让大模型团队协作更高效：结构化对话+分层纠错
Talk Structurally, Act Hierarchically: A Collaborative Framework for LLM Multi-Agent Systems
- 用结构化协议让多智能体高效沟通，避免信息混乱
- 分层修正机制显著减少错误输出与偏见，准确率提升明显
- 适合复杂任务场景，如问答、广告生成，可直接落地
基于大模型的多智能体系统虽有进展，但在复杂任务中仍面临沟通混乱与结果偏差问题。本文提出「TalkHier」框架，通过结构化通信协议实现上下文丰富的信息交换，并引入分层修正机制，有效缓解错误输出、虚假信息和偏见。该框架在开放域问答、领域特定提问及广告文案生成等多样任务中，超越包括OpenAI-o1、AgentVerse在内的多种当前最先进模型，以及ReAct、GPT4o等单智能体基线方法。实验表明其具备成为新一代多智能体系统标准的潜力，代码已开源。
原文摘要 · Abstract (English)
Recent advancements in LLM-based multi-agent (LLM-MA) systems have shown promise, yet significant challenges remain in managing communication and refinement when agents collaborate on complex tasks. In this paper, we propose \textit{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. \textit{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 code is available https://github.com/sony/talkhier.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。