The Ramon Llull's Thinking Machine for Automated Ideation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918134799138816 |
|---|---|
| author | Zhao, Xinran Zheng, Boyuan Si, Chenglei Yu, Haofei Liu, Ken Zhou, Runlong Li, Ruochen Chen, Tong Li, Xiang Zhang, Yiming Wu, Tongshuang |
| author_facet | Zhao, Xinran Zheng, Boyuan Si, Chenglei Yu, Haofei Liu, Ken Zhou, Runlong Li, Ruochen Chen, Tong Li, Xiang Zhang, Yiming Wu, Tongshuang |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_19200 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | The Ramon Llull's Thinking Machine for Automated Ideation Zhao, Xinran Zheng, Boyuan Si, Chenglei Yu, Haofei Liu, Ken Zhou, Runlong Li, Ruochen Chen, Tong Li, Xiang Zhang, Yiming Wu, Tongshuang Artificial Intelligence Computation and Language 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. |
| title | The Ramon Llull's Thinking Machine for Automated Ideation |
| topic | Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2508.19200 |