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 30 / 40 页

  1. NeurIPS 2026Economy of Minds: Emerging Multi-Agent Intelligence with Economic Interactions
  2. NeurIPS 2026Effective Knowledge Conflict Detection via Joint Agentic Optimization
  3. NeurIPS 2026Efficient evaluation and error pattern discovery for blackbox AI systems
  4. NeurIPS 2026Efficient Serving for Dynamic Agent Workflows with Prediction-based KV-Cache Management
  5. NeurIPS 2026EfficientRollout: System-Aware Self-Speculative Decoding for RL Rollouts
  6. NeurIPS 2026EgoBench: An Interactive Egocentric Multimodal Benchmark for Tool-Using Agents
  7. NeurIPS 2026Embedded-Arena: Building Hardware-in-the-Loop Coding Agents to Run AI on Microcontrollers
  8. NeurIPS 2026Empirical Bayes Rebiasing
  9. NeurIPS 2026EngramState: Loadable Tool Priors for Efficient Function Calling
  10. NeurIPS 2026Enhancing Agentic Code Localization with Traceability Recovered from Repository Evolution
  11. NeurIPS 2026Entropy Dynamics of Agent Reinforcement Learning
  12. NeurIPS 2026Epistemic Pairwise Maximin Share
  13. NeurIPS 2026Epistemic Social Learning: Latent Behavioral Structure under Endogenous Multi-Agent Interaction
  14. NeurIPS 2026Ergodic Trajectory Design by Learned Pushforward Maps: Provable Coverage via Conditional Flow Matching
  15. NeurIPS 2026EVA: Evidence-seeking Visual Agent for Hallucination-Resistant Multimodal Reasoning
  16. NeurIPS 2026Evaluating Physical Reasoning in LLM Agents Requires Construction Benchmarks
  17. NeurIPS 2026Evaluating Test-Time Scaling of General LLM Agents
  18. NeurIPS 2026Every Bit, Everywhere, All At Once: A Binomial Multibit LLM Watermark
  19. NeurIPS 2026EVOCHAMBER: Test-Time Co-evolution of Multi-Agent System at Individual, Team, and Population Scales
  20. NeurIPS 2026EvoCodeBench: Evaluating Coding Agents in Multi-Turn Iterative Interactions
  21. NeurIPS 2026EvoCUA: Evolving Computer Use Agents via Learning from Scalable Synthetic Experience
  22. NeurIPS 2026EvoDiagram: Agentic Editable Diagram Creation via Design Expertise Evolution
  23. NeurIPS 2026EvoInspect: A Unified Self-Evolving Multi-Agent Framework for Industrial Hardware Inspection
  24. NeurIPS 2026Evolutionary System Prompt Learning for Reinforcement Learning in LLMs
  25. NeurIPS 2026EvoMemBench: Benchmarking Agent Memory from a Self-Evolving Perspective
  26. NeurIPS 2026EvoMM: Reinforced Self-Evolving Multimodal Agentic Memory
  27. NeurIPS 2026EvoOptiGraph: Weakness-Driven Coevolution via Graph-Based Structural Generation for Optimization Modeling
  28. NeurIPS 2026ExComm: Exploration-Stage Communication for Error-Resilient Agentic Test-Time Scaling
  29. NeurIPS 2026Exemplar2VQA: A Scalable Exemplar-Driven Visual Question Answering Generation Framework via Multi-Agent Coding
  30. NeurIPS 2026Expanding LLM Agent Boundaries with Strategy-Guided Exploration
  31. NeurIPS 2026Explanations over Graphs: An Agent Architecture for IT Enterprise Diagnostic Tasks
  32. NeurIPS 2026ExploitGym: Can AI Agents Turn Security Vulnerabilities into Real Attacks?
  33. NeurIPS 2026Extrapolative Weight Averaging Reveals Correctness–Efficiency Frontiers in Code RL
  34. NeurIPS 2026Fair Division of Work in Collaborative Mean Estimation via Bargaining
  35. NeurIPS 2026FASD: Hardware Acceleration for Multi-AI-Agent Discussion
  36. NeurIPS 2026Fast KVzip: Efficient and Accurate LLM Inference with Gated KV Eviction
  37. NeurIPS 2026FedProG: Federated Graph Learning via Server-Side LLM Semantic Bridging and Uncertainty-Aware Distillation
  38. NeurIPS 2026FEP-Agent: Grounding LLM Agent Self-Evolution in Active Inference with Semantic Memory
  39. NeurIPS 2026Fine-Grained Benchmark Generation for Comprehensive Evaluation of Foundation Models
  40. NeurIPS 2026Fingerprinting Inference Systems of Large Language Models
  41. NeurIPS 2026Finite-Sample Convergence in Networked Average Reward MARL: Decentralization Pitfalls and Entropy Remedies
  42. NeurIPS 2026FinReasoning: A Hierarchical Benchmark for Reliable Financial Research Reporting
  43. NeurIPS 2026Fisher-R1: Training LLM Agents for Reliable Hypothesis Testing
  44. NeurIPS 2026Fix the Structural Bottleneck: Context Compression via Explicit Information Transmission
  45. NeurIPS 2026FLARE: Verifying MILP Reformulations with LLM-Based Formal Proof Synthesis
  46. NeurIPS 2026FlashEvolve: Accelerating Agent Self-Evolution with Asynchronous Stage Orchestration
  47. NeurIPS 2026Flow Matching for Offline Reinforcement Learning with Discrete Actions
  48. NeurIPS 2026FlowLeak: Coverage-Guided Extraction of Dynamic Workflows in LLM-Based Multi-Agent Systems
  49. NeurIPS 2026FlowSteer: Prompt-Only Workflow Steering Exposes Planning-Time Vulnerabilities in Multi-Agent LLM Systems
  50. NeurIPS 2026FlowSteer: Towards Agents Designing Agentic Workflows via Reinforced Progressive Canvas Editing

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