NeurIPS 2025 accepted papers on Multi-agent systems and games
213 of the 5,812 papers accepted at NeurIPS 2025 (3.7%) are on Multi-agent systems and games, compared with 2.6% at NeurIPS 2024. They fall into 4 topics.
See NeurIPS 2025 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 · 105 papers
- Why Do Multi-Agent LLM Systems Fail? (33 citations)
- A-Mem: Agentic Memory for LLM Agents (25 citations)
- AgentNet: Decentralized Evolutionary Coordination for LLM-based Multi-Agent Systems (20 citations)
- TheAgentCompany: Benchmarking LLM Agents on Consequential Real World Tasks (13 citations)
- Multi-Agent Collaboration via Evolving Orchestration (6 citations)
- AgentDAM: Privacy Leakage Evaluation for Autonomous Web Agents (5 citations)
- Debate or Vote: Which Yields Better Decisions in Multi-Agent Large Language Models? (4 citations)
- G-Memory: Tracing Hierarchical Memory for Multi-Agent Systems (4 citations)
- KVFlow: Efficient Prefix Caching for Accelerating LLM-Based Multi-Agent Workflows (4 citations)
- LC-Opt: Benchmarking Reinforcement Learning and Agentic AI for End-to-End Liquid Cooling Optimization in Data Centers (4 citations)
- SWE-smith: Scaling Data for Software Engineering Agents (4 citations)
- WASP: Benchmarking Web Agent Security Against Prompt Injection Attacks (4 citations)
and 93 more in the interactive map.
Human-AI and goal-conditioned · 57 papers
- MetaMind: Modeling Human Social Thoughts with Metacognitive Multi-Agent Systems (3 citations)
- AGC-Drive: A Large-Scale Dataset for Real-World Aerial-Ground Collaboration in Driving Scenarios (2 citations)
- Embodied Web Agents: Bridging Physical-Digital Realms for Integrated Agent Intelligence (2 citations)
- Learning 3D Persistent Embodied World Models (2 citations)
- TwinMarket: A Scalable Behavioral and Social Simulation for Financial Markets (2 citations)
- UrbanIng-V2X: A Large-Scale Multi-Vehicle, Multi-Infrastructure Dataset Across Multiple Intersections for Cooperative Perception (2 citations)
- Active Test-time Vision-Language Navigation (1 citation)
- CAML: Collaborative Auxiliary Modality Learning for Multi-Agent Systems (1 citation)
- CREA: A Collaborative Multi-Agent Framework for Creative Image Editing and Generation (1 citation)
- LabUtopia: High-Fidelity Simulation and Hierarchical Benchmark for Scientific Embodied Agents (1 citation)
- MindForge: Empowering Embodied Agents with Theory of Mind for Lifelong Cultural Learning (1 citation)
- Open-World Drone Active Tracking with Goal-Centered Rewards (1 citation)
and 45 more in the interactive map.
Cooperative multi-agent RL · 30 papers
- Adaptive Context Length Optimization with Low-Frequency Truncation for Multi-Agent Reinforcement Learning (2 citations)
- Bayesian Ego-graph inference for Networked Multi-Agent Reinforcement Learning (2 citations)
- A Principle of Targeted Intervention for Multi-Agent Reinforcement Learning (1 citation)
- Learning and Planning Multi-Agent Tasks via an MoE-based World Model (1 citation)
- MALinZero: Efficient Low-Dimensional Search for Mastering Complex Multi-Agent Planning (1 citation)
- Sequential Multi-Agent Dynamic Algorithm Configuration (1 citation)
- Bi-Level Knowledge Transfer for Multi-Task Multi-Agent Reinforcement Learning
- COGNAC: Cooperative Graph-based Networked Agent Challenges for Multi-Agent Reinforcement Learning
- Continuous Soft Actor-Critic: An Off-Policy Learning Method Robust to Time Discretization
- Effective Policy Learning for Multi-Agent Online Coordination Beyond Submodular Objectives
- Empirical Study on Robustness and Resilience in Cooperative Multi-Agent Reinforcement Learning
- High-order Interactions Modeling for Interpretable Multi-Agent Q-Learning
and 18 more in the interactive map.
Games and equilibria · 21 papers
- LOPT: Learning Optimal Pigovian Tax in Sequential Social Dilemmas (1 citation)
- On Feasible Rewards in Multi-Agent Inverse Reinforcement Learning (1 citation)
- A Cramér–von Mises Approach to Incentivizing Truthful Data Sharing
- Assignments for Congestion-Averse Agents: Seeking Competitive and Envy-Free Solutions
- Cooperative Bargaining Games Without Utilities: Mediated Solutions from Direction Oracles
- Evaluating LLMs in Open-Source Games
- Fair Cooperation in Mixed-Motive Games via Conflict-Aware Gradient Adjustment
- Impartial Selection with Predictions
- Incentivizing Desirable Effort Profiles in Strategic Classification: The Role of Causality and Uncertainty
- Learning Equilibria from Data: Provably Efficient Multi-Agent Imitation Learning
- Mechanism Design via the Interim Relaxation
- Multi-agent KTO: Enhancing Strategic Interactions of Large Language Model in Language Game
and 9 more in the interactive map.