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 1,983 篇，第 4 / 40 页

  1. ICLR 2026AnyBCQ: Hardware Efficient Flexible Binary-Coded Quantization for Multi-Precision LLMs
  2. ICLR 2026AstaBench: Rigorous Benchmarking of AI Agents with a Scientific Research Suite
  3. ICLR 2026ATLAS: Constraints-Aware Multi-Agent Collaboration for Real-World Travel Planning
  4. ICLR 2026Auditing Black-Box LLM APIs with a Rank-Based Uniformity Test
  5. ICLR 2026AutoFigure: Generating and Refining Publication-Ready Scientific Illustrations
  6. ICLR 2026AutoLibra: Agent Metric Induction from Open-Ended Human Feedback
  7. ICLR 2026Automated Stateful Specialization for Adaptive Agent Systems
  8. ICLR 2026AutoSP: Unlocking Long-Context LLM Training Via Compiler-Based Sequence Parallelism
  9. ICLR 2026Bayesian Robust Cooperative Multi-Agent Reinforcement Learning Against Unknown Adversaries
  10. ICLR 2026BEAT: Visual Backdoor Attacks on VLM-based Embodied Agents via Contrastive Trigger Learning
  11. ICLR 2026BED-LLM: Intelligent Information Gathering with LLMs and Bayesian Experimental Design
  12. ICLR 2026Benchmarking LLM Tool-Use in the Wild
  13. ICLR 2026Benchmarking Multi-Agent Reinforcement Learning in Power Grid Operations
  14. ICLR 2026Benefits and Limitations of Communication in Multi-Agent Reasoning
  15. ICLR 2026Beyond Magic Words: Sharpness-Aware Prompt Evolving for Robust Large Language Models with TARE
  16. ICLR 2026Beyond Prompt-Induced Lies: Investigating LLM Deception on Benign Prompts
  17. ICLR 2026Beyond URLs: Metadata Diversity and Position for Efficient LLM Pretraining
  18. ICLR 2026BiasBusters: Uncovering and Mitigating Tool Selection Bias in Large Language Models
  19. ICLR 2026BIRD-INTERACT: Re-imagining Text-to-SQL Evaluation via Lens of Dynamic Interactions
  20. ICLR 2026Breaking Agent Backbones: Evaluating the Security of Backbone LLMs in AI Agents
  21. ICLR 2026Breaking and Fixing Defenses Against Control Flow Hijacking in Multi-Agent Systems
  22. ICLR 2026BRIDGE: Bi-level Reinforcement Learning for Dynamic Group Structure in Coalition Formation Games
  23. ICLR 2026Building a Foundational Guardrail for General Agentic Systems via Synthetic Data
  24. ICLR 2026Cache-to-Cache: Direct Semantic Communication Between Large Language Models
  25. ICLR 2026Can Language Models Discover Scaling Laws?
  26. ICLR 2026Cancer-Myth: Evaluating Large Language Models on Patient Questions with False Presuppositions
  27. ICLR 2026CARD: Towards Conditional Design of Multi-agent Topological Structures
  28. ICLR 2026CARE: Towards Clinical Accountability in Multi-Modal Medical Reasoning with an Evidence-Grounded Agentic Framework
  29. ICLR 2026Catalog-Native LLM: Speaking Item-ID dialect with Less Entanglement for Recommendation
  30. ICLR 2026CellAgent: LLM-Driven Multi-Agent Framework for Natural Language-Based Single-Cell Analysis
  31. ICLR 2026CellDuality: Unlocking Biological Reasoning in LLMs with Self-Supervised RLVR
  32. ICLR 2026ChatInject: Abusing Chat Templates for Prompt Injection in LLM Agents
  33. ICLR 2026ChinaTravel: An Open-Ended Travel Planning Benchmark with Compositional Constraint Validation for Language Agents
  34. ICLR 2026CLAUSE: Agentic Neuro-Symbolic Knowledge Graph Reasoning via Dynamic Learnable Context Engineering
  35. ICLR 2026CoAct-1: Computer-using Multi-agent System with Coding Actions
  36. ICLR 2026CoDA: Agentic Systems for Collaborative Data Visualization
  37. ICLR 2026Collaborative Gym: A Framework for Enabling and Evaluating Human-Agent Collaboration
  38. ICLR 2026CoLLMLight: Cooperative Large Language Model Agents for Network-Wide Traffic Signal Control
  39. ICLR 2026CoMAS: Co-Evolving Multi-Agent Systems via Interaction Rewards
  40. ICLR 2026CoMind: Towards Community-Driven Agents for Machine Learning Engineering
  41. ICLR 2026Comparing AI Agents to Cybersecurity Professionals in Real-World Penetration Testing
  42. ICLR 2026Completing Missing Annotation: Multi-Agent Debate for Accurate and Scalable Relevant Assessment for IR Benchmarks
  43. ICLR 2026Computer Agent Arena: Toward Human-Centric Evaluation and Analysis of Computer-Use Agents
  44. ICLR 2026ComputerRL: Scaling End-to-End Online Reinforcement Learning for Computer Use Agents
  45. ICLR 2026CoNavBench: Collaborative Long-Horizon Vision-Language Navigation Benchmark
  46. ICLR 2026Context Learning for Multi-Agent Discussion
  47. ICLR 2026ContextNav: Towards Agentic Multimodal In-Context Learning
  48. ICLR 2026Continual Low-Rank Adapters for LLM-based Generative Recommender Systems
  49. ICLR 2026Continuous-Time Value Iteration for Multi-Agent Reinforcement Learning
  50. ICLR 2026Control Tax: The Price of Keeping AI in Check

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