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 28 / 66 页

  1. NeurIPS 2026Benchmarking Open-Ended Multi-Agent Coordination in Language Agents
  2. NeurIPS 2026Beyond Domains: Reusing Web Skills via Transferable Interaction Patterns
  3. NeurIPS 2026Beyond DSA: Conjugacy-based Comparison of Dynamical Systems
  4. NeurIPS 2026Beyond High and Low: Evaluating Graded Cognitive Diversity in LLM Persona Simulations
  5. NeurIPS 2026Beyond IPS: Reliable Counterfactual Evaluation in Multi-Stage Ad Systems without Logged Propensities
  6. NeurIPS 2026Beyond Prediction: Steering VLM Agents with Retrospective World Modeling
  7. NeurIPS 2026Beyond Semantic Similarity: Rethinking Retrieval for Agentic Search via Direct Corpus Interaction
  8. NeurIPS 2026Beyond Suspicious Steps: Ontological Trust in Long-Horizon Agents
  9. NeurIPS 2026Beyond Task Success: Probing Cognitive Primitives in Web Agents
  10. NeurIPS 2026Beyond Training Time, Test-Time Coordination is Essential for Cooperative MARL
  11. NeurIPS 2026Beyond Truthfulness: Evaluating Honesty in Large Language Models
  12. NeurIPS 2026Bian Que: An Agentic Framework with Flexible Skill Arrangement for Online System Operations
  13. NeurIPS 2026BiasTrojan: LLM Judgers Are Easily Distorted by Few Hundreds of Contrastive Biased Training Data
  14. NeurIPS 2026BioMicroAgents: A Co-evolutionary Multi-Agent Framework for High-Fidelity Biomicroscopy Imaging
  15. NeurIPS 2026BioXArena: Benchmarking LLM Agents on Multi-Modal Biomedical Machine Learning Tasks
  16. NeurIPS 2026BIRD-RL: Scaling Agentic Reinforcement Learning over Stateful Data-Centric Environments
  17. NeurIPS 2026Bits Beat Tokens: A Regret Rate Distortion Theory for Large Language Model Agents
  18. NeurIPS 2026BlenderFORGE: Framework for Optimizing Reactive 3D-Graphics Editing Ability of MLLMs
  19. NeurIPS 2026BootstrapAgent: Turning Repository Setup into Reusable Agent Knowledge
  20. NeurIPS 2026Boundary-Induced Forgetting in Large Language Model Tool Chains: Measuring Field-Routing Failures
  21. NeurIPS 2026Breadcrumbing Search Agents: Per-Turn Scheming Over Long-Horizon Trajectories
  22. NeurIPS 2026Bridging Modalities, Spanning Time: Structured Memory for Ultra-Long Agentic Video Reasoning
  23. NeurIPS 2026Bridging Simulation and Reality: Geometry and Decision Alignment for Autonomous Driving
  24. NeurIPS 2026Build-and-Find: An Effort-Aware Protocol for Evaluating Agent-Managed Codebases
  25. NeurIPS 2026CAFE: Causally-Guided Automated Feature Engineering with Multi-Agent Reinforcement Learning
  26. NeurIPS 2026Calibration Is Not Control: Intervention Advantage for LLM-Agent Oversight
  27. NeurIPS 2026CaMeLs Can Use Computers Too: System-level Security for Computer Use Agents
  28. NeurIPS 2026Can Agents Price a Reaction? Evaluating LLMs on Chemical Cost Reasoning
  29. NeurIPS 2026Can AI Agents Synthesize Scientific Conclusions?
  30. NeurIPS 2026Can LLM Agents Respond to Disasters? Benchmarking Heterogeneous Geospatial Reasoning in Emergency Operations
  31. NeurIPS 2026CANDO: Cooperative Agentic Network for Layout Design Optimization
  32. NeurIPS 2026Capturing LLM Capabilities via Evidence-Calibrated Query Clustering
  33. NeurIPS 2026CARD: Internalizing Expert Critique into Reinforcement Learning for Deep Search
  34. NeurIPS 2026CASPIAN: Online Detection and Attribution of Cascade Attacks in LLM Multi-Agent Systems via Cross-Channel Causal Monitoring
  35. NeurIPS 2026Causal Effects with Unobserved Unit Types in Interacting Human–AI Systems
  36. NeurIPS 2026CEO-Bench: Can Agents Play the Long Game?
  37. NeurIPS 2026Chain-of-Route: State-Aware LLM Routing for Multi-Turn Conversations
  38. NeurIPS 2026CHAIN: Continual Heterogeneous Cooperation with Information Bottleneck for Multi-Agent Reinforcement Learning
  39. NeurIPS 2026Cheap Talk, Real Stakes: Commitment and Exploitation in Human-LLM Strategic Interaction
  40. NeurIPS 2026Choosing Before Acting: Comparative Value Estimation for Long-Horizon Tool-Use Agents
  41. NeurIPS 2026CivBench: A Long-Horizon Benchmark for Tool-Mediated Agents in Civilization VI
  42. NeurIPS 2026Claude Coke: Prevent Automated Crime by Agents
  43. NeurIPS 2026CLIOPATRA: Extracting Private Information from LLM Insights
  44. NeurIPS 2026CME–SpectrumBench: Can LLMs Analyze Condensed Matter Spectral Data?
  45. NeurIPS 2026CoE-Agent: Co-Evolving Patient-Doctor Agents via Interactive Policy Graph Optimization for Clinical Decision Making
  46. NeurIPS 2026CoffeeBench: A Benchmark for Long-Horizon Strategic Decision-Making in Multi-Agent Economies
  47. NeurIPS 2026Conditional Multi-Event Temporal Grounding in Long-Form Video
  48. NeurIPS 2026Conformal Agent Error Attribution
  49. NeurIPS 2026Consumer Search and Social Learning in Agentic Markets
  50. NeurIPS 2026Continual Learning Bench: Evaluating Frontier AI Systems in Real-World Stateful Environments

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