Extracting effective solutions hidden in large language models via generated comprehensive specialists: case studies in developing electronic devices

2024-12-31

AI Summary

Integrating interdisciplinary knowledge remains a critical challenge in electronic device R&D. Method: This paper proposes SELLM—a structured, expert-guided framework that leverages the MECE principle (e.g., IPC classification, periodic table) to construct domain-specific knowledge inventories, enabling large language models (LLMs) to orchestrate multi-disciplinary “expert agents” for targeted, interpretable solution generation. Unlike generic prompting, SELLM introduces a novel paradigm of structured-knowledge-driven solution enumeration. Contribution/Results: Evaluated on OLED light-extraction optimization and novel memristor electrode design, SELLM generated multiple expert-validated, technically feasible solutions—demonstrating significantly broader disciplinary coverage and higher solution feasibility than baseline LLMs without domain-customized prompting. The framework establishes a reusable methodology for deploying LLMs in complex, interdisciplinary engineering innovation.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Search and Optimization: Mixed Discrete/Continuous Search
• Multiagent Systems: Mechanism Design

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Uses of LLMs and GenAI for marketplace design, bidding, and strategic interactions
• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information

Abstract

Recently, many studies have increasingly explored the use of large language models (LLMs) to generate research ideas and scientific hypotheses. However, real-world research and development often require solving complex, interdisciplinary challenges where solutions may not be readily found through existing knowledge related to the problem. Therefore, it is desirable to leverage the vast, comprehensive knowledge of LLMs to generate effective, breakthrough solutions by integrating various perspectives from other disciplines. Here, we propose SELLM (Solution Enumeration via comprehensive List and LLM), a framework leveraging LLMs and structured guidance using MECE (Mutually Exclusive, Collectively Exhaustive) principles, such as International Patent Classification (IPC) and the periodic table of elements. SELLM systematically constructs comprehensive expert agents from the list to generate cross-disciplinary and effective solutions. To evaluate SELLM's practicality, we applied it to two challenges: improving light extraction in organic light-emitting diode (OLED) lighting and developing electrodes for next-generation memory materials. The results demonstrate that SELLM significantly facilitates the generation of effective solutions compared to cases without specific customization or effort, showcasing the potential of SELLM to enable LLMs to generate effective solutions even for challenging problems.

Problem

• Large Language Models
• Interdisciplinary Understanding
• Electronic Devices

Innovation

• SELLM
• Interdisciplinary Problem Solving
• Large Language Model Integration