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 1,983 篇，第 2 / 40 页

51. CVPR 2026MangoBench A Benchmark for Multi-Agent Goal-Conditioned Offline Reinforcement Learning
52. CVPR 2026MeanFuser Fast One-Step Multi-Modal Trajectory Generation and Adaptive Reconstruction via
53. CVPR 2026MMBench-GUI A Unified Hierarchical Evaluation Framework for Multi-Platform GUI Agents
54. CVPR 2026MoReGen Multi-Agent Motion-Reasoning Engine for Code-based Text-to-Video Synthesis
55. CVPR 2026NERFIFY A Multi-Agent Framework for Turning NeRF Papers into Code
56. CVPR 2026NitroGen An Open Foundation Model for Generalist Gaming Agents
57. CVPR 2026OctoT2I A Self-Evolving Agentic Text-to-Image Router
58. CVPR 2026Omni2Sound Towards Unified Video-Text-to-Audio Generation
59. CVPR 2026Open-Ended Instruction Realization with LLM-Enabled Multi-Planner Scheduling in Autonomous Vehicles
60. CVPR 2026OralGPT-Plus Learning to Use Visual Tools via Reinforcement Learning for
61. CVPR 2026Paper2Figure A Multi-Agent Collaborative System for Figure Generation Towards Academic
62. CVPR 2026Pixel2Phys Distilling Governing Laws from Visual Dynamics
63. CVPR 2026ProSoftArena Benchmarking Hierarchical Capabilities of Multi-modal Agents in Professional Software
64. CVPR 2026PTC-Depth Pose-Refined Monocular Depth Estimation with Temporal Consistency
65. CVPR 2026PureProof Diffusion-Resistant Black-box Targeted Attack on Large Vision-Language Models
66. CVPR 2026RAAS LLM Agentic System Architecture Search with GRPO
67. CVPR 2026ReFAct Empowering Multimodal Web Agents with Visual and Context Focusing
68. CVPR 2026RefAV Towards Planning-Centric Scenario Mining
69. CVPR 2026Refer-Agent A Collaborative Multi-Agent System with Reasoning and Reflection for
70. CVPR 2026Resolving Evidence Sparsity Agentic Context Engineering for Long-Document Understanding
71. CVPR 2026RLFTSim Realistic and Controllable Multi-Agent Traffic Simulation via Reinforcement Learning
72. CVPR 2026SAGE Scalable Agentic 3D Scene Generation for Embodied AI
73. CVPR 2026Scaling Agentic Reinforcement Learning for Tool-Integrated Reasoning in VLMs
74. CVPR 2026SciEducator Scientific Video Understanding and Educating via Deming-Cycle Multi-Agent System
75. CVPR 2026See Think Act Teaching Multimodal Agents to Effectively Interact with
76. CVPR 2026SenseSearch Empowering Vision-Language Models with High-Resolution Agentic Search-Reasoning via Reinforcement
77. CVPR 2026SHARP Short-Window Streaming for Accurate and Robust Prediction in Motion
78. CVPR 2026Simple Agents Outperform Experts in Biomedical Imaging Workflow Optimization
79. CVPR 2026SO-Bench A Structural Output Evaluation of Multimodal LLM
80. CVPR 2026Socratic-Geo Synthetic Data Generation and Cross-Modal Geometric Reasoning via Multi-Agent
81. CVPR 2026SpaceTools Tool-Augmented Spatial Reasoning via Double Interactive RL
82. CVPR 2026SpatialScore Towards Comprehensive Evaluation for Spatial Intelligence
83. CVPR 2026SpatialTree How Spatial Intelligence Branches Out in MLLMs
84. CVPR 2026SVAgent Storyline-guided Long Video Understanding via Cross-Modal Multi-Agent Collaboration
85. CVPR 2026SVBench Evaluation of Video Generation Models on Social Reasoning
86. CVPR 2026Symphony A Cognitively-Inspired Multi-Agent System for Long-Video Understanding
87. CVPR 2026SyncMos Scalable Motion Synchronisation for Multi-Agent Scene Interaction
88. CVPR 2026Tackling Model Bias via Game-theoretic Multi-agent Collaboration Framework for Hateful
89. CVPR 2026TaskForce Cooperative Multi-agent Reinforcement Learning for Multi-task Optimization
90. CVPR 2026Thermally Activated Dual-Modal Adversarial Clothing against AI Surveillance Systems
91. CVPR 2026Think Before You Drive World Model-Inspired Multimodal Grounding
92. CVPR 2026Think Then Verify A Hypothesis-Verification Multi-Agent Framework for Long Video
93. CVPR 2026Thinking With Videos Multimodal Tool-Augmented Reinforcement Learning for Long Video
94. CVPR 2026TopoMA Topology-Guided Multi-Agent Dense RGB 3D Reconstruction via Distributed Inference
95. CVPR 2026Training High-Level Schedulers with Execution-Feedback Reinforcement Learning for Long-Horizon GUI
96. CVPR 2026Training One Model to Master Cross-Level Agentic Actions via Reinforcement
97. CVPR 2026UniM A Unified Any-to-Any Interleaved Multimodal Benchmark
98. CVPR 2026UniVBench Towards Unified Evaluation for Video Foundation Models
99. CVPR 2026Universal Guideline-Driven Image Clustering via a Hybrid LLM Agent
100. CVPR 2026Unsupervised Multi-agent and Single-agent Perception from Cooperative Views

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。