. NeurIPS 2023Decentralized Randomly Distributed Multi-agent Multi-armed Bandit with Heterogeneous Rewards
  9. NeurIPS 2023Diverse Conventions for Human-AI Collaboration
  10. NeurIPS 2023Echoes Beyond Points: Unleashing the Power of Raw Radar Data in Multi-modality Fusion
  11. NeurIPS 2023Effective Human-AI Teams via Learned Natural Language Rules and Onboarding
  12. NeurIPS 2023Efficient Policy Adaptation with Contrastive Prompt Ensemble for Embodied Agents
  13. NeurIPS 2023Emergent Communication for Rules Reasoning
  14. NeurIPS 2023Emergent Communication in Interactive Sketch Question Answering
  15. NeurIPS 2023Explainable and Efficient Randomized Voting Rules
  16. NeurIPS 2023Exponential Lower Bounds for Fictitious Play in Potential Games
  17. NeurIPS 2023Fair Allocation of Indivisible Chores: Beyond Additive Costs
  18. NeurIPS 2023FIND: A Function Description Benchmark for Evaluating Interpretability Methods
  19. NeurIPS 2023Fine-Grained Cross-View Geo-Localization Using a Correlation-Aware Homography Estimator
  20. NeurIPS 2023Glance and Focus: Memory Prompting for Multi-Event Video Question Answering
  21. NeurIPS 2023Guarantees for Self-Play in Multiplayer Games via Polymatrix Decomposability
  22. NeurIPS 2023Hierarchical Multi-Agent Skill Discovery
  23. NeurIPS 2023Higher-Order Uncoupled Dynamics Do Not Lead to Nash Equilibrium - Except When They Do
  24. NeurIPS 2023History Filtering in Imperfect Information Games: Algorithms and Complexity
  25. NeurIPS 2023Hokoff: Real Game Dataset from Honor of Kings and its Offline Reinforcement Learning Benchmarks
  26. NeurIPS 2023Honesty Is the Best Policy: Defining and Mitigating AI Deception
  27. NeurIPS 2023How2comm: Communication-Efficient and Collaboration-Pragmatic Multi-Agent Perception
  28. NeurIPS 2023HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face
  29. NeurIPS 2023IMP-MARL: a Suite of Environments for Large-scale Infrastructure Management Planning via MARL
  30. NeurIPS 2023Intrinsic Dimension Estimation for Robust Detection of AI-Generated Texts
  31. NeurIPS 2023Large Language Models Are Semi-Parametric Reinforcement Learning Agents
  32. NeurIPS 2023Learning to Influence Human Behavior with Offline Reinforcement Learning
  33. NeurIPS 2023Lending Interaction Wings to Recommender Systems with Conversational Agents
  34. NeurIPS 2023MG-ViT: A Multi-Granularity Method for Compact and Efficient Vision Transformers
  35. NeurIPS 2023Mind2Web: Towards a Generalist Agent for the Web
  36. NeurIPS 2023Multi-Agent First Order Constrained Optimization in Policy Space
  37. NeurIPS 2023Multi-Agent Learning with Heterogeneous Linear Contextual Bandits
  38. NeurIPS 2023Natural Language Instruction-following with Task-related Language Development and Translation
  39. NeurIPS 2023OKRidge: Scalable Optimal k-Sparse Ridge Regression
  40. NeurIPS 2023OpenAGI: When LLM Meets Domain Experts
  41. NeurIPS 2023Optimal testing using combined test statistics across independent studies
  42. NeurIPS 2023Pgx: Hardware-Accelerated Parallel Game Simulators for Reinforcement Learning
  43. NeurIPS 2023Policy Space Diversity for Non-Transitive Games
  44. NeurIPS 2023Provably Fast Convergence of Independent Natural Policy Gradient for Markov Potential Games
  45. NeurIPS 2023Quantizable Transformers: Removing Outliers by Helping Attention Heads Do Nothing
  46. NeurIPS 2023Quantus: An Explainable AI Toolkit for Responsible Evaluation of Neural Network Explanations and Beyond
  47. NeurIPS 2023Responsible AI (RAI) Games and Ensembles
  48. NeurIPS 2023RiskQ: Risk-sensitive Multi-Agent Reinforcement Learning Value Factorization
  49. NeurIPS 2023Robust Multi-Agent Reinforcement Learning via Adversarial Regularization: Theoretical Foundation and Stable Algorithms
  50. NeurIPS 2023ScenarioNet: Open-Source Platform for Large-Scale Traffic Scenario Simulation and Modeling

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