NeurIPS 2024 accepted papers on Multi-agent systems and games
119 of the 4,560 papers accepted at NeurIPS 2024 (2.6%) are on Multi-agent systems and games, compared with 2.4% at NeurIPS 2023. They fall into 4 topics.
See NeurIPS 2024 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
Human-AI and goal-conditioned · 45 papers
- DeMo: Decoupling Motion Forecasting into Directional Intentions and Dynamic States (18 citations)
- SMART: Scalable Multi-agent Real-time Motion Generation via Next-token Prediction (12 citations)
- Reasoning Multi-Agent Behavioral Topology for Interactive Autonomous Driving (10 citations)
- BehaviorGPT: Smart Agent Simulation for Autonomous Driving with Next-Patch Prediction (8 citations)
- Long-Horizon Planning for Multi-Agent Robots in Partially Observable Environments (7 citations)
- AuctionNet: A Novel Benchmark for Decision-Making in Large-Scale Games (6 citations)
- Language Grounded Multi-agent Reinforcement Learning with Human-interpretable Communication (6 citations)
- CooHOI: Learning Cooperative Human-Object Interaction with Manipulated Object Dynamics (5 citations)
- WorldCoder, a Model-Based LLM Agent: Building World Models by Writing Code and Interacting with the Environment (5 citations)
- Agent Planning with World Knowledge Model (4 citations)
- Trajectory Diffusion for ObjectGoal Navigation (4 citations)
- Latent Learning Progress Drives Autonomous Goal Selection in Human Reinforcement Learning (3 citations)
and 33 more in the interactive map.
LLM agents · 30 papers
- AgentPoison: Red-teaming LLM Agents via Poisoning Memory or Knowledge Bases (49 citations)
- OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments (39 citations)
- FinCon: A Synthesized LLM Multi-Agent System with Conceptual Verbal Reinforcement for Enhanced Financial Decision Making (37 citations)
- SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering (30 citations)
- Mobile-Agent-v2: Mobile Device Operation Assistant with Effective Navigation via Multi-Agent Collaboration (26 citations)
- Reflective Multi-Agent Collaboration based on Large Language Models (24 citations)
- Multi-LLM Debate: Framework, Principals, and Interventions (23 citations)
- Can Large Language Model Agents Simulate Human Trust Behavior? (21 citations)
- Cooperation, Competition, and Maliciousness: LLM-Stakeholders Interactive Negotiation (15 citations)
- Secret Collusion among AI Agents: Multi-Agent Deception via Steganography (12 citations)
- AgentBoard: An Analytical Evaluation Board of Multi-turn LLM Agents (11 citations)
- Richelieu: Self-Evolving LLM-Based Agents for AI Diplomacy (11 citations)
and 18 more in the interactive map.
Games and equilibria · 23 papers
- Contracting with a Learning Agent (5 citations)
- Bayesian Strategic Classification (3 citations)
- Multi-Agent Imitation Learning: Value is Easy, Regret is Hard (3 citations)
- Learning to Discuss Strategically: A Case Study on One Night Ultimate Werewolf (2 citations)
- Aligning Individual and Collective Objectives in Multi-Agent Cooperation (1 citation)
- Automating Data Annotation under Strategic Human Agents: Risks and Potential Solutions (1 citation)
- Bias Detection via Signaling (1 citation)
- Learning to Balance Altruism and Self-interest Based on Empathy in Mixed-Motive Games (1 citation)
- Learning to Mitigate Externalities: the Coase Theorem with Hindsight Rationality (1 citation)
- Maximizing utility in multi-agent environments by anticipating the behavior of other learners (1 citation)
- Aggregating Quantitative Relative Judgments: From Social Choice to Ranking Prediction
- Can an AI Agent Safely Run a Government? Existence of Probably Approximately Aligned Policies
and 11 more in the interactive map.
Cooperative multi-agent RL · 21 papers
- MADiff: Offline Multi-agent Learning with Diffusion Models (8 citations)
- JaxMARL: Multi-Agent RL Environments and Algorithms in JAX (7 citations)
- Randomized Exploration in Cooperative Multi-Agent Reinforcement Learning (7 citations)
- WFCRL: A Multi-Agent Reinforcement Learning Benchmark for Wind Farm Control (7 citations)
- BenchMARL: Benchmarking Multi-Agent Reinforcement Learning (5 citations)
- SustainDC: Benchmarking for Sustainable Data Center Control (5 citations)
- Scalable Constrained Policy Optimization for Safe Multi-agent Reinforcement Learning (4 citations)
- Multi-Agent Coordination via Multi-Level Communication (3 citations)
- Kaleidoscope: Learnable Masks for Heterogeneous Multi-agent Reinforcement Learning (1 citation)
- Learning Distinguishable Trajectory Representation with Contrastive Loss (1 citation)
- Measuring Mutual Policy Divergence for Multi-Agent Sequential Exploration (1 citation)
- Mimicking To Dominate: Imitation Learning Strategies for Success in Multiagent Games (1 citation)
and 9 more in the interactive map.