This paper revisits Ramon Llull's Ars combinatoria - a medieval framework for generating knowledge through symbolic recombination - as a conceptual foundation for building a modern Llull's thinking machine for research ideation. Our approach defines three compositional axes: Theme (e.g., efficiency, adaptivity), Domain (e.g., question answering, machine translation), and Method (e.g., adversarial training, linear attention). These elements represent high-level abstractions common in scientific work - motivations, problem settings, and technical approaches - and serve as building blocks for LLM-driven exploration. We mine elements from human experts or conference papers and show that prompting LLMs with curated combinations produces research ideas that are diverse, relevant, and grounded in current literature. This modern thinking machine offers a lightweight, interpretable tool for augmenting scientific creativity and suggests a path toward collaborative ideation between humans and AI.
@article{arxiv.2508.19200,
title = {The Ramon Llull's Thinking Machine for Automated Ideation},
author = {Xinran Zhao and Boyuan Zheng and Chenglei Si and Haofei Yu and Ken Liu and Runlong Zhou and Ruochen Li and Tong Chen and Xiang Li and Yiming Zhang and Tongshuang Wu},
journal= {arXiv preprint arXiv:2508.19200},
year = {2025}
}