ICML 2026 accepted papers on Multi-agent systems and games
363 of the 6,341 papers accepted at ICML 2026 (5.7%) are on Multi-agent systems and games, compared with 2.9% at ICML 2025. They fall into 4 topics.
See ICML 2026 in the interactive map
Working on something in this area? Describe your idea in scime atlas to see the closest accepted papers by meaning and how crowded the spot has become.
Topics and papers
LLM agents · 281 papers
- Measuring Agents in Production (3 citations)
- Multi-Agent Teams Hold Experts Back (2 citations)
- RedDebate: Safer Responses Through Multi-Agent Red Teaming Debates (2 citations)
- Towards a Science of AI Agent Reliability (2 citations)
- A-MemGuard: A Proactive Defense Framework For LLM-Based Agent Memory (1 citation)
- BioAgent Bench: An AI Agent Evaluation Suite for Bioinformatics (1 citation)
- Constitutional Black-Box Monitoring for Scheming in LLM Agents (1 citation)
- Evolving Interpretable Constitutions for Multi-Agent Coordination (1 citation)
- From Weak Cues to Real Identities: Evaluating Inference-Driven De-Anonymization in LLM Agents (1 citation)
- Is Vibe Coding Safe? Benchmarking Vulnerability of Agent-Generated Code in Real-World Tasks (1 citation)
- It's a TRAP! Task-Redirecting Agent Persuasion Benchmark for Web Agents (1 citation)
- Latent Collaboration in Multi-Agent Systems (1 citation)
and 269 more in the interactive map.
Human-AI and goal-conditioned · 34 papers
- A Behavioural and Representational Evaluation of Goal-Directedness in Language Model Agents
- Agent Learning via Early Experience
- AgentSteerTTS: A Multi-Agent Closed-Loop Framework for Composite-Instruction Text-to-Speech
- Benchmarking the Limits of In-Context Reinforcement Learning for Ad-Hoc Teamwork
- CINOC: Cardinality-Invariant Neural Operator Policies for Scalable PDE Control
- CooT: Learning to Coordinate In-Context with Coordination Transformers
- Corrigibility Transformation: Constructing Goals That Accept Updates
- Data Agent: Learning to Select Data via End-to-End Dynamic Optimization
- Detecting Perspective Shifts in Multi-Agent Systems
- Dreaming in Code for Curriculum Learning in Open-Ended Worlds
- EMBGuard: Constructing Hazard-Aware Guardrails for Safe Planning in Embodied Agents
- Goal-Conditioned Agents that Learn Everything All at Once
and 22 more in the interactive map.
Cooperative multi-agent RL · 32 papers
- Automata-Conditioned Cooperative Multi-Agent Reinforcement Learning
- Diffusing to Coordinate: Efficient Online Multi-Agent Diffusion Policies
- Factored Value Functions for Graph-Based Multi-Agent Reinforcement Learning
- HyPOLE: Hyperproperty-Guided Multi-Agent Reinforcement Learning under Partial Observation
- Interaction-Breaking Adversarial Learning Framework for Robust Multi-Agent Reinforcement Learning
- Learning Decentralized LLM Collaboration with Multi-Agent Actor Critic
- Learning Multi-Agent Coordination via Sheaf-ADMM
- LLM-Guided Communication for Cooperative Multi-Agent Reinforcement Learning
- MAFE: Enabling Equitable Algorithm Design in Multi-Agent Multi-Stage Decision-Making Systems
- MEAL: A Benchmark for Continual Multi-Agent Reinforcement Learning
- Multi-Agent Reinforcement Learning with Submodular Reward
- NonZero: Interaction-Guided Exploration for Multi-Agent Monte Carlo Tree Search
and 20 more in the interactive map.
Games and equilibria · 16 papers
- Anytime Detection of Strategic Deviations in Multi-Agent Systems
- Beyond Rational Illusion: Behaviorally Realistic Strategic Classification
- CoopEval: Benchmarking Cooperation-Sustaining Mechanisms and LLM Agents in Social Dilemmas
- Deep Incentive Design with Differentiable Equilibrium Blocks
- Distributionally Robust Markov Games with Average Reward
- Emergent Alignment via Competition
- Multi-agent imitation learning with function approximation: linear Markov games and beyond
- Multi-Level Strategic Classification: Incentivizing Improvement through Promotion and Relegation Dynamics
- Off-Policy Evaluation with Strategic Agents via Local Disclosure
- On the Coordination of Value-Maximizing Bidders
- Optimal Rates for Feasible Payoff Set Estimation in Games
- Population-Aware Imitation Learning in Mean-field Games with Common Noise
and 4 more in the interactive map.