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 6 / 16 页

  1. ICML 2025Adaptive Self-improvement LLM Agentic System for ML Library Development
  2. ICML 2025AdvAgent: Controllable Blackbox Red-teaming on Web Agents
  3. ICML 2025Adversarial Robustness in Two-Stage Learning-to-Defer: Algorithms and Guarantees
  4. ICML 2025Agent Reviewers: Domain-specific Multimodal Agents with Shared Memory for Paper Review
  5. ICML 2025Agent Workflow Memory
  6. ICML 2025Agent-as-a-Judge: Evaluate Agents with Agents
  7. ICML 2025Agent-Centric Actor-Critic for Asynchronous Multi-Agent Reinforcement Learning
  8. ICML 2025Aguvis: Unified Pure Vision Agents for Autonomous GUI Interaction
  9. ICML 2025AI for Global Climate Cooperation: Modeling Global Climate Negotiations, Agreements, and Long-Term Cooperation in RICE-N
  10. ICML 2025Aligning LLMs by Predicting Preferences from User Writing Samples
  11. ICML 2025Are Large Language Models Ready for Multi-Turn Tabular Data Analysis?
  12. ICML 2025AssistanceZero: Scalably Solving Assistance Games
  13. ICML 2025AutoAdvExBench: Benchmarking Autonomous Exploitation of Adversarial Example Defenses
  14. ICML 2025Automated Benchmark Generation for Repository-Level Coding Tasks
  15. ICML 2025Automated Hypothesis Validation with Agentic Sequential Falsifications
  16. ICML 2025Automated Red Teaming with GOAT: the Generative Offensive Agent Tester
  17. ICML 2025AutoML-Agent: A Multi-Agent LLM Framework for Full-Pipeline AutoML
  18. ICML 2025Behavioral Exploration: Learning to Explore via In-Context Adaptation
  19. ICML 2025Benchmarking Abstract and Reasoning Abilities Through A Theoretical Perspective
  20. ICML 2025Boosting Virtual Agent Learning and Reasoning: A Step-Wise, Multi-Dimensional, and Generalist Reward Model with Benchmark
  21. ICML 2025Breaking the Curse of Multiagency in Robust Multi-Agent Reinforcement Learning
  22. ICML 2025BRIDGE: Bootstrapping Text to Control Time-Series Generation via Multi-Agent Iterative Optimization and Diffusion Modeling
  23. ICML 2025C-3PO: Compact Plug-and-Play Proxy Optimization to Achieve Human-like Retrieval-Augmented Generation
  24. ICML 2025Can Compressed LLMs Truly Act? An Empirical Evaluation of Agentic Capabilities in LLM Compression
  25. ICML 2025Closed-Loop Long-Horizon Robotic Planning via Equilibrium Sequence Modeling
  26. ICML 2025Code-Generated Graph Representations Using Multiple LLM Agents for Material Properties Prediction
  27. ICML 2025CogMath: Assessing LLMs' Authentic Mathematical Ability from a Human Cognitive Perspective
  28. ICML 2025Communicating Activations Between Language Model Agents
  29. ICML 2025Concurrent Reinforcement Learning with Aggregated States via Randomized Least Squares Value Iteration
  30. ICML 2025Continuously Updating Digital Twins using Large Language Models
  31. ICML 2025Convex Markov Games: A New Frontier for Multi-Agent Reinforcement Learning
  32. ICML 2025Counterfactual Effect Decomposition in Multi-Agent Sequential Decision Making
  33. ICML 2025Cowpox: Towards the Immunity of VLM-based Multi-Agent Systems
  34. ICML 2025Cradle: Empowering Foundation Agents towards General Computer Control
  35. ICML 2025Craftium: Bridging Flexibility and Efficiency for Rich 3D Single- and Multi-Agent Environments
  36. ICML 2025Cross-environment Cooperation Enables Zero-shot Multi-agent Coordination
  37. ICML 2025CVE-Bench: A Benchmark for AI Agents’ Ability to Exploit Real-World Web Application Vulnerabilities
  38. ICML 2025Decision Theoretic Foundations for Conformal Prediction: Optimal Uncertainty Quantification for Risk-Averse Agents
  39. ICML 2025Demystifying Cost-Efficiency in LLM Serving over Heterogeneous GPUs
  40. ICML 2025DipLLM: Fine-Tuning LLM for Strategic Decision-making in Diplomacy
  41. ICML 2025Distributionally Robust Multi-Agent Reinforcement Learning for Dynamic Chute Mapping
  42. ICML 2025Divide and Conquer: Grounding LLMs as Efficient Decision-Making Agents via Offline Hierarchical Reinforcement Learning
  43. ICML 2025Efficient Robotic Policy Learning via Latent Space Backward Planning
  44. ICML 2025EmbodiedBench: Comprehensive Benchmarking Multi-modal Large Language Models for Vision-Driven Embodied Agents
  45. ICML 2025Enhancing Cooperative Multi-Agent Reinforcement Learning with State Modelling and Adversarial Exploration
  46. ICML 2025Enhancing Diversity In Parallel Agents: A Maximum State Entropy Exploration Story
  47. ICML 2025EnIGMA: Interactive Tools Substantially Assist LM Agents in Finding Security Vulnerabilities
  48. ICML 2025FACTER: Fairness-Aware Conformal Thresholding and Prompt Engineering for Enabling Fair LLM-Based Recommender Systems
  49. ICML 2025Fast Large Language Model Collaborative Decoding via Speculation
  50. ICML 2025Finite-Sample Convergence Bounds for Trust Region Policy Optimization in Mean Field Games

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