Talk Structurally, Act Hierarchically: A Collaborative Refinement Framework for LLM Multi-Agent Systems

While recent advancements in Large Language Model-based Multi-Agent (LLM-MA) systems have shown promise, significant challenges remain in managing communication and refinement when agents collaborate on complex tasks. In this paper, we proposeTalk Structurally,Act Hierarchically (TalkHier), a novel framework that introduces a structured communication protocol for context-rich exchanges and a hierarchical refinement system to address issues such as incorrect outputs, falsehoods, and biases.TalkHiersurpasses various types of SoTA, including inference scaling model (OpenAI-o1), open-source multi-agent models (e.g., AgentVerse), and majority voting strategies on current LLM and single-agent baselines (e.g., ReAct, GPT4o), across diverse tasks, including open-domain question answering, domain-specific selective questioning, and practical advertisement text generation. These results highlight its potential to set a new standard for LLM-MA systems, paving the way for more effective, adaptable, and collaborative multi-agent frameworks. The source code is available athttps://github.com/sony/talkhier.