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 1,317 篇，第 7 / 27 页

  1. NeurIPS 2026How Do Agentic LLMs Decide to Call Tools? A Scaffold Default Controlled by Suppression
  2. NeurIPS 2026How Does Personalized Memory Shape LLM Behavior? Benchmarking Rational Preference Utilization in Personalized Assistants
  3. NeurIPS 2026How Likely Are Voting Rules Equitable?
  4. NeurIPS 2026How LLMs Distinguish Threats from Offers
  5. NeurIPS 2026How to Interpret Agent Behavior
  6. NeurIPS 2026How to Train a Surgeon? Benchmarking Generalist Agents in Surgical Scene Understanding
  7. NeurIPS 2026How Useful Is Cross-Domain Generalization for Training LLM Monitors?
  8. NeurIPS 2026HSCO-Bench: An Agent-Driven End-to-End Hardware-Software Co-design Benchmark for Systems-on-Chip
  9. NeurIPS 2026Hyperagents
  10. NeurIPS 2026I-PTC: Interactive Programmatic Tool Calling for Stateful Tool-Augmented Agents
  11. NeurIPS 2026Improving LLM Final Representations with Inter-Layer Geometry
  12. NeurIPS 2026Improving the Efficiency of Language Agent Teams with Adaptive Task Graphs
  13. NeurIPS 2026Inadvertent Context Leakage in Language Models
  14. NeurIPS 2026Incentivizing Agentic Retrieval for Disease-Centric Clinical Case Search via Trajectory Memory
  15. NeurIPS 2026Independent Learning of Nash Equilibria in Partially Observable Markov Potential Games with Decoupled Dynamics
  16. NeurIPS 2026Inductive Deductive Synthesis: Enabling AI to Generate Formally Verified Systems
  17. NeurIPS 2026Inferential Theory of Learning as a Framework for Test-Time Computation in Foundation Models
  18. NeurIPS 2026Instrumental Choices: Measuring the Propensity of LLM Agents to Pursue Instrumental Behaviors
  19. NeurIPS 2026Integrating Strengths of Different Multi-Agent Workflows via Step-Aware Hybrid Topology Planning
  20. NeurIPS 2026Inter-Agent Influence: Evaluating Persuasion, Deception and Coercion in Multi-Agent Systems
  21. NeurIPS 2026InterLV-Search: Benchmarking Interleaved Multimodal Agentic Search
  22. NeurIPS 2026InvestigationWorlds: An Agentic Environment for Legal Investigation
  23. NeurIPS 2026Is Agentic AI Ready for Real-World Hardware Engineering? A Deep Dive with Phoenix-bench
  24. NeurIPS 2026Is Your LLM-as-a-Recommender Agent Trustable? LLMs' Recommendation is Easily Hacked by Biases (Preferences)
  25. NeurIPS 2026It Takes Two: Complementary Self-Distillation for Contextual Integrity in LLMs
  26. NeurIPS 2026Iterative Critique-and-Routing Controller for Multi-Agent Systems with Heterogeneous LLMs
  27. NeurIPS 2026JARVIS-Bench: Benchmarking Personal Intelligence Agents on Long-Horizon Real-User Daily Traces
  28. NeurIPS 2026Jet-Long: Efficient Long-Context Extension with Dynamic Bifocal RoPE
  29. NeurIPS 2026Joint Optimization of Tool Creation and Use for Large Language Model Agents
  30. NeurIPS 2026Justitia: Fair and Efficient Scheduling of Task-parallel LLM Agents with Selective Pampering
  31. NeurIPS 2026KaliBench: A Fine-Grained Benchmark for Cybersecurity Tool Use on Kali Linux with Runtime-Free Verifiable Rewards
  32. NeurIPS 2026Know Where You Stand: Memory-Source Choice in Long-Context Dialogue Agents
  33. NeurIPS 2026Know Your Task, Learn It Right: Task-Aware Optimistic Value Learning for Multi-Task Multi-Agent Reinforcement Learning
  34. NeurIPS 2026KnowEvo: Knowledge Evolution for Protein Optimization
  35. NeurIPS 2026Knowing What is Missing: Efficient Conversational Memory via Explicit Evidence-Gap Tracking
  36. NeurIPS 2026KV-PRM: Efficient Process Reward Modeling via KV-Cache Transfer for Multi-Agent Test-Time Scaling
  37. NeurIPS 2026L$^2$EAP: Supercharging LLMs for Formal Mathematics with Agentic Frameworks
  38. NeurIPS 2026L2-Bench: An Evaluation Benchmark for Measuring LLM Capabilities in Second Language Education
  39. NeurIPS 2026Language-Based Agent Control
  40. NeurIPS 2026Large-Scale Pretraining unlocks Few-Shot Prediction for Relational Data
  41. NeurIPS 2026Latent-Lens: Visual Perception in Small Language Models Through Latent Communication
  42. NeurIPS 2026Learn Locally, Recurse Globally: Neural Circuit Synthesis Beyond Training Depth
  43. NeurIPS 2026Learning Agentic World Vision-Language-Action Models for Autonomous Driving
  44. NeurIPS 2026Learning CLI Agents with Structured Action Credit under Selective Observation
  45. NeurIPS 2026Learning Digital Twins under Drift: Optimal Tracking Rates for Non-Stationary Dynamical Systems
  46. NeurIPS 2026Learning in Causal Markov Games
  47. NeurIPS 2026Learning Large-Scale Competitive Team Behaviors with Mean-Field Interactions
  48. NeurIPS 2026Learning Orthogonal Multi-Index Models Beyond Small Initialization: Incremental Learning, Competitive Dynamics and Symmetry
  49. NeurIPS 2026Learning to Commit: Next-Commit Prediction via Online Supervised Contrastive Reflection
  50. NeurIPS 2026Learning to Persuade Exposes How Easily LLMs Abandon Correct Beliefs

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