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 91 篇，第 2 / 2 页

51. ICLR 2025InvestESG: A multi-agent reinforcement learning benchmark for studying climate investment as a social dilemma
52. ICLR 2025Learned Reference-based Diffusion Sampler for multi-modal distributions
53. ICLR 2025Learning Multi-Index Models with Neural Networks via Mean-Field Langevin Dynamics
54. ICLR 2025Learning on One Mode: Addressing Multi-modality in Offline Reinforcement Learning
55. ICLR 2025Learning to Help in Multi-Class Settings
56. ICLR 2025Lightweight Neural App Control
57. ICLR 2025LiveXiv - A Multi-Modal live benchmark based on Arxiv papers content
58. ICLR 2025MACPO: Weak-to-Strong Alignment via Multi-Agent Contrastive Preference Optimization
59. ICLR 2025MindSearch: Mimicking Human Minds Elicits Deep AI Searcher
60. ICLR 2025Minimal Impact ControlNet: Advancing Multi-ControlNet Integration
61. ICLR 2025Mixture-of-Agents Enhances Large Language Model Capabilities
62. ICLR 2025MTU-Bench: A Multi-granularity Tool-Use Benchmark for Large Language Models
63. ICLR 2025Multi-Dimensional Conformal Prediction
64. ICLR 2025Multi-Draft Speculative Sampling: Canonical Decomposition and Theoretical Limits
65. ICLR 2025Multi-Label Node Classification with Label Influence Propagation
66. ICLR 2025Multi-modal Agent Tuning: Building a VLM-Driven Agent for Efficient Tool Usage
67. ICLR 2025Multiagent Finetuning: Self Improvement with Diverse Reasoning Chains
68. ICLR 2025Near-Optimal Online Learning for Multi-Agent Submodular Coordination: Tight Approximation and Communication Efficiency
69. ICLR 2025OBI-Bench: Can LMMs Aid in Study of Ancient Script on Oracle Bones?
70. ICLR 2025Pairwise Elimination with Instance-Dependent Guarantees for Bandits with Cost Subsidy
71. ICLR 2025PARTNR: A Benchmark for Planning and Reasoning in Embodied Multi-agent Tasks
72. ICLR 2025POGEMA: A Benchmark Platform for Cooperative Multi-Agent Pathfinding
73. ICLR 2025Rational Decision-Making Agent with Learning Internal Utility Judgment
74. ICLR 2025Rethinking Self-Distillation: Label Averaging and Enhanced Soft Label Refinement with Partial Labels
75. ICLR 2025REVISITING MULTI-PERMUTATION EQUIVARIANCE THROUGH THE LENS OF IRREDUCIBLE REPRESENTATIONS
76. ICLR 2025Robust Gymnasium: A Unified Modular Benchmark for Robust Reinforcement Learning
77. ICLR 2025SaMer: A Scenario-aware Multi-dimensional Evaluator for Large Language Models
78. ICLR 2025Scaling Large Language Model-based Multi-Agent Collaboration
79. ICLR 2025SelectFormer in Data Markets: Privacy-Preserving and Efficient Data Selection for Transformers with Multi-Party Computation
80. ICLR 2025Self-Evolving Multi-Agent Collaboration Networks for Software Development
81. ICLR 2025Simple yet Effective Incomplete Multi-view Clustering: Similarity-level Imputation and Intra-view Hybrid-group Prototype Construction
82. ICLR 2025Single-agent Poisoning Attacks Suffice to Ruin Multi-Agent Learning
83. ICLR 2025Sports-Traj: A Unified Trajectory Generation Model for Multi-Agent Movement in Sports
84. ICLR 2025Stochastic Semi-Gradient Descent for Learning Mean Field Games with Population-Aware Function Approximation
85. ICLR 2025Towards Optimal Multi-draft Speculative Decoding
86. ICLR 2025Trusted Multi-View Classification via Evolutionary Multi-View Fusion
87. ICLR 2025uniINF: Best-of-Both-Worlds Algorithm for Parameter-Free Heavy-Tailed MABs
88. ICLR 2025VVC-Gym: A Fixed-Wing UAV Reinforcement Learning Environment for Multi-Goal Long-Horizon Problems
89. ICLR 2025Weak to Strong Generalization for Large Language Models with Multi-capabilities
90. ICLR 2025Weighted Multi-Prompt Learning with Description-free Large Language Model Distillation
91. ICLR 2025When LLMs Play the Telephone Game: Cultural Attractors as Conceptual Tools to Evaluate LLMs in Multi-turn Settings

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。