Multi-Agent RL papers, 2023–2026

Key findings

• Multi-Agent RL went from 311 papers in 2023 to 868 in 2026, roughly 2.8x in three years.
• NeurIPS publishes the most Multi-Agent RL work: 809 papers from 2023 to 2026, 38% of the four-venue total.
• The fastest-growing overlap is with Multimodal LLMs: papers tagged with both rose from 9 in 2023 to 70 in 2026.
• Among the 5 topics under Games and Planning, it ranks #1 by 2026 paper count; the fastest grower in the group, Classical Planning, is up 3.3x versus 2.8x here.

Representative papers

Spread across years and venues so every edition shows up

• 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

All Multi-Agent RL papers

153 papers, page 3 of 4

101. ICLR 2026Non-Asymptotic Analysis of (Sticky) Track-and-Stop
102. ICLR 2026Numerion: A Multi-Hypercomplex Model for Time Series Forecasting
103. ICLR 2026OmniActor: A Generalist GUI and Embodied Agent for 2D&3D Worlds
104. ICLR 2026Opponent Shaping in LLM Agents
105. ICLR 2026OrchestrationBench: LLM-Driven Agentic Planning and Tool Use in Multi-Domain Scenarios
106. ICLR 2026OrthAlign: Orthogonal Subspace Decomposition for Non-Interfering Multi-Objective Alignment
107. ICLR 2026Pairwise is Not Enough: Hypergraph Neural Networks for Multi-Agent Pathfinding
108. ICLR 2026Peng's Q($\lambda$) for Conservative Value Estimation in Offline Reinforcement Learning
109. ICLR 2026Personalized Collaborative Learning with Affinity-Based Variance Reduction
110. ICLR 2026PIRN: Prototypical-based Intra-modal Reconstruction with Normality Communication for Multi-modal Anomaly Detection.
111. ICLR 2026PixelCraft: A Multi-Agent system for High-Fidelity Visual Reasoning on Structured Images
112. ICLR 2026PoinnCARE: Hyperbolic Multi-Modal Learning for Enzyme Classification
113. ICLR 2026Protein Structure Tokenization via Geometric Byte Pair Encoding
114. ICLR 2026Randomization Boosts KV Caching, Learning Balances Query Load: A Joint Perspective
115. ICLR 2026RECAST: Expanding the Boundaries of LLMs' Complex Instruction Following with Multi-Constraint Data
116. ICLR 2026Reevaluating Policy Gradient Methods for Imperfect-Information Games
117. ICLR 2026Relationship Alignment for View-aware Multi-view Clustering
118. ICLR 2026Rethinking Consistent Multi-Label Classification under Inexact Supervision
119. ICLR 2026Revisiting Matrix Sketching in Linear Bandits: Achieving Sublinear Regret via Dyadic Block Sketching
120. ICLR 2026Revisiting Nonstationary Kernel Design for Multi-Output Gaussian Processes
121. ICLR 2026RIG: Synergizing Reasoning and Imagination in End-to-End Generalist Policy
122. ICLR 2026Robust Multi-Objective Controlled Decoding of Large Language Models
123. ICLR 2026SAM-Veteran: An MLLM-Based Human-like SAM Agent for Reasoning Segmentation
124. ICLR 2026Scaling Agents via Continual Pre-training
125. ICLR 2026Scaling Generalist Data-Analytic Agents
126. ICLR 2026Shuffling the Data, Extrapolating the Step: Sharper Bias In Constant Step-Size SGD
127. ICLR 2026SocialJax: An Evaluation Suite for Multi-agent Reinforcement Learning in Sequential Social Dilemmas
128. ICLR 2026Solving the 2-norm k-hyperplane clustering problem via multi-norm formulations
129. ICLR 2026Spinning Straw into Gold: Relabeling LLM Agent Trajectories in Hindsight for Successful Demonstrations
130. ICLR 2026STARK: Strategic Team of Agents for Refining Kernels
131. ICLR 2026Stochastic Self-Organization in Multi-Agent Systems
132. ICLR 2026Stop Wasting Your Tokens: Towards Efficient Runtime Multi-Agent Systems
133. ICLR 2026Stronger-MAS: Multi-Agent Reinforcement Learning for Collaborative LLMs
134. ICLR 2026T-TAMER: Provably Taming Trade-offs in ML Serving
135. ICLR 2026TableDART: Dynamic Adaptive Multi-Modal Routing for Table Understanding
136. ICLR 2026Toward Enhancing Representation Learning in Federated Multi-Task Settings
137. ICLR 2026Towards Reliable Benchmarking: A Contamination Free, Controllable Evaluation Framework for Multi-step LLM Function Calling
138. ICLR 2026Towards Self-Evolving Agent Benchmarks : Validatable Agent Trajectory via Test-Time Exploration
139. ICLR 2026Towards Sustainable Investment Policies Informed by Opponent Shaping
140. ICLR 2026Trade in Minutes! Rationality-Driven Agentic System for Quantitative Financial Trading
141. ICLR 2026TRIM: Hybrid Inference via Targeted Stepwise Routing in Multi-Step Reasoning Tasks
142. ICLR 2026Trinity: An Evolved LLM Coordinator
143. ICLR 2026TUMIX: Multi-Agent Test-Time Scaling with Tool-Use Mixture
144. ICLR 2026Uncover Underlying Correspondence for Robust Multi-view Clustering
145. ICLR 2026Unified and Efficient Multi-view Clustering from Probabilistic Perspective
146. ICLR 2026UniTrack: Differentiable Graph Representation Learning for Multi-Object Tracking
147. ICLR 2026Unlocking the Power of Co-Occurrence in CLIP: A DualPrompt-Driven Method for Training-Free Zero-Shot Multi-Label Classification
148. ICLR 2026Unlocking the Power of Multi-Agent LLM for Reasoning: From Lazy Agents to Deliberation
149. ICLR 2026Visual Multi-Agent System: Mitigating Hallucination Snowballing via Visual Flow
150. ICLR 2026WebSailor-V2: Bridging the Chasm to Proprietary Agents via Synthetic Data and Scalable Reinforcement Learning

FAQ

How many Multi-Agent RL papers were published at NeurIPS, ICLR, ICML and CVPR from 2023 to 2026?

2,126 in total: 311 in 2023, 373 in 2024, 574 in 2025, 868 in 2026.

How many Multi-Agent RL papers are at NeurIPS 2026?

NeurIPS 2026 has 319 Multi-Agent RL papers, versus 255 the year before.

How many Multi-Agent RL papers are at ICLR 2026?

ICLR 2026 has 153 Multi-Agent RL papers, versus 91 the year before.

How many Multi-Agent RL papers are at ICML 2026?

ICML 2026 has 224 Multi-Agent RL papers, versus 115 the year before.

How many Multi-Agent RL papers are at CVPR 2026?

CVPR 2026 has 172 Multi-Agent RL papers, versus 113 the year before.

Which conference publishes the most Multi-Agent RL papers?

NeurIPS, with 809 papers from 2023 to 2026.