multi-agent systems
AI systems comprised of multiple interacting agents that can cooperate, compete, or coordinate to solve complex problems, often inspired by social behaviors observed in nature.
- AgentBreeder: Mitigating the AI Safety Risks of Multi-Agent Scaffolds via Self-Improvement
- AgentNet: Decentralized Evolutionary Coordination for LLM-based Multi-Agent Systems
- Automated Composition of Agents: A Knapsack Approach for Agentic Component Selection
- Breaking the Performance Ceiling in Reinforcement Learning requires Inference Strategies
- Breaking the Performance Ceiling in Reinforcement Learning requires Inference Strategies
- ChemX: A Collection of Chemistry Datasets for Benchmarking Automated Information Extraction
- G-Memory: Tracing Hierarchical Memory for Multi-Agent Systems
- HMARL-CBF – Hierarchical Multi-Agent Reinforcement Learning with Control Barrier Functions for Safety-Critical Autonomous Systems
- Individual Regret in Cooperative Stochastic Multi-Armed Bandits
- KARMA: Leveraging Multi-Agent LLMs for Automated Knowledge Graph Enrichment
- KVCOMM: Online Cross-context KV-cache Communication for Efficient LLM-based Multi-agent Systems
- Large Language Models Miss the Multi-agent Mark
- Many LLMs Are More Utilitarian Than One
- Multi-Agent Imitation by Learning and Sampling from Factorized Soft Q-Function
- Multi-Agent Reinforcement Learning with Communication-Constrained Priors
- OWL: Optimized Workforce Learning for General Multi-Agent Assistance in Real-World Task Automation
- On Feasible Rewards in Multi-Agent Inverse Reinforcement Learning
- PARCO: Parallel AutoRegressive Models for Multi-Agent Combinatorial Optimization
- R&D-Agent-Quant: A Multi-Agent Framework for Data-Centric Factors and Model Joint Optimization
- Rainbow Delay Compensation: A Multi-Agent Reinforcement Learning Framework for Mitigating Observation Delays
- Regret Lower Bounds for Decentralized Multi-Agent Stochastic Shortest Path Problems
- Regret-Optimal Q-Learning with Low Cost for Single-Agent and Federated Reinforcement Learning
- Shapley-Coop: Credit Assignment for Emergent Cooperation in Self-Interested LLM Agents
- SiriuS: Self-improving Multi-agent Systems via Bootstrapped Reasoning
- Solving Continuous Mean Field Games: Deep Reinforcement Learning for Non-Stationary Dynamics
- Stackelberg Learning with Outcome-based Payment
- Thought Communication in Multiagent Collaboration
- Towards Principled Unsupervised Multi-Agent Reinforcement Learning