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
- 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。
各会议论文数
按年份和会议统计
| 年份 | NeurIPS | ICLR | ICML | CVPR | 合计 |
|---|---|---|---|---|---|
| 2023 | 76 | 40 | 41 | 13 | 170 |
| 2024 | 150 | 73 | 88 | 18 | 329 |
| 2025 | 362 | 204 | 178 | 40 | 784 |
| 2026 | 729 | 500 | 640 | 114 | 1,983 |
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
- 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 3,266 篇，第 41 / 66 页
- CVPR 2025Insight-V: Exploring Long-Chain Visual Reasoning with Multimodal Large Language Models
- CVPR 2025Learning to Detect Objects from Multi-Agent LiDAR Scans without Manual Labels
- CVPR 2025LLM-driven Multimodal and Multi-Identity Listening Head Generation
- CVPR 2025MAC-Ego3D: Multi-Agent Gaussian Consensus for Real-Time Collaborative Ego-Motion and Photorealistic 3D Reconstruction
- CVPR 2025MAGiC-SLAM: Multi-Agent Gaussian Globally Consistent SLAM
- CVPR 2025Magma: A Foundation Model for Multimodal AI Agents
- CVPR 2025MCCD: Multi-Agent Collaboration-based Compositional Diffusion for Complex Text-to-Image Generation
- CVPR 2025MNE-SLAM: Multi-Agent Neural SLAM for Mobile Robots
- CVPR 2025NADER: Neural Architecture Design via Multi-Agent Collaboration
- CVPR 2025OmniDrive: A Holistic Vision-Language Dataset for Autonomous Driving with Counterfactual Reasoning
- CVPR 2025One-Step Event-Driven High-Speed Autofocus
- CVPR 2025Poly-Autoregressive Prediction for Modeling Interactions
- CVPR 2025Reasoning in Visual Navigation of End-to-end Trained Agents: A Dynamical Systems Approach
- CVPR 2025Sim-to-Real Causal Transfer: A Metric Learning Approach to Causally-Aware Interaction Representations
- CVPR 2025Sketchtopia: A Dataset and Foundational Agents for Benchmarking Asynchronous Multimodal Communication with Iconic Feedback
- CVPR 2025SocialMOIF: Multi-Order Intention Fusion for Pedestrian Trajectory Prediction
- CVPR 2025SpiritSight Agent: Advanced GUI Agent with One Look
- CVPR 2025TANGO: Training-free Embodied AI Agents for Open-world Tasks
- CVPR 2025TraF-Align: Trajectory-aware Feature Alignment for Asynchronous Multi-agent Perception
- CVPR 2025Unified Uncertainty-Aware Diffusion for Multi-Agent Trajectory Modeling
- CVPR 2025V-Stylist: Video Stylization via Collaboration and Reflection of MLLM Agents
- CVPR 2025VideoRefer Suite: Advancing Spatial-Temporal Object Understanding with Video LLM
- CVPR 2025Visual Agentic AI for Spatial Reasoning with a Dynamic API
- ICLR 2025A Generalist Hanabi Agent
- ICLR 2025A Policy-Gradient Approach to Solving Imperfect-Information Games with Best-Iterate Convergence
- ICLR 2025ACC-Collab: An Actor-Critic Approach to Multi-Agent LLM Collaboration
- ICLR 2025Active Task Disambiguation with LLMs
- ICLR 2025Advantage Alignment Algorithms
- ICLR 2025AFlow: Automating Agentic Workflow Generation
- ICLR 2025Agent S: An Open Agentic Framework that Uses Computers Like a Human
- ICLR 2025Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents
- ICLR 2025Agent-Oriented Planning in Multi-Agent Systems
- ICLR 2025AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents
- ICLR 2025AgentOccam: A Simple Yet Strong Baseline for LLM-Based Web Agents
- ICLR 2025AgentRefine: Enhancing Agent Generalization through Refinement Tuning
- ICLR 2025Agents' Room: Narrative Generation through Multi-step Collaboration
- ICLR 2025AgentSquare: Automatic LLM Agent Search in Modular Design Space
- ICLR 2025AgentStudio: A Toolkit for Building General Virtual Agents
- ICLR 2025AgentTrek: Agent Trajectory Synthesis via Guiding Replay with Web Tutorials
- ICLR 2025Aligned LLMs Are Not Aligned Browser Agents
- ICLR 2025Aligning Generative Denoising with Discriminative Objectives Unleashes Diffusion for Visual Perception
- ICLR 2025An Intelligent Agentic System for Complex Image Restoration Problems
- ICLR 2025AndroidWorld: A Dynamic Benchmarking Environment for Autonomous Agents
- ICLR 2025Anyprefer: An Agentic Framework for Preference Data Synthesis
- ICLR 2025Audio Large Language Models Can Be Descriptive Speech Quality Evaluators
- ICLR 2025AutoDAN-Turbo: A Lifelong Agent for Strategy Self-Exploration to Jailbreak LLMs
- ICLR 2025Automated Design of Agentic Systems
- ICLR 2025BadRobot: Jailbreaking Embodied LLM Agents in the Physical World
- ICLR 2025Balancing Act: Diversity and Consistency in Large Language Model Ensembles
- ICLR 2025BALROG: Benchmarking Agentic LLM and VLM Reasoning On Games
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"}
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。