Talk Structurally, Act Hierarchically: A Collaborative Refinement Framework for LLM Multi-Agent Systems
Top Cited Papers
- 20 March 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Artificial Intelligence
- Vol. PP (9) , 1-11
Abstract
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 propose Talk 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. TalkHier surpasses 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 at https://github.com/sony/talkhier.Keywords
This publication has 17 references indexed in Scilit:
- Exploring Large Language Model‐Based Intelligent Agents: Definitions, Methods, and ProspectsWIREs Data Mining and Knowledge Discovery, 2026
- The rise and potential of large language model based agents: a surveyScience China Information Sciences, 2025
- A survey on LLM-based multi-agent systems: workflow, infrastructure, and challengesVicinagearth, 2024
- Idea2Img: Iterative Self-refinement with GPT-4V for Automatic Image Design and Generation2024
- Large language models empowered agent-based modeling and simulation: a survey and perspectivesHumanities and Social Sciences Communications, 2024
- A Multimodal Foundation Agent for Financial Trading: Tool-Augmented, Diversified, and Generalist2024
- A survey on large language model based autonomous agentsFrontiers of Computer Science, 2024
- Rethinking the Bounds of LLM Reasoning: Are Multi-Agent Discussions the Key?2024
- Striking Gold in Advertising: Standardization and Exploration of Ad Text Generation2024
- coeval, adj. & n.2023