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 170 篇，第 2 / 4 页

51. ICLR 2023The Implicit Bias of Minima Stability in Multivariate Shallow ReLU Networks
52. ICLR 2023Towards Effective and Interpretable Human-Agent Collaboration in MOBA Games: A Communication Perspective
53. ICLR 2023Truthful Self-Play
54. ICML 2023A Game-Theoretic Framework for Managing Risk in Multi-Agent Systems
55. ICML 2023An Adaptive Entropy-Regularization Framework for Multi-Agent Reinforcement Learning
56. ICML 2023Best Arm Identification in Multi-Agent Multi-Armed Bandits
57. ICML 2023Collaborative Multi-Agent Heterogeneous Multi-Armed Bandits
58. ICML 2023Complementary Attention for Multi-Agent Reinforcement Learning
59. ICML 2023Context-Aware Bayesian Network Actor-Critic Methods for Cooperative Multi-Agent Reinforcement Learning
60. ICML 2023Controlling Type Confounding in Ad Hoc Teamwork with Instance-wise Teammate Feedback Rectification
61. ICML 2023Cooperative Multi-Agent Reinforcement Learning: Asynchronous Communication and Linear Function Approximation
62. ICML 2023DoG is SGD's Best Friend: A Parameter-Free Dynamic Step Size Schedule
63. ICML 2023DoMo-AC: Doubly Multi-step Off-policy Actor-Critic Algorithm
64. ICML 2023DSGD-CECA: Decentralized SGD with Communication-Optimal Exact Consensus Algorithm
65. ICML 2023Emergent Agentic Transformer from Chain of Hindsight Experience
66. ICML 2023Entity Divider with Language Grounding in Multi-Agent Reinforcement Learning
67. ICML 2023K-SHAP: Policy Clustering Algorithm for Anonymous Multi-Agent State-Action Pairs
68. ICML 2023Lazy Agents: A New Perspective on Solving Sparse Reward Problem in Multi-agent Reinforcement Learning
69. ICML 2023Learning Intuitive Policies Using Action Features
70. ICML 2023Learning to Decouple Complex Systems
71. ICML 2023Learning to Incentivize Information Acquisition: Proper Scoring Rules Meet Principal-Agent Model
72. ICML 2023Learning to Optimize Differentiable Games
73. ICML 2023Local Optimization Achieves Global Optimality in Multi-Agent Reinforcement Learning
74. ICML 2023MANSA: Learning Fast and Slow in Multi-Agent Systems
75. ICML 2023Motion Question Answering via Modular Motion Programs
76. ICML 2023Multi-Agent Best Arm Identification with Private Communications
77. ICML 2023Multi-Agent Learning from Learners
78. ICML 2023Multi-Agent Online Optimization with Delays: Asynchronicity, Adaptivity, and Optimism
79. ICML 2023Multi-agent Online Scheduling: MMS Allocations for Indivisible Items
80. ICML 2023Multi-channel Autobidding with Budget and ROI Constraints
81. ICML 2023N$\text{A}^\text{2}$Q: Neural Attention Additive Model for Interpretable Multi-Agent Q-Learning
82. ICML 2023Network Effects in Performative Prediction Games
83. ICML 2023Neural Collapse in Deep Linear Networks: From Balanced to Imbalanced Data
84. ICML 2023Offline Learning in Markov Games with General Function Approximation
85. ICML 2023One-Step Estimator for Permuted Sparse Recovery
86. ICML 2023Probably Anytime-Safe Stochastic Combinatorial Semi-Bandits
87. ICML 2023RACE: Improve Multi-Agent Reinforcement Learning with Representation Asymmetry and Collaborative Evolution
88. ICML 2023Scalable Multi-Agent Reinforcement Learning through Intelligent Information Aggregation
89. ICML 2023Sparse Learning of Dynamical Systems in RKHS: An Operator-Theoretic Approach
90. ICML 2023System Identification of Neural Systems: If We Got It Right, Would We Know?
91. ICML 2023The Ideal Continual Learner: An Agent That Never Forgets
92. ICML 2023The Impact of Exploration on Convergence and Performance of Multi-Agent Q-Learning Dynamics
93. ICML 2023The Role of Entropy and Reconstruction in Multi-View Self-Supervised Learning
94. ICML 2023What do CNNs Learn in the First Layer and Why? A Linear Systems Perspective
95. NeurIPS 2023AdaPlanner: Adaptive Planning from Feedback with Language Models
96. NeurIPS 2023AlberDICE: Addressing Out-Of-Distribution Joint Actions in Offline Multi-Agent RL via Alternating Stationary Distribution Correction Estimation
97. NeurIPS 2023Alexa Arena: A User-Centric Interactive Platform for Embodied AI
98. NeurIPS 2023AllSim: Simulating and Benchmarking Resource Allocation Policies in Multi-User Systems
99. NeurIPS 2023AndroidInTheWild: A Large-Scale Dataset For Android Device Control
100. NeurIPS 2023Automatic Grouping for Efficient Cooperative Multi-Agent Reinforcement Learning

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。