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 88 篇，第 2 / 2 页

51. ICML 2024Lookbehind-SAM: k steps back, 1 step forward
52. ICML 2024MAGDi: Structured Distillation of Multi-Agent Interaction Graphs Improves Reasoning in Smaller Language Models
53. ICML 2024Major-Minor Mean Field Multi-Agent Reinforcement Learning
54. ICML 2024Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads
55. ICML 2024MLAgentBench: Evaluating Language Agents on Machine Learning Experimentation
56. ICML 2024Multi-Agent Reinforcement Learning Meets Leaf Sequencing in Radiotherapy
57. ICML 2024Multi-Agent Reinforcement Learning with Hierarchical Coordination for Emergency Responder Stationing
58. ICML 2024Multi-Sender Persuasion: A Computational Perspective
59. ICML 2024Multi-Track Message Passing: Tackling Oversmoothing and Oversquashing in Graph Learning via Preventing Heterophily Mixing
60. ICML 2024Near-Optimal Reinforcement Learning with Self-Play under Adaptivity Constraints
61. ICML 2024Nonlinear Filtering with Brenier Optimal Transport Maps
62. ICML 2024Offline Training of Language Model Agents with Functions as Learnable Weights
63. ICML 2024On the Identifiability of Switching Dynamical Systems
64. ICML 2024Online Learning in Betting Markets: Profit versus Prediction
65. ICML 2024Optimistic Multi-Agent Policy Gradient
66. ICML 2024PGODE: Towards High-quality System Dynamics Modeling
67. ICML 2024Position: AI-Powered Autonomous Weapons Risk Geopolitical Instability and Threaten AI Research
68. ICML 2024Position: Enforced Amnesia as a Way to Mitigate the Potential Risk of Silent Suffering in the Conscious AI
69. ICML 2024Position: Foundation Agents as the Paradigm Shift for Decision Making
70. ICML 2024Position: Fundamental Limitations of LLM Censorship Necessitate New Approaches
71. ICML 2024Position: Towards Unified Alignment Between Agents, Humans, and Environment
72. ICML 2024QuIP$\#$: Even Better LLM Quantization with Hadamard Incoherence and Lattice Codebooks
73. ICML 2024R2E: Turning any Github Repository into a Programming Agent Environment
74. ICML 2024Reason for Future, Act for Now: A Principled Architecture for Autonomous LLM Agents
75. ICML 2024Residual Quantization with Implicit Neural Codebooks
76. ICML 2024Sample-Efficient Robust Multi-Agent Reinforcement Learning in the Face of Environmental Uncertainty
77. ICML 2024Scalable Safe Policy Improvement for Factored Multi-Agent MDPs
78. ICML 2024SceneCraft: An LLM Agent for Synthesizing 3D Scenes as Blender Code
79. ICML 2024Self-Rewarding Language Models
80. ICML 2024Sequential Asynchronous Action Coordination in Multi-Agent Systems: A Stackelberg Decision Transformer Approach
81. ICML 2024Should we be going MAD? A Look at Multi-Agent Debate Strategies for LLMs
82. ICML 2024Socialized Learning: Making Each Other Better Through Multi-Agent Collaboration
83. ICML 2024STEER: Assessing the Economic Rationality of Large Language Models
84. ICML 2024Towards Resource-friendly, Extensible and Stable Incomplete Multi-view Clustering
85. ICML 2024TravelPlanner: A Benchmark for Real-World Planning with Language Agents
86. ICML 2024Two-sided Competing Matching Recommendation Markets With Quota and Complementary Preferences Constraints
87. ICML 2024WorkArena: How Capable are Web Agents at Solving Common Knowledge Work Tasks?
88. ICML 2024Zero-Sum Positional Differential Games as a Framework for Robust Reinforcement Learning: Deep Q-Learning Approach

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。