# Sparking Scientific Creativity via LLM-Driven Interdisciplinary Inspiration

arXiv: https://arxiv.org/abs/2603.12226 · HTML: https://mlsanity.com/paper/2603.12226/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 48 references that are in the map.
- First posted on arXiv 12 Mar 2026.

## Builds on (most cited first, 14 of 14)

- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [gpt-oss-120b & gpt-oss-20b Model Card](https://mlsanity.com/paper/2508.10925/) (2025)
- [Can LLMs Generate Novel Research Ideas? A Large-Scale Human Study with 100+ NLP Researchers](https://mlsanity.com/paper/2409.04109/) (2024)
- [SciMON: Scientific Inspiration Machines Optimized for Novelty](https://mlsanity.com/paper/2305.14259/) (2023)
- [The Semantic Scholar Open Data Platform](https://mlsanity.com/paper/2301.10140/) (2023)
- [The Ideation-Execution Gap: Execution Outcomes of LLM-Generated versus Human Research Ideas](https://mlsanity.com/paper/2506.20803/) (2025)
- [IdeaSynth: Iterative Research Idea Development Through Evolving and Composing Idea Facets with Literature-Grounded Feedback](https://mlsanity.com/paper/2410.04025/) (2024)
- [Training AI Co-Scientists Using Rubric Rewards](https://mlsanity.com/paper/2512.23707/) (2025)
- [Cognitive Foundations for Reasoning and Their Manifestation in LLMs](https://mlsanity.com/paper/2511.16660/) (2025)
- [TaxoAdapt: Aligning LLM-Based Multidimensional Taxonomy Construction to Evolving Research Corpora](https://mlsanity.com/paper/2506.10737/) (2025)
- [DiscipLink: Unfolding Interdisciplinary Information Seeking Process via Human-AI Co-Exploration](https://mlsanity.com/paper/2408.00447/) (2024)
- [Automatic Evaluation of Generative Models with Instruction Tuning](https://mlsanity.com/paper/2310.20072/) (2023)
- [Idea2Plan: Exploring AI-Powered Research Planning](https://mlsanity.com/paper/2510.24891/) (2025)
- [Beyond True or False: Retrieval-Augmented Hierarchical Analysis of Nuanced Claims](https://mlsanity.com/paper/2506.10728/) (2025)

## Built on by (most cited first, 4 of 4)

- [TCA-SIR: Learning Target-Conditioned Abstractions for Scientific Inspiration Retrieval](https://mlsanity.com/paper/2607.28498/) (2026)
- [DeepInstructor: An Agentic AI Instructor for Experience-Driven Idea Evaluation](https://mlsanity.com/paper/2609.22104/) (2026)
- [Same Problem, Different Field: Cross-Domain Solution Import via Domain-Stripped Computational Fingerprints](https://mlsanity.com/paper/2609.07595/) (2026)
- [Reinforcing Agentic Creativity in Scientific Ideation with Night Science](https://mlsanity.com/paper/2609.35706/) (2026)

## Abstract (arXiv)

Despite interdisciplinary research leading to larger and longer-term impact, most work remains confined to single-domain academic silos. Recent AI-based approaches to scientific discovery show promise for interdisciplinary research, but many prioritize rapidly designing experiments and solutions, bypassing the exploratory, collaborative reasoning processes that drive creative interdisciplinary breakthroughs. As a result, prior efforts largely prioritize automating scientific discovery rather than augmenting the reasoning processes that underlie scientific disruption. We present Idea-Catalyst, a novel framework that systematically identifies interdisciplinary insights to support creative reasoning in both humans and large language models. Starting from an abstract research goal, Idea-Catalyst is designed to assist the brainstorming stage, explicitly avoiding premature anchoring on specific solutions. The framework embodies key metacognitive features of interdisciplinary reasoning: (a) defining and assessing research goals, (b) awareness of a domain's opportunities and unresolved challenges, and (c) strategic exploration of interdisciplinary ideas based on impact potential. Concretely, Idea-Catalyst decomposes an abstract goal (e.g., improving human-AI collaboration) into core target-domain research questions that guide the analysis of progress and open challenges within that domain. These challenges are reformulated as domain-agnostic conceptual problems, enabling retrieval from external disciplines (e.g., Psychology, Sociology) that address analogous issues. By synthesizing and recontextualizing insights from these domains back into the target domain, Idea-Catalyst ranks source domains by their interdisciplinary potential. Empirically, this targeted integration improves average novelty by 21% and insightfulness by 16%, while remaining grounded in the original research problem.