多智能体 RL论文趋势 2023–2026

主要结论

• 多智能体 RL论文从 2023 年的 311 篇增长到 2026 年的 868 篇，三年间扩大到约 2.8 倍。
• NeurIPS 是发多智能体 RL论文最多的会议，2023–2026 年共 809 篇，占四个会议总量的 38%。
• 交叉方向里涨得最快的是多模态大模型：同时属于两个主题的论文从 2023 年的 9 篇增至 2026 年的 70 篇。
• 在「博弈与规划」的 5 个主题里，它的 2026 年论文数排第 1；同组增长最快的经典规划是 3.3 倍，多智能体 RL是 2.8 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 20262-Step Agent: How a Bayesian Decision Maker Learns from AI-Decision Support
• ICML 2026A Causal Decomposition Approach for Fair Contextual Multi-Armed Bandits
• ICLR 2026Calibrated Information Bottleneck for Trusted Multi-modal Clustering
• CVPR 2026A Sanity Check for Multi-In-Domain Face Forgery Detection in the
• NeurIPS 2025Algorithms and SQ Lower Bounds for Robustly Learning Real-valued Multi-Index Models
• ICML 2025A Classification View on Meta Learning Bandits
• ICLR 2025BEEM: Boosting Performance of Early Exit DNNs using Multi-Exit Classifiers as Experts
• CVPR 2025All-Day Multi-Camera Multi-Target Tracking
• NeurIPS 2024A New Multi-Source Light Detection Benchmark and Semi-Supervised Focal Light Detection
• ICML 2024A Federated Stochastic Multi-level Compositional Minimax Algorithm for Deep AUC Maximization
• ICLR 2024An Intuitive Multi-Frequency Feature Representation for SO(3)-Equivariant Networks
• CVPR 2024DeconfuseTrack: Dealing with Confusion for Multi-Object Tracking
• NeurIPS 2023A Novel Approach for Effective Multi-View Clustering with Information-Theoretic Perspective
• ICML 2023A Framework for Adapting Offline Algorithms to Solve Combinatorial Multi-Armed Bandit Problems with Bandit Feedback
• ICLR 2023An Additive Instance-Wise Approach to Multi-class Model Interpretation
• CVPR 2023A Light Touch Approach to Teaching Transformers Multi-View Geometry
• NeurIPS 2026A Black-Box Reduction from Regret to Multi-Level Coverage
• ICML 2026A Consensus Anchor-guided Hypergraph Framework for Incomplete Multi-view Clustering
• ICLR 2026Confident Block Diagonal Structure-Aware Invariable Graph Completion for Incomplete Multi-view Clustering
• CVPR 2026Anti-Degradation Lifelong Multi-View Clustering

