AI 智能体论文趋势 2023–2026

主要结论

• AI 智能体论文从 2023 年的 170 篇增长到 2026 年的 1,983 篇，三年间扩大到约 12 倍。
• NeurIPS 是发AI 智能体论文最多的会议，2023–2026 年共 1,317 篇，占四个会议总量的 40%。
• 交叉方向里涨得最快的是大模型基准：同时属于两个主题的论文从 2023 年的 1 篇增至 2026 年的 116 篇。
• 在「前沿系统」的 4 个主题里，它的 2026 年论文数排第 2；同组增长最快的世界模型是 11 倍，AI 智能体是 12 倍。

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

• NeurIPS 2026$\boldsymbol{f}$-OPD: Stabilizing Long-Horizon On-Policy Distillation with Freshness-Aware Control
• ICML 2026$\tau$-Knowledge: Evaluating Conversational Agents over Unstructured Knowledge
• ICLR 2026A Benchmark for Deep Information Synthesis
• CVPR 20263D-VCD Hallucination Mitigation in 3D-LLM Embodied Agents through Visual Contrastive
• NeurIPS 20254KAgent: Agentic Any Image to 4K Super-Resolution
• ICML 2025A Unified Approach to Routing and Cascading for LLMs
• ICLR 2025A Generalist Hanabi Agent
• CVPR 2025Collaborative Tree Search for Enhancing Embodied Multi-Agent Collaboration
• NeurIPS 2024AdaSociety: An Adaptive Environment with Social Structures for Multi-Agent Decision-Making
• ICML 2024A Human-Inspired Reading Agent with Gist Memory of Very Long Contexts
• ICLR 2024A Real-World WebAgent with Planning, Long Context Understanding, and Program Synthesis
• CVPR 2024Density-Adaptive Model Based on Motif Matrix for Multi-Agent Trajectory Prediction
• NeurIPS 2023AdaPlanner: Adaptive Planning from Feedback with Language Models
• ICML 2023A Game-Theoretic Framework for Managing Risk in Multi-Agent Systems
• ICLR 2023Achieving Near-Optimal Individual Regret & Low Communications in Multi-Agent Bandits
• CVPR 2023Behavioral Analysis of Vision-and-Language Navigation Agents
• NeurIPS 20262-Step Agent: How a Bayesian Decision Maker Learns from AI-Decision Support
• ICML 2026$\tau$-Voice: Benchmarking Full-Duplex Voice Agents on Real-World Domains
• ICLR 2026A Framework for Studying AI Agent Behavior: Evidence from Consumer Choice Experiments
• CVPR 2026A Multi-Agent Perception-Action Alliance for Efficient Long Video Reasoning

