The paper introduces Coordination Graphs for Constrained Multi-Agent Reinforcement Learning (CG-CMARL), a scalable framework that decomposes complex joint action spaces into pairwise regions to handle…

The paper proposes a Network Distributed Multi-Agent Reinforcement Learning (ND-MARL) framework that enables stable, scalable consensus control for large swarms of quadcopters using only local neighbo…

The paper evaluates dynamic coordination strategy selection for enterprise multi-agent systems, finding that a calibrated default routing approach is effective, even if a deterministic winner-selectio…

This paper characterizes Pure Nash Equilibria and presents a polynomial-time algorithm for finding them in the Intermittent Strategic Cooperation-Based Two-Agent Path Planning game.

This paper proposes a method for multi-agent systems that allows human managers to control learned agents through simple instructions and enables uninstructed agents to adaptively complement overlooke…

The paper proposes a scalable, distributed approach for constrained Multi-Agent Reinforcement Learning by using local consensus over dual variables to ensure global constraint satisfaction without cen…

This paper systematically studies the potential of prompt optimization in multi-agent systems (MAS) across various setups, revealing significant gains but also open challenges.

This paper explores tools for control engineers to design socio-technical systems in a more principled and ethical manner, using feedback optimization, control of Markov decision processes, and model…

This paper provides an information bottleneck perspective on the differences between single-agent and multi-agent systems, showing that the advantage of MAS arises under bounded relays and introducing…

This paper investigates the scaling behavior of homogeneous LLM-driven Multi-Agent Systems (MAS) and finds that performance exhibits diminishing returns due to coordination overhead, rather than scali…

This paper proposes a method for ensuring safety in multi-agent reinforce learning through decentralized execution, using a shared global specification and a non-stationary multi-armed bandit.

The paper proposes Multi-Agent Computer Use (MACU) systems, which significantly improve performance on complex, long-horizon tasks by enabling parallel execution and dynamic task decomposition compare…

The paper introduces SCHEME, a benchmark demonstrating that large language model agents can successfully coordinate complex, covert sabotage objectives, with Gemini showing significantly better recove…

The paper proposes TCP-MCP, a co-evolution framework that jointly optimizes agent prompts and communication topologies to design highly efficient and effective multi-agent systems.

Restructuring the communication topology among robots provides significantly greater performance gains in multi-robot coordination than simply increasing the size of the onboard AI models, given fixed…