全部多智能体 RL论文

共 574 篇，第 3 / 12 页

101. CVPR 2025ShowUI: One Vision-Language-Action Model for GUI Visual Agent
102. CVPR 2025SocialMOIF: Multi-Order Intention Fusion for Pedestrian Trajectory Prediction
103. CVPR 2025SpiritSight Agent: Advanced GUI Agent with One Look
104. CVPR 2025SyncVP: Joint Diffusion for Synchronous Multi-Modal Video Prediction
105. CVPR 2025Theory-Inspired Deep Multi-View Multi-Label Learning with Incomplete Views and Noisy Labels
106. CVPR 2025Towards Consistent Multi-Task Learning: Unlocking the Potential of Task-Specific Parameters
107. CVPR 2025Towards Optimizing Large-Scale Multi-Graph Matching in Bioimaging
108. CVPR 2025TraF-Align: Trajectory-aware Feature Alignment for Asynchronous Multi-agent Perception
109. CVPR 2025UMFN: Unified Multi-Domain Face Normalization for Joint Cross-domain Prototype Learning and Heterogeneous Face Recognition
110. CVPR 2025Understanding Multi-layered Transmission Matrices
111. CVPR 2025Unified Uncertainty-Aware Diffusion for Multi-Agent Trajectory Modeling
112. CVPR 2025Unleashing the Potential of Consistency Learning for Detecting and Grounding Multi-Modal Media Manipulation
113. CVPR 2025Which Viewpoint Shows it Best? Language for Weakly Supervising View Selection in Multi-view Instructional Videos
114. ICLR 2025A Multi-Power Law for Loss Curve Prediction Across Learning Rate Schedules
115. ICLR 2025A-Bench: Are LMMs Masters at Evaluating AI-generated Images?
116. ICLR 2025ACC-Collab: An Actor-Critic Approach to Multi-Agent LLM Collaboration
117. ICLR 2025Agent Skill Acquisition for Large Language Models via CycleQD
118. ICLR 2025Agent-Oriented Planning in Multi-Agent Systems
119. ICLR 2025Agent-to-Sim: Learning Interactive Behavior Models from Casual Longitudinal Videos
120. ICLR 2025AgentOccam: A Simple Yet Strong Baseline for LLM-Based Web Agents
121. ICLR 2025AgentRefine: Enhancing Agent Generalization through Refinement Tuning
122. ICLR 2025Agents' Room: Narrative Generation through Multi-step Collaboration
123. ICLR 2025AgentTrek: Agent Trajectory Synthesis via Guiding Replay with Web Tutorials
124. ICLR 2025Analyzing and Boosting the Power of Fine-Grained Visual Recognition for Multi-modal Large Language Models
125. ICLR 2025AutoDAN-Turbo: A Lifelong Agent for Strategy Self-Exploration to Jailbreak LLMs
126. ICLR 2025Balanced Ranking with Relative Centrality: A multi-core periphery perspective
127. ICLR 2025Bayesian Analysis of Combinatorial Gaussian Process Bandits
128. ICLR 2025BEEM: Boosting Performance of Early Exit DNNs using Multi-Exit Classifiers as Experts
129. ICLR 2025Breaking Mental Set to Improve Reasoning through Diverse Multi-Agent Debate
130. ICLR 2025CaPo: Cooperative Plan Optimization for Efficient Embodied Multi-Agent Cooperation
131. ICLR 2025CHASE-SQL: Multi-Path Reasoning and Preference Optimized Candidate Selection in Text-to-SQL
132. ICLR 2025Classic but Everlasting: Traditional Gradient-Based Algorithms Converge Fast Even in Time-Varying Multi-Player Games
133. ICLR 2025CofCA: A STEP-WISE Counterfactual Multi-hop QA benchmark
134. ICLR 2025COMBO: Compositional World Models for Embodied Multi-Agent Cooperation
135. ICLR 2025Competing Large Language Models in Multi-Agent Gaming Environments
136. ICLR 2025CoMRes: Semi-Supervised Time Series Forecasting Utilizing Consensus Promotion of Multi-Resolution
137. ICLR 2025COPER: Correlation-based Permutations for Multi-View Clustering
138. ICLR 2025Cut the Crap: An Economical Communication Pipeline for LLM-based Multi-Agent Systems
139. ICLR 2025DelTA: An Online Document-Level Translation Agent Based on Multi-Level Memory
140. ICLR 2025Direct Post-Training Preference Alignment for Multi-Agent Motion Generation Model Using Implicit Feedback from Pre-training Demonstrations
141. ICLR 2025Discriminator-Guided Embodied Planning for LLM Agent
142. ICLR 2025DistRL: An Asynchronous Distributed Reinforcement Learning Framework for On-Device Control Agent
143. ICLR 2025Divergence-Regularized Discounted Aggregation: Equilibrium Finding in Multiplayer Partially Observable Stochastic Games
144. ICLR 2025Do as We Do, Not as You Think: the Conformity of Large Language Models
145. ICLR 2025Do LLM Agents Have Regret? A Case Study in Online Learning and Games
146. ICLR 2025DUET: Decentralized Bilevel Optimization without Lower-Level Strong Convexity
147. ICLR 2025Duoduo CLIP: Efficient 3D Understanding with Multi-View Images
148. ICLR 2025EC-Diffuser: Multi-Object Manipulation via Entity-Centric Behavior Generation
149. ICLR 2025EFFICIENT JAILBREAK ATTACK SEQUENCES ON LARGE LANGUAGE MODELS VIA MULTI-ARMED BANDIT-BASED CONTEXT SWITCHING
150. ICLR 2025EgoSim: Egocentric Exploration in Virtual Worlds with Multi-modal Conditioning

常见问题

2023–2026 年四大会议一共有多少篇多智能体 RL论文？

共 2,126 篇，按年份分别是 2023 年 311 篇、2024 年 373 篇、2025 年 574 篇、2026 年 868 篇。

NeurIPS 2026 有多少篇多智能体 RL论文？

NeurIPS 2026 有 319 篇多智能体 RL论文，上一届是 255 篇。

ICLR 2026 有多少篇多智能体 RL论文？

ICLR 2026 有 153 篇多智能体 RL论文，上一届是 91 篇。

ICML 2026 有多少篇多智能体 RL论文？

ICML 2026 有 224 篇多智能体 RL论文，上一届是 115 篇。

CVPR 2026 有多少篇多智能体 RL论文？

CVPR 2026 有 172 篇多智能体 RL论文，上一届是 113 篇。

哪个会议的多智能体 RL论文最多？

NeurIPS，2023–2026 年共 809 篇。