全部AI 智能体论文

共 784 篇，第 1 / 16 页

1. CVPR 2025Automated Generation of Challenging Multiple-Choice Questions for Vision Language Model Evaluation
2. CVPR 2025Closed-Loop Supervised Fine-Tuning of Tokenized Traffic Models
3. CVPR 2025Collaborative Tree Search for Enhancing Embodied Multi-Agent Collaboration
4. CVPR 2025ComfyBench: Benchmarking LLM-based Agents in ComfyUI for Autonomously Designing Collaborative AI Systems
5. CVPR 2025CoSDH: Communication-Efficient Collaborative Perception via Supply-Demand Awareness and Intermediate-Late Hybridization
6. CVPR 2025CroCoDL: Cross-device Collaborative Dataset for Localization
7. CVPR 2025Cross-Modal 3D Representation with Multi-View Images and Point Clouds
8. CVPR 2025Distilling Multi-modal Large Language Models for Autonomous Driving
9. CVPR 2025Ego4o: Egocentric Human Motion Capture and Understanding from Multi-Modal Input
10. CVPR 2025Enduring, Efficient and Robust Trajectory Prediction Attack in Autonomous Driving via Optimization-Driven Multi-Frame Perturbation Framework
11. CVPR 2025Enhancing Video-LLM Reasoning via Agent-of-Thoughts Distillation
12. CVPR 2025Feature4X: Bridging Any Monocular Video to 4D Agentic AI with Versatile Gaussian Feature Fields
13. CVPR 2025FilmComposer: LLM-Driven Music Production for Silent Film Clips
14. CVPR 2025From Multimodal LLMs to Generalist Embodied Agents: Methods and Lessons
15. CVPR 2025Generative Map Priors for Collaborative BEV Semantic Segmentation
16. CVPR 2025GUI-Xplore: Empowering Generalizable GUI Agents with One Exploration
17. CVPR 2025Imputation-free and Alignment-free: Incomplete Multi-view Clustering Driven by Consensus Semantic Learning
18. CVPR 2025Insight-V: Exploring Long-Chain Visual Reasoning with Multimodal Large Language Models
19. CVPR 2025Learning to Detect Objects from Multi-Agent LiDAR Scans without Manual Labels
20. CVPR 2025LLM-driven Multimodal and Multi-Identity Listening Head Generation
21. CVPR 2025MAC-Ego3D: Multi-Agent Gaussian Consensus for Real-Time Collaborative Ego-Motion and Photorealistic 3D Reconstruction
22. CVPR 2025MAGiC-SLAM: Multi-Agent Gaussian Globally Consistent SLAM
23. CVPR 2025Magma: A Foundation Model for Multimodal AI Agents
24. CVPR 2025MCCD: Multi-Agent Collaboration-based Compositional Diffusion for Complex Text-to-Image Generation
25. CVPR 2025MNE-SLAM: Multi-Agent Neural SLAM for Mobile Robots
26. CVPR 2025NADER: Neural Architecture Design via Multi-Agent Collaboration
27. CVPR 2025OmniDrive: A Holistic Vision-Language Dataset for Autonomous Driving with Counterfactual Reasoning
28. CVPR 2025One-Step Event-Driven High-Speed Autofocus
29. CVPR 2025Poly-Autoregressive Prediction for Modeling Interactions
30. CVPR 2025Reasoning in Visual Navigation of End-to-end Trained Agents: A Dynamical Systems Approach
31. CVPR 2025Sim-to-Real Causal Transfer: A Metric Learning Approach to Causally-Aware Interaction Representations
32. CVPR 2025Sketchtopia: A Dataset and Foundational Agents for Benchmarking Asynchronous Multimodal Communication with Iconic Feedback
33. CVPR 2025SocialMOIF: Multi-Order Intention Fusion for Pedestrian Trajectory Prediction
34. CVPR 2025SpiritSight Agent: Advanced GUI Agent with One Look
35. CVPR 2025TANGO: Training-free Embodied AI Agents for Open-world Tasks
36. CVPR 2025TraF-Align: Trajectory-aware Feature Alignment for Asynchronous Multi-agent Perception
37. CVPR 2025Unified Uncertainty-Aware Diffusion for Multi-Agent Trajectory Modeling
38. CVPR 2025V-Stylist: Video Stylization via Collaboration and Reflection of MLLM Agents
39. CVPR 2025VideoRefer Suite: Advancing Spatial-Temporal Object Understanding with Video LLM
40. CVPR 2025Visual Agentic AI for Spatial Reasoning with a Dynamic API
41. ICLR 2025A Generalist Hanabi Agent
42. ICLR 2025A Policy-Gradient Approach to Solving Imperfect-Information Games with Best-Iterate Convergence
43. ICLR 2025ACC-Collab: An Actor-Critic Approach to Multi-Agent LLM Collaboration
44. ICLR 2025Active Task Disambiguation with LLMs
45. ICLR 2025Advantage Alignment Algorithms
46. ICLR 2025AFlow: Automating Agentic Workflow Generation
47. ICLR 2025Agent S: An Open Agentic Framework that Uses Computers Like a Human
48. ICLR 2025Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents
49. ICLR 2025Agent-Oriented Planning in Multi-Agent Systems
50. ICLR 2025AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents

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。