面向多智能体大语言模型系统的分层思维链提示：迈向可解释大语言模型的综合方法
Layered Chain-of-Thought Prompting for Multi-Agent LLM Systems: A Comprehensive Approach to Explainable Large Language Models
AI总结：
本文提出分层思维链提示框架，将大语言模型推理过程分层并引入外部检查与用户反馈，在医疗分诊、金融风险评估和敏捷工程等场景中提升多智能体系统的透明度、正确性与用户参与度。
摘要：
大语言模型（LLMs）利用思维链（CoT）提示来提供逐步推理依据，从而提升在复杂任务上的表现。尽管思维链具有诸多优势，但原始思维链（vanilla CoT）往往无法充分验证中间推理过程，并且可能产生具有误导性的解释。在本工作中，我们提出了分层思维链（Layered-CoT）提示，这是一个新颖的框架，它将推理过程系统地划分为多个层次，每一层都接受外部检查以及可选的用户反馈。我们扩展了关键概念，展示了三个场景——医疗分诊、金融风险评估和敏捷工程——并证明了分层思维链在透明度、正确性和用户参与度方面优于原始思维链。通过整合近期 arXiv 论文中关于交互式可解释性、多智能体框架以及基于智能体的协作的参考文献，我们说明了分层思维链如何为高风险领域中更可靠、更有依据的解释铺平道路。
英文摘要：
Large Language Models (LLMs) leverage chain-of-thought (CoT) prompting to provide step-by-step rationales, improving performance on complex tasks. Despite its benefits, vanilla CoT often fails to fully verify intermediate inferences and can produce misleading explanations. In this work, we propose Layered Chain-of-Thought (Layered-CoT) Prompting, a novel framework that systematically segments the reasoning process into multiple layers, each subjected to external checks and optional user feedback. We expand on the key concepts, present three scenarios -- medical triage, financial risk assessment, and agile engineering -- and demonstrate how Layered-CoT surpasses vanilla CoT in terms of transparency, correctness, and user engagement. By integrating references from recent arXiv papers on interactive explainability, multi-agent frameworks, and agent-based collaboration, we illustrate how Layered-CoT paves the way for more reliable and grounded explanations in high-stakes domains.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
