# The Ramon Llull's Thinking Machine for Automated Ideation

Source: [The Ramon Llull's Thinking Machine for Automated Ideation](<https://www.sota2.com/research/paper/68fa7b1d1e209131cea86a26>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-28T13:57:21.130Z

Authors: Xinran Zhao, Boyuan Zheng, Chenglei Si, Haofei Yu, Ken Liu, Runlong Zhou, Ruochen Li, Tong Chen, Xiang Li, Yiming Zhang, Tongshuang Wu

Published: 2025-08-26T17:03:43.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2508.19200>)

[PDF](<https://arxiv.org/pdf/2508.19200.pdf>)
