2025-10-07 横浜市立大学
図１ SELLMのフロー
最初に、知識や技術を網羅するリストから各知識を１つずつ取り出し、その知識に関する「専門家」として振る舞うよう、LLMにテキストベースで指示する。次に、それぞれの「専門家」に対し課題を与え、解決策を提案させる。
＜関連情報＞
- https://www.yokohama-cu.ac.jp/res-portal/news/20251007terayama.html
- https://www.nature.com/articles/s43246-025-00946-5
生成された包括的な専門家を介して大規模言語モデルに隠された効果的な解決策を抽出する：電子機器の開発におけるケーススタディ Extracting effective solutions hidden in large language models via generated comprehensive specialists: case studies in developing electronic devices
Hikari Tomita,Nobuhiro Nakamura,Shoichi Ishida,Toshio Kamiya & Kei Terayama
Communications Materials Published:06 October 2025
DOI:https://doi.org/10.1038/s43246-025-00946-5
Abstract
Recently, the use of large-scale language models (LLMs) for generating research ideas and constructing scientific hypotheses has been gaining significant attention. 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.
