# The Ramon Llull's Thinking Machine for Automated Ideation

arXiv: https://arxiv.org/abs/2508.19200 · HTML: https://mlsanity.com/paper/2508.19200/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 17 of its 51 references that are in the map.
- First posted on arXiv 26 Aug 2025.

## Placed in

- LLM reasoning / [Reasoning benchmarks and evaluation](https://mlsanity.com/lr/reasoning-benchmarks-and-evaluation/)

## Builds on (most cited first, 17 of 17)

- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://mlsanity.com/paper/2403.05530/) (2024)
- [A Diversity-Promoting Objective Function for Neural Conversation Models](https://mlsanity.com/paper/1510.03055/) (2015)
- [Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets](https://mlsanity.com/paper/2201.02177/) (2022)
- [Gradient Descent on Neural Networks Typically Occurs at the Edge of Stability](https://mlsanity.com/paper/2103.00065/) (2021)
- [Repairing the Cracked Foundation: A Survey of Obstacles in Evaluation Practices for Generated Text](https://mlsanity.com/paper/2202.06935/) (2022)
- [MATH-Perturb: Benchmarking LLMs' Math Reasoning Abilities against Hard Perturbations](https://mlsanity.com/paper/2502.06453/) (2025)
- [NoveltyBench: Evaluating Language Models for Humanlike Diversity](https://mlsanity.com/paper/2504.05228/) (2025)
- [The Ideation-Execution Gap: Execution Outcomes of LLM-Generated versus Human Research Ideas](https://mlsanity.com/paper/2506.20803/) (2025)
- [CodeScientist: End-to-End Semi-Automated Scientific Discovery with Code-based Experimentation](https://mlsanity.com/paper/2503.22708/) (2025)
- [Human-LLM Compound System for Scientific Ideation through Facet Recombination and Novelty Evaluation](https://mlsanity.com/paper/2409.14634/) (2024)
- [ResearchTown: Simulator of Human Research Community](https://mlsanity.com/paper/2412.17767/) (2024)
- [Ai2 Scholar QA: Organized Literature Synthesis with Attribution](https://mlsanity.com/paper/2504.10861/) (2025)
- [An Open Review of OpenReview: A Critical Analysis of the Machine Learning Conference Review Process](https://mlsanity.com/paper/2010.05137/) (2020)
- [A Reply to Makelov et al. (2023)'s "Interpretability Illusion" Arguments](https://mlsanity.com/paper/2401.12631/) (2024)
- [Taxonomy-guided Semantic Indexing for Academic Paper Search](https://mlsanity.com/paper/2410.19218/) (2024)
- [CHIMERA: A Knowledge Base of Scientific Idea Recombinations for Research Analysis and Ideation](https://mlsanity.com/paper/2505.20779/) (2025)

## Built on by (most cited first, 3 of 3)

- [GIANTS: Generative Insight Anticipation from Scientific Literature](https://mlsanity.com/paper/2604.09793/) (2026)
- [Can Large Language Models Forecast What Researchers Study Next?](https://mlsanity.com/paper/2609.00747/) (2026)
- [Priced Guidance: Can Language Models Generate Future Research Ideas?](https://mlsanity.com/paper/2610.04976/) (2026)

## Abstract (arXiv)

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.