Chat-of-Thought: Collaborative Multi-Agent System for Generating Domain Specific Information

TL;DR

This paper introduces Chat-of-Thought, a multi-agent AI system that collaboratively generates and refines FMEA documents for industrial assets through dynamic, multi-role discussions among LLM-based agents.

Contribution

It presents a novel multi-agent framework with role-specific LLMs and dynamic task routing for improved FMEA document creation and validation.

Findings

Effective multi-agent collaboration for FMEA generation

Enhanced iterative refinement through multi-persona discussions

Potential for improved industrial asset analysis workflows

Abstract

This paper presents a novel multi-agent system called Chat-of-Thought, designed to facilitate the generation of Failure Modes and Effects Analysis (FMEA) documents for industrial assets. Chat-of-Thought employs multiple collaborative Large Language Model (LLM)-based agents with specific roles, leveraging advanced AI techniques and dynamic task routing to optimize the generation and validation of FMEA tables. A key innovation in this system is the introduction of a Chat of Thought, where dynamic, multi-persona-driven discussions enable iterative refinement of content. This research explores the application domain of industrial equipment monitoring, highlights key challenges, and demonstrates the potential of Chat-of-Thought in addressing these challenges through interactive, template-driven workflows and context-aware agent collaboration.