ICLR 2024 accepted papers on Multi-agent systems and games
53 of the 2,259 papers accepted at ICLR 2024 (2.3%) are on Multi-agent systems and games, compared with 2.3% at ICLR 2023. They fall into 4 topics.
See ICLR 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 · 24 papers
- AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors (26 citations)
- Habitat 3.0: A Co-Habitat for Humans, Avatars, and Robots (15 citations)
- Motif: Intrinsic Motivation from Artificial Intelligence Feedback (6 citations)
- Multimodal Web Navigation with Instruction-Finetuned Foundation Models (6 citations)
- Robust agents learn causal world models (5 citations)
- SOTOPIA: Interactive Evaluation for Social Intelligence in Language Agents (4 citations)
- An Extensible Framework for Open Heterogeneous Collaborative Perception (2 citations)
- HAZARD Challenge: Embodied Decision Making in Dynamically Changing Environments (2 citations)
- Modeling Boundedly Rational Agents with Latent Inference Budgets (2 citations)
- Skill Machines: Temporal Logic Skill Composition in Reinforcement Learning (2 citations)
- Designing Skill-Compatible AI: Methodologies and Frameworks in Chess (1 citation)
- GROOT: Learning to Follow Instructions by Watching Gameplay Videos (1 citation)
and 12 more in the interactive map.
Cooperative multi-agent RL · 11 papers
- Learning Multi-Agent Communication from Graph Modeling Perspective (4 citations)
- Efficient Episodic Memory Utilization of Cooperative Multi-Agent Reinforcement Learning (3 citations)
- Maximum Entropy Heterogeneous-Agent Reinforcement Learning (3 citations)
- Attention-Guided Contrastive Role Representations for Multi-agent Reinforcement Learning (2 citations)
- Byzantine Robust Cooperative Multi-Agent Reinforcement Learning as a Bayesian Game (2 citations)
- Efficient Multi-agent Reinforcement Learning by Planning (1 citation)
- Learning Decentralized Partially Observable Mean Field Control for Artificial Collective Behavior (1 citation)
- Learning Multi-Agent Communication with Contrastive Learning
- On the Hardness of Constrained Cooperative Multi-Agent Reinforcement Learning
- Solving Homogeneous and Heterogeneous Cooperative Tasks with Greedy Sequential Execution
- Whittle Index with Multiple Actions and State Constraint for Inventory Management
LLM agents · 10 papers
- MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework (153 citations)
- ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate (55 citations)
- AgentBench: Evaluating LLMs as Agents (53 citations)
- Building Cooperative Embodied Agents Modularly with Large Language Models (39 citations)
- Identifying the Risks of LM Agents with an LM-Emulated Sandbox (6 citations)
- Retroformer: Retrospective Large Language Agents with Policy Gradient Optimization (5 citations)
- Steve-Eye: Equipping LLM-based Embodied Agents with Visual Perception in Open Worlds (3 citations)
- Synapse: Trajectory-as-Exemplar Prompting with Memory for Computer Control (3 citations)
- Towards Robust Multi-Modal Reasoning via Model Selection (1 citation)
- WebArena: A Realistic Web Environment for Building Autonomous Agents
Games and equilibria · 8 papers
- A Black-box Approach for Non-stationary Multi-agent Reinforcement Learning
- Learning in reverse causal strategic environments with ramifications on two sided markets
- Learning Mean Field Games on Sparse Graphs: A Hybrid Graphex Approach
- LOQA: Learning with Opponent Q-Learning Awareness
- Online Information Acquisition: Hiring Multiple Agents
- Provable Memory Efficient Self-Play Algorithm for Model-free Reinforcement Learning
- Sample-Efficient Multi-Agent RL: An Optimization Perspective
- Achieving Fairness in Multi-Agent MDP Using Reinforcement Learning