Decentralized Collaborative Reasoning with Communication-Constrained Multi-Agent Large Language Models for Multi-Domain Dialogue Systems
TL;DR
Experimental results demonstrate that the proposed method outperforms single-agent and centralized coordination baselines, achieving a 15% improvement in task success rate and a 20% reduction in communication cost, indicating that communication-efficient decentralized coordination significantly enhances both efficiency and robustness.
Abstract
Large language model (LLM)-based multi-agent systems show strong potential for supporting complex reasoning and decision-making in dialogue tasks. However, existing systems often rely on centralized coordination or uncontrolled inter-agent communication, which can limit scalability and increase communication overhead in multi-domain task-oriented dialogue environments. In this paper, we propose a decentralized multi-agent framework that combines role-based collaboration with communication-efficient coordination, enabling agents to operate effectively under constrained token budgets. The proposed approach aims to improve scalability, reduce communication cost, and enhance task success across diverse dialogue domains. Experimental results demonstrate that the proposed method outperforms single-agent and centralized coordination baselines, achieving a 15% improvement in task success rate and a 20% reduction in communication cost. These findings indicate that communication-efficient decentralized coordination significantly enhances both efficiency and robustness. Overall, the proposed architecture provides a practical and scalable solution for multi-domain task-oriented dialogue systems, particularly in resource-constrained environments.