Multi-agent coordination improves with responsibility-centered commitments

A Responsibility-Centered Coordination Mechanism for Decentralized Multi-Agent Systems

Multiagent SystemsArtificial Intelligence

Summary

Coordinating many agents (like robots or software programs) is tricky because centralized control can get overwhelmed, while fully decentralized setups can lose track of who is responsible for tasks. The authors propose a new method called RCM that ties task delegation to clear responsibilities using commitments between agents. This way, even when tasks are handed down many times, everyone stays accountable, and agents coordinate on their own without a central boss. Tests showed RCM leads to better task success and detects failures more reliably than existing approaches.

What this means in practice

  • For robotics engineers: Enable robots to share and manage tasks autonomously while maintaining clear responsibilities to improve teamwork and reduce coordination failures.
  • For distributed software developers: Implement responsibility-aware protocols in software agents to boost reliable task coordination and failure recovery without a central controller.

Authors

Thi-Nhung Nguyen, Viet-Thanh Pham, Linhao Luo, Thuy-Trang Vu, Dinh Phung

Abstract

Centralized orchestration provides comprehensive multi-agent coordination but creates bottlenecks in scalability, adaptability, and collective performance. Decentralized approaches alleviate these bottlenecks by distributing coordination across agents, yet often leave responsibility for delegated dependencies and failure recovery unclear. To address this gap, we propose RCM, a responsibility-centered coordination mechanism that leverages commitments to couple task delegation with explicit responsibilities of the involved parties. Through recursive delegation, agents retain their upstream responsibilities while locally orchestrating downstream commitments, thereby preserving accountability across delegation chains, creating a network of local orchestration. We operationalize this mechanism locally through responsibility-constrained decision-making and a responsibility-oriented communication protocol (RCP), enabling agents to autonomously establish, manage, and terminate commitments. As agents act in parallel, their local actions continuously evolve the commitment graph, allowing global coordination to emerge and adapt toward a shared mission without centralized control. Experiments across reasoning, coding, and executable agent environments demonstrate that RCM outperforms strong centralized and decentralized coordination baselines by up to 18.7 points in task performance and 10.2 points in Responsibility, while improving failure and harm detection without task-specific training.