IM-Chat: A Multi-agent LLM-based Framework for Knowledge Transfer in Injection Molding Industry

2025-07-21

AI Summary

The injection molding industry faces critical knowledge loss due to the retirement of experienced workers and multilingual communication barriers on the shop floor. To address this, we propose IM-Chat—a modular, large language model (LLM)-based multi-agent framework that operates without fine-tuning and adapts dynamically to evolving production environments. IM-Chat integrates retrieval-augmented generation (RAG), a data-driven process condition generator, and a multi-agent coordination mechanism to enable context-aware reasoning and tool invocation over both documented knowledge and real-time shop-floor data. It achieves strong performance on both single-tool and hybrid tasks. Expert evaluation and automated benchmarks confirm a positive correlation between LLM capability and task accuracy. This work presents the first lightweight, fine-tuning-free multi-agent architecture specifically designed for injection molding knowledge transfer—significantly enhancing knowledge dissemination efficiency and system scalability.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Multiagent Systems: Agent Communication
• Cognitive Modeling & Cognitive Systems: Agent Architectures

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

Abstract

The injection molding industry faces critical challenges in preserving and transferring field knowledge, particularly as experienced workers retire and multilingual barriers hinder effective communication. This study introduces IM-Chat, a multi-agent framework based on large language models (LLMs), designed to facilitate knowledge transfer in injection molding. IM-Chat integrates both limited documented knowledge (e.g., troubleshooting tables, manuals) and extensive field data modeled through a data-driven process condition generator that infers optimal manufacturing settings from environmental inputs such as temperature and humidity, enabling robust and context-aware task resolution. By adopting a retrieval-augmented generation (RAG) strategy and tool-calling agents within a modular architecture, IM-Chat ensures adaptability without the need for fine-tuning. Performance was assessed across 100 single-tool and 60 hybrid tasks for GPT-4o, GPT-4o-mini, and GPT-3.5-turbo by domain experts using a 10-point rubric focused on relevance and correctness, and was further supplemented by automated evaluation using GPT-4o guided by a domain-adapted instruction prompt. The evaluation results indicate that more capable models tend to achieve higher accuracy, particularly in complex, tool-integrated scenarios. Overall, these findings demonstrate the viability of multi-agent LLM systems for industrial knowledge workflows and establish IM-Chat as a scalable and generalizable approach to AI-assisted decision support in manufacturing.

Problem

• Addressing knowledge loss in injection molding due to retiring experts
• Overcoming multilingual barriers in industrial knowledge communication
• Optimizing manufacturing settings from environmental inputs automatically

Innovation

• Multi-agent LLM framework for knowledge transfer
• Data-driven process condition generator integration
• Retrieval-augmented generation without fine-tuning