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

2,126 papers, page 17 of 43

801. NeurIPS 2026Secure Seed-Based Multi-bit Watermarking for Diffusion Models from First Principles
802. NeurIPS 2026Seeing Beyond the Next Step: World-Model-Guided Human-Like Navigation in Multi-Agent Scenes
803. NeurIPS 2026Selective Rollout: Mid-Trajectory Termination for Multi-Sample Agent RL
804. NeurIPS 2026Self-Supervised Goal-Reaching Results in Multi-Agent Cooperation and Exploration
805. NeurIPS 2026SIGA: Scientific Simulation Coding Agent Adapter- A Geophysics Case Study
806. NeurIPS 2026Skill-SD: Skill-Conditioned Self-Distillation for Multi-turn LLM Agents
807. NeurIPS 2026SkillOpt: Executive Strategy for Self-Evolving Agent Skills
808. NeurIPS 2026SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks
809. NeurIPS 2026SMART: Scalable Multi-Agent Role-conditioned Teaming via LLM-free Tree Search
810. NeurIPS 2026SpecForge: Agent-Oriented Code Documentation Optimization via Multi-Frontier Tree Search
811. NeurIPS 2026Spend Only What You Need: Defect-Aware Residual Coverage for Efficient Multi-Agent Reasoning
812. NeurIPS 2026Stability in Multi-Step Reasoning via Jacobian-based Error Accumulation Analysis
813. NeurIPS 2026STAR-Math: Multi-Agent Mathematical Reasoning under Persistent Meta-Strategic Supervision
814. NeurIPS 2026StateLedger: Path-Addressed External Memory for Persistent Multi-Agent Systems
815. NeurIPS 2026Stealth Apart, Harm Together: Skill Cascading Attacks on Skill-Based Agent Systems
816. NeurIPS 2026Structural Entropy Optimized Communication for Multi-Agent Reinforcement Learning
817. NeurIPS 2026Structurally Separated DAG Learning with Multi-Scale Normalized Closure
818. NeurIPS 2026Structure-Semantic Guided Closed-Loop Medical Anomaly Detection via Multi-Agent Collaboration
819. NeurIPS 2026Surface Recovery Is Not State Recovery: Pressure–Recovery–Relapse in Multi-turn LLMs
820. NeurIPS 2026Sustainability in the Loop: AI Model Development Should Be Multi-Objective
821. NeurIPS 2026SwitchLingua V2: Agent-Driven Code-Switching via Digital Clones
822. NeurIPS 2026SyncLight: Single-Edit Multi-View Relighting
823. NeurIPS 2026Talk Less, Work More: Communication-Efficient Decentralized Stochastic Approximation
824. NeurIPS 2026Taming the Curses of Multiagency in Robust Markov Games with Large State Space through Linear Function Approximation
825. NeurIPS 2026Test-time Multi-agent Coordination by Decomposed Value Gradient Flow
826. NeurIPS 2026The Geometry of Agent Skills: Non-Commutative Composition in Representation Space
827. NeurIPS 2026The Horizon Threshold in Cooperative Multi-Agent Reward-Free Exploration
828. NeurIPS 2026The Long-Run Distribution of Regularized Learning in Non-Concave Games: A Large Deviations Approach
829. NeurIPS 2026The Reciprocity Gradient
830. NeurIPS 2026The Reflexivity Threshold: A Phase Transition for Multi-Agent Performative Prediction
831. NeurIPS 2026The Ringelmann Effect in Multi-Agent LLM Systems: A Scaling Law for Effective Team Size
832. NeurIPS 2026TimeClaw: A Time-Series AI Agent with Exploratory Execution Learning
833. NeurIPS 2026To trust or not to trust: Attention-based Trust Management for LLM Multi-Agent Systems
834. NeurIPS 2026ToMAToMP: Robust and Multi-Parameter Topological Clustering
835. NeurIPS 2026TopoScope: A Graph-Scoped LLM Agent for Printed Circuit Board Schematic Design
836. NeurIPS 2026Toward Executable Multi-framework Front-end Code Generation with Self-Correction
837. NeurIPS 2026Towards Direct Latent-Space Synthesis for Parallel Branches in LLM-Agent Workflows
838. NeurIPS 2026Towards Effective and Transferable Physical Camouflage against Multi-View BEV-based 3D Perception in Autonomous Driving
839. NeurIPS 2026Towards High Semantic Fidelity: Hyperdimensional Symbolic Messages in Multi-Agent Communication
840. NeurIPS 2026Towards Multi-Human-Value Alignment via Value Localization in LLMs
841. NeurIPS 2026TraceML: An Empirical Analysis of Human-Agent Planning in Machine Learning Development
842. NeurIPS 2026Train the Agent, Not the Expert: Learning to Harness Heterogeneous Experts for Multi-Turn Visual Reasoning
843. NeurIPS 2026TreemapMix: Dirichlet-Controlled Multi-Image Augmentation for Probability and Ordinal Supervision
844. NeurIPS 2026Truthful Calibration Errors for Multi-Class Prediction
845. NeurIPS 2026UMAS: System-Level Uncertainty Quantification for Multi-Agent LLM Systems
846. NeurIPS 2026Understanding Multi-View Transformers
847. NeurIPS 2026Unified Panoramic Geometry Estimation via Multi-View Foundation Models
848. NeurIPS 2026Unified Resource-Grounded Coordination Protocol for Orchestrator-Free Heterogeneous Multi-Agent Systems
849. NeurIPS 2026UniVer: A Unified Perspective for Multi-step and Multi-draft Speculative Decoding
850. NeurIPS 2026Veri-Sure: Multi-Agent RTL Code Generation with Temporal Tracing, Slicing and Formal Verification

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.