ICML 2024 accepted papers on Multi-agent systems and games

LLM agents · 15 papers

• Executable Code Actions Elicit Better LLM Agents (10 citations)
• Language Agent Tree Search Unifies Reasoning, Acting, and Planning in Language Models (10 citations)
• MLAgentBench: Evaluating Language Agents on Machine Learning Experimentation (9 citations)
• Language Agents with Reinforcement Learning for Strategic Play in the Werewolf Game (8 citations)
• CompeteAI: Understanding the Competition Dynamics of Large Language Model-based Agents (7 citations)
• Should we be going MAD? A Look at Multi-Agent Debate Strategies for LLMs (5 citations)
• Agent Smith: A Single Image Can Jailbreak One Million Multimodal LLM Agents Exponentially Fast (4 citations)
• WorkArena: How Capable are Web Agents at Solving Common Knowledge Work Tasks? (2 citations)
• AnyTool: Self-Reflective, Hierarchical Agents for Large-Scale API Calls (1 citation)
• MAGDi: Structured Distillation of Multi-Agent Interaction Graphs Improves Reasoning in Smaller Language Models (1 citation)
• diff History for Neural Language Agents
• From Words to Actions: Unveiling the Theoretical Underpinnings of LLM-Driven Autonomous Systems

and 3 more in the interactive map.

Human-AI and goal-conditioned · 15 papers

• RoboGen: Towards Unleashing Infinite Data for Automated Robot Learning via Generative Simulation (10 citations)
• Learning to Model the World With Language (3 citations)
• BAGEL: Bootstrapping Agents by Guiding Exploration with Language (2 citations)
• Advancing DRL Agents in Commercial Fighting Games: Training, Integration, and Agent-Human Alignment (1 citation)
• Building Socially-Equitable Public Models (1 citation)
• AD3: Implicit Action is the Key for World Models to Distinguish the Diverse Visual Distractors
• Dr. Strategy: Model-Based Generalist Agents with Strategic Dreaming
• Improving Token-Based World Models with Parallel Observation Prediction
• Position: Beyond Personhood: Agency, Accountability, and the Limits of Anthropomorphic Ethical Analysis
• Position: Towards Unified Alignment Between Agents, Humans, and Environment
• Deep Demonstration Tracing: Learning Generalizable Imitator Policy for Runtime Imitation from a Single Demonstration
• Learning to Explore in POMDPs with Informational Rewards

and 3 more in the interactive map.

Cooperative multi-agent RL · 15 papers

• Locally Interdependent Multi-Agent MDP: Theoretical Framework for Decentralized Agents with Dynamic Dependencies (4 citations)
• Major-Minor Mean Field Multi-Agent Reinforcement Learning (3 citations)
• Controlling Behavioral Diversity in Multi-Agent Reinforcement Learning (2 citations)
• LAGMA: LAtent Goal-guided Multi-Agent Reinforcement Learning (1 citation)
• Optimistic Multi-Agent Policy Gradient (1 citation)
• ${\rm E}(3)$-Equivariant Actor-Critic Methods for Cooperative Multi-Agent Reinforcement Learning
• FightLadder: A Benchmark for Competitive Multi-Agent Reinforcement Learning
• Individual Contributions as Intrinsic Exploration Scaffolds for Multi-agent Reinforcement Learning
• Multi-Agent Reinforcement Learning Meets Leaf Sequencing in Radiotherapy
• Multi-Agent Reinforcement Learning with Hierarchical Coordination for Emergency Responder Stationing
• Open Ad Hoc Teamwork with Cooperative Game Theory
• Detecting Influence Structures in Multi-Agent Reinforcement Learning

and 3 more in the interactive map.

Games and equilibria · 8 papers

• Impact of Decentralized Learning on Player Utilities in Stackelberg Games (1 citation)
• Configurable Mirror Descent: Towards a Unification of Decision Making
• Fast Peer Adaptation with Context-aware Exploration
• Mastering Zero-Shot Interactions in Cooperative and Competitive Simultaneous Games
• Multi-Sender Persuasion: A Computational Perspective
• Sample-Efficient Robust Multi-Agent Reinforcement Learning in the Face of Environmental Uncertainty
• Zero-Sum Positional Differential Games as a Framework for Robust Reinforcement Learning: Deep Q-Learning Approach
• Agent-Specific Effects: A Causal Effect Propagation Analysis in Multi-Agent MDPs