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 9 / 16 页

  1. ICML 2025SyncMind: Measuring Agent Out-of-Sync Recovery in Collaborative Software Engineering
  2. ICML 2025Synthesizing Software Engineering Data in a Test-Driven Manner
  3. ICML 2025The Berkeley Function Calling Leaderboard (BFCL): From Tool Use to Agentic Evaluation of Large Language Models
  4. ICML 2025The Hidden Dimensions of LLM Alignment: A Multi-Dimensional Analysis of Orthogonal Safety Directions
  5. ICML 2025The Sample Complexity of Online Strategic Decision Making with Information Asymmetry and Knowledge Transportability
  6. ICML 2025The Synergy of LLMs & RL Unlocks Offline Learning of Generalizable Language-Conditioned Policies with Low-fidelity Data
  7. ICML 2025Tokenized Bandit for LLM Decoding and Alignment
  8. ICML 2025Tool Unlearning for Tool-Augmented LLMs
  9. ICML 2025Towards Efficient Online Tuning of VLM Agents via Counterfactual Soft Reinforcement Learning
  10. ICML 2025Towards Practical Defect-Focused Automated Code Review
  11. ICML 2025Training a Generally Curious Agent
  12. ICML 2025Training Software Engineering Agents and Verifiers with SWE-Gym
  13. ICML 2025UDora: A Unified Red Teaming Framework against LLM Agents by Dynamically Hijacking Their Own Reasoning
  14. ICML 2025UI-Vision: A Desktop-centric GUI Benchmark for Visual Perception and Interaction
  15. ICML 2025Unbiased Evaluation of Large Language Models from a Causal Perspective
  16. ICML 2025Understanding Bias Reinforcement in LLM Agents Debate
  17. ICML 2025UP-VLA: A Unified Understanding and Prediction Model for Embodied Agent
  18. ICML 2025What Limits Virtual Agent Application? OmniBench: A Scalable Multi-Dimensional Benchmark for Essential Virtual Agent Capabilities
  19. ICML 2025Which Agent Causes Task Failures and When? On Automated Failure Attribution of LLM Multi-Agent Systems
  20. ICML 2025Windows Agent Arena: Evaluating Multi-Modal OS Agents at Scale
  21. ICML 2025Wolfpack Adversarial Attack for Robust Multi-Agent Reinforcement Learning
  22. ICML 2025µnit Scaling: Simple and Scalable FP8 LLM Training
  23. NeurIPS 20253DLLM-Mem: Long-Term Spatial-Temporal Memory for Embodied 3D Large Language Model
  24. NeurIPS 20254KAgent: Agentic Any Image to 4K Super-Resolution
  25. NeurIPS 2025A machine learning approach that beats Rubik's cubes
  26. NeurIPS 2025A Near-optimal, Scalable and Parallelizable Framework for Stochastic Bandits Robust to Adversarial Corruptions and Beyond
  27. NeurIPS 2025A Principle of Targeted Intervention for Multi-Agent Reinforcement Learning
  28. NeurIPS 2025A-Mem: Agentic Memory for LLM Agents
  29. NeurIPS 2025Abstract Counterfactuals for Language Model Agents
  30. NeurIPS 2025AC-LoRA: (Almost) Training-Free Access Control Aware Multi-Modal LLMs
  31. NeurIPS 2025Adaptive Context Length Optimization with Low-Frequency Truncation for Multi-Agent Reinforcement Learning
  32. NeurIPS 2025Adaptive Preference Arithmetic: A Personalized Agent with Adaptive Preference Arithmetic for Dynamic Preference Modeling
  33. NeurIPS 2025Adaptively Coordinating with Novel Partners via Learned Latent Strategies
  34. NeurIPS 2025AGC-Drive: A Large-Scale Dataset for Real-World Aerial-Ground Collaboration in Driving Scenarios
  35. NeurIPS 2025AgentAuditor: Human-level Safety and Security Evaluation for LLM Agents
  36. NeurIPS 2025AgentBreeder: Mitigating the AI Safety Risks of Multi-Agent Scaffolds via Self-Improvement
  37. NeurIPS 2025AgentDAM: Privacy Leakage Evaluation for Autonomous Web Agents
  38. NeurIPS 2025Agentic Plan Caching: Test-Time Memory for Fast and Cost-Efficient LLM Agents
  39. NeurIPS 2025Agentic RL Scaling Law: Spontaneous Code Execution for Mathematical Problem Solving
  40. NeurIPS 2025AGENTIF: Benchmarking Large Language Models Instruction Following Ability in Agentic Scenarios
  41. NeurIPS 2025AgentNet: Decentralized Evolutionary Coordination for LLM-based Multi-Agent Systems
  42. NeurIPS 2025AgentRecBench: Benchmarking LLM Agent-based Personalized Recommender Systems
  43. NeurIPS 2025Agents Robust to Distribution Shifts Learn Causal World Models Even Under Mediation
  44. NeurIPS 2025AgentTTS: Large Language Model Agent for Test-time Compute-optimal Scaling Strategy in Complex Tasks
  45. NeurIPS 2025AI Research Agents for Machine Learning: Search, Exploration, and Generalization in MLE-bench
  46. NeurIPS 2025AI-Researcher: Autonomous Scientific Innovation
  47. NeurIPS 2025ALE-Bench: A Benchmark for Long-Horizon Objective-Driven Algorithm Engineering
  48. NeurIPS 2025Among Us: A Sandbox for Measuring and Detecting Agentic Deception
  49. NeurIPS 2025APIGen-MT: Agentic Pipeline for Multi-Turn Data Generation via Simulated Agent-Human Interplay
  50. NeurIPS 2025APOLLO: Automated LLM and Lean Collaboration for Advanced Formal Reasoning

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