AAAI 2026 accepted papers on Multi-agent systems and games
224 of the 4,417 papers accepted at AAAI 2026 (5.1%) are on Multi-agent systems and games, compared with 4.0% at AAAI 2025. They fall into 4 topics.
See AAAI 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 · 113 papers
- MCPTox: A Benchmark for Tool Poisoning on Real-World MCP Servers (7 citations)
- U2UData+: A Scalable Swarm UAVs Autonomous Flight Dataset for Embodied Long-horizon Tasks (7 citations)
- RareAgents: Autonomous Multi-disciplinary Team for Rare Disease Diagnosis and Treatment (4 citations)
- Agent-SAMA: State-Aware Mobile Assistant (3 citations)
- AgentMental: An Interactive Multi-Agent Framework for Explainable and Adaptive Mental Health Assessment (3 citations)
- AgentSense: Virtual Sensor Data Generation Using LLM Agents in Simulated Home Environments (3 citations)
- GitTaskBench: A Benchmark for Code Agents Solving Real-World Tasks Through Code Repository Leveraging (3 citations)
- InEx: Hallucination Mitigation via Introspection and Cross-Modal Multi-Agent Collaboration (3 citations)
- MedLA: A Logic-Driven Multi-Agent Framework for Complex Medical Reasoning with Large Language Models (3 citations)
- Simulating Dispute Mediation with LLM-Based Agents for Legal Research (3 citations)
- AgentCDM: Enhancing Multi-Agent Collaborative Decision-Making via ACH-Inspired Structured Reasoning (2 citations)
- AgentSwift: Efficient LLM Agent Design via Value-Guided Hierarchical Search (2 citations)
and 101 more in the interactive map.
Human-AI and goal-conditioned · 53 papers
- InfoCom: Kilobyte-Scale Communication-Efficient Collaborative Perception with Information Bottleneck (4 citations)
- Cook and Clean Together: Teaching Embodied Agents for Parallel Task Execution (2 citations)
- Differentiable Semantic Meta-Learning Framework for Long-Tail Motion Forecasting in Autonomous Driving (2 citations)
- UniMM-V2X: MoE-Enhanced Multi-Level Fusion for End-to-End Cooperative Autonomous Driving (2 citations)
- A Logical Analysis of an Information Filtering Architecture Based on Epistemic Trust Inference (1 citation)
- Dimension-Aware Active Annotation for Aesthetic Perception via Multi-Agent Human–AI Collaboration (1 citation)
- Enhancing PIBT via Multi-Action Operations (1 citation)
- Learning to Cooperate with Minimal Observability (1 citation)
- SmartAgent: Chain-of-User-Thought for Embodied Personalized Agent in Cyber World (1 citation)
- Spatially Grouped Curriculum Learning for Multi-Agent Path Finding (1 citation)
- Symbolic Planning and Multi-Agent Path Finding in Extremely Dense Environments with Unassigned Agents (1 citation)
- Truncated Counterfactual Learning for Anytime Multi-Agent Path Finding (1 citation)
and 41 more in the interactive map.
Cooperative multi-agent RL · 40 papers
- LLM Collaboration with Multi-Agent Reinforcement Learning (7 citations)
- Communication-efficient Multi-Agent Reinforcement Learning with Spatiotemporal Information Hub (3 citations)
- M2I2: Learning Efficient Multi-Agent Communication via Masked State Modeling and Intention Inference (3 citations)
- HCPO: Hierarchical Conductor-Based Policy Optimization in Multi-Agent Reinforcement Learning (2 citations)
- Think How Your Teammates Think: Active Inference Can Benefit Decentralized Execution (2 citations)
- VIL2C: Value-of-Information Aware Low-Latency Communication for Multi-Agent Reinforcement Learning (2 citations)
- Achieving Equilibrium Under Utility Heterogeneity: An Agent-Attention Framework for Multi-Agent Multi-Objective Reinforcement Learning (1 citation)
- ADAPT: Adaptive Decentralized Architecture with Perception-Aligned Training for Structural Generalization in Multi-Agent RL (1 citation)
- Advancing Protein Design via Multi-Agent Reinforcement Learning with Pareto-Based Collaborative Optimization (1 citation)
- Autonomous Partner Selection for Cooperative Multi-Agent Reinforcement Learning (1 citation)
- Beyond Monotonicity: Revisiting Factorization Principles in Multi-Agent Q-Learning (1 citation)
- Expert-Inspired Multi-Agent Coordination for Multi-Objective Molecular Optimization (1 citation)
and 28 more in the interactive map.
Games and equilibria · 18 papers
- Fairness Aware Reinforcement Learning via Proximal Policy Optimization (2 citations)
- When Natural Strategies Meet Fuzziness and Resource-Bounded Actions (2 citations)
- A Graph-Theoretical Perspective on Law Design for Multiagent Systems
- Agentmandering: A Game-Theoretic Framework for Fair Redistricting via Large Language Model Agents
- Area-Optimal Control Strategies for Heterogeneous Multi-Agent Pursuit
- CSP4SDG: Constraint and Information-Theory Based Role Identification in Social Deduction Games with LLM-Enhanced Inference
- Delta Matters: An Analytically Tractable Model for beta–delta Discounting Agents
- Designing Optimal Mechanisms to Locate Facilities with Insufficient Capacity for Bayesian Agents
- ElementaryNet: A Non-Strategic Neural Network for Predicting Human Behavior in Normal-Form Games
- Enhancing Strategy Logic with Procedural Rationality
- Facility Location for Congesting Commuters and Generalizing the Cost-Distance Problem
- Fair Division Among Couples and Small Groups
and 6 more in the interactive map.