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 320 篇，第 2 / 7 页

51. ICLR 2026FingerTip 20K: A Benchmark for Proactive and Personalized Mobile LLM Agents
52. ICLR 2026Flow-based Conformal Prediction for Multi-dimensional Time Series
53. ICLR 2026From Assumptions to Actions: Turning LLM Reasoning into Uncertainty-Aware Planning for Embodied Agents
54. ICLR 2026From Medical Records to Diagnostic Dialogues: A Clinical-Grounded Approach and Dataset for Psychiatric Comorbidity
55. ICLR 2026From Single to Multi-Granularity: Toward Long-Term Memory Association and Selection of Conversational Agents
56. ICLR 2026From What to Why: A Multi-Agent System for Evidence-based Chemical Reaction Condition Reasoning
57. ICLR 2026Goal-Aware Identification and Rectification of Misinformation in Multi-Agent Systems
58. ICLR 2026Graph-of-Agents: A Graph-based Framework for Multi-Agent LLM Collaboration
59. ICLR 2026GT-Space: Enhancing Heterogeneous Collaborative Perception with Ground Truth Feature Space
60. ICLR 2026HAMLET: Hyperadaptive Agent-based Modeling for Live Embodied Theatrics
61. ICLR 2026Helmsman: Autonomous Synthesis of Federated Learning Systems via Collaborative LLM Agents
62. ICLR 2026Hierarchical Multi-Stage Recovery Framework for Kronecker Compressed Sensing
63. ICLR 2026Holistic Agent Leaderboard: The Missing Infrastructure for AI Agent Evaluation
64. ICLR 2026Huxley-G\"odel Machine: Human-Level Coding Agent Development by an Approximation of the Optimal Self-Improving Machine
65. ICLR 2026ICaRus: Identical Cache Reuse for Efficient Multi-Model Inference
66. ICLR 2026Identifying and Evaluating Inactive Heads in Pretrained LLMs
67. ICLR 2026Information Gain-based Policy Optimization: A Simple and Effective Approach for Multi-Turn LLM Agents
68. ICLR 2026InnoGym: Benchmarking the Innovation Potential of AI Agents
69. ICLR 2026Interactive Agents to Overcome Underspecificity in Software Engineering
70. ICLR 2026IR-Agent: Expert-Inspired LLM Agents for Structure Elucidation from Infrared Spectra
71. ICLR 2026JointDiff: Bridging Continuous and Discrete in Multi-Agent Trajectory Generation
72. ICLR 2026Kimi-Dev: Agentless Training as Skill Prior for SWE-agents
73. ICLR 2026KnowGuard: Knowledge-Driven Abstention for Multi-Round Clinical Reasoning
74. ICLR 2026KVComm: Enabling Efficient LLM Communication through Selective KV Sharing
75. ICLR 2026Learning to Play Multi-Follower Bayesian Stackelberg Games
76. ICLR 2026Learning with Dual-level Noisy Correspondence for Multi-modal Entity Alignment
77. ICLR 2026LiveResearchBench: Benchmarking Single- and Multi-Agent Systems for Citation-Grounded Deep Research
78. ICLR 2026LongHorizonUI: A Unified Framework for Robust long-horizon Task Automation of GUI Agent
79. ICLR 2026MARSHAL: Incentivizing Multi-Agent Reasoning via Self-Play with Strategic LLMs
80. ICLR 2026MAS$^2$: Self-Generative, Self-Configuring, Self-Rectifying Multi-Agent Systems
81. ICLR 2026MATA: A Trainable Hierarchical Automaton System for Multi-Agent Visual Reasoning
82. ICLR 2026Matching multiple experts: on the exploitability of multi-agent imitation learning
83. ICLR 2026Measuring and Mitigating Rapport Bias of Large Language Models under Multi-Agent Social Interactions
84. ICLR 2026Measuring Bias Amplification in Multi-Agent Systems with Large Language Models
85. ICLR 2026MemAgent: Reshaping Long-Context LLM with Multi-Conv RL-based Memory Agent
86. ICLR 2026Meta-RL Induces Exploration in Language Agents
87. ICLR 2026MHLA: Restoring Expressivity of Linear Attention via Token-Level Multi-Head
88. ICLR 2026MIRA: Memory-Integrated Reinforcement Learning Agent with Limited LLM Guidance
89. ICLR 2026MLE-Smith: Scaling MLE Tasks with Automated Multi-agent Pipeline
90. ICLR 2026MoRA: Mobility as the Backbone for Geospatial Representation Learning at Scale
91. ICLR 2026Multi-Action Self-Improvement For Neural Combinatorial Optimization
92. ICLR 2026Multi-Agent Debate with Memory Masking
93. ICLR 2026Multi-Agent Design: Optimizing Agents with Better Prompts and Topologies
94. ICLR 2026Multi-LLM Adaptive Conformal Inference for Reliable LLM Response
95. ICLR 2026Multi-ReduNet: Interpretable Class-Wise Decomposition of ReduNet
96. ICLR 2026Multi-Scale Diffusion-Guided Graph Learning with Power-Smoothing Random Walk Contrast for Multi-View Clustering
97. ICLR 2026Multi-Scale Hypergraph Meets LLMs: Aligning Large Language Models for Time Series Analysis
98. ICLR 2026Multi-View Encoders for Performance Prediction in LLM-Based Agentic Workflows
99. ICLR 2026MVCustom: Multi-View Customized Diffusion via Geometric Latent Rendering and Completion
100. ICLR 2026Neural Networks Learn Generic Multi-Index Models Near Information-Theoretic Limit

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。