# Unlocking LLM Creativity in Science through Analogical Reasoning

arXiv: https://arxiv.org/abs/2605.11258 · HTML: https://mlsanity.com/paper/2605.11258/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning.
- Builds on 37 of its 54 references that are in the map.
- First posted on arXiv 11 May 2026.

## Placed in

- LLM reasoning / [Knowledge- and tool-augmented reasoning](https://mlsanity.com/lr/knowledge-and-tool-augmented-reasoning/)

## Builds on (most cited first, 30 of 37)

- [The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery](https://mlsanity.com/paper/2408.06292/) (2024)
- [The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search](https://mlsanity.com/paper/2504.08066/) (2025)
- [SPECTER: Document-level Representation Learning using Citation-informed Transformers](https://mlsanity.com/paper/2004.07180/) (2020)
- [Accelerating scientific discovery with Co-Scientist](https://mlsanity.com/paper/2502.18864/) (2025)
- [Can LLMs Generate Novel Research Ideas? A Large-Scale Human Study with 100+ NLP Researchers](https://mlsanity.com/paper/2409.04109/) (2024)
- [The Vendi Score: A Diversity Evaluation Metric for Machine Learning](https://mlsanity.com/paper/2210.02410/) (2022)
- [Diverse Beam Search: Decoding Diverse Solutions from Neural Sequence Models](https://mlsanity.com/paper/1610.02424/) (2016)
- [Emergent Analogical Reasoning in Large Language Models](https://mlsanity.com/paper/2212.09196/) (2022)
- [ResearchAgent: Iterative Research Idea Generation over Scientific Literature with Large Language Models](https://mlsanity.com/paper/2404.07738/) (2024)
- [Turning Up the Heat: Min-p Sampling for Creative and Coherent LLM Outputs](https://mlsanity.com/paper/2407.01082/) (2024)
- [Artificial Hivemind: The Open-Ended Homogeneity of Language Models (and Beyond)](https://mlsanity.com/paper/2510.22954/) (2025)
- [The Semantic Scholar Open Data Platform](https://mlsanity.com/paper/2301.10140/) (2023)
- [Verbalized Sampling: How to Mitigate Mode Collapse and Unlock LLM Diversity](https://mlsanity.com/paper/2510.01171/) (2025)
- [Large Language Models as Analogical Reasoners](https://mlsanity.com/paper/2310.01714/) (2023)
- [Large Language Models for Automated Open-domain Scientific Hypotheses Discovery](https://mlsanity.com/paper/2309.02726/) (2023)
- [Kosmos: An AI Scientist for Autonomous Discovery](https://mlsanity.com/paper/2511.02824/) (2025)
- [Can large language models explore in-context?](https://mlsanity.com/paper/2403.15371/) (2024)
- [Many Heads Are Better Than One: Improved Scientific Idea Generation by A LLM-Based Multi-Agent System](https://mlsanity.com/paper/2410.09403/) (2024)
- [Strong Model Collapse](https://mlsanity.com/paper/2410.04840/) (2024)
- [Diverse Preference Optimization](https://mlsanity.com/paper/2501.18101/) (2025)
- [Base Models Beat Aligned Models at Randomness and Creativity](https://mlsanity.com/paper/2505.00047/) (2025)
- [Forcing Diffuse Distributions out of Language Models](https://mlsanity.com/paper/2404.10859/) (2024)
- [The Price of Format: Diversity Collapse in LLMs](https://mlsanity.com/paper/2505.18949/) (2025)
- [Quality-Diversity through AI Feedback](https://mlsanity.com/paper/2310.13032/) (2023)
- [PerturBench: Benchmarking Machine Learning Models for Cellular Perturbation Analysis](https://mlsanity.com/paper/2408.10609/) (2024)
- [AutoDiscovery: Open-ended Scientific Discovery via Bayesian Surprise](https://mlsanity.com/paper/2507.00310/) (2025)
- [Towards Execution-Grounded Automated AI Research](https://mlsanity.com/paper/2601.14525/) (2026)
- [The Denario project: Deep knowledge AI agents for scientific discovery](https://mlsanity.com/paper/2510.26887/) (2025)
- [Literature-Grounded Novelty Assessment of Scientific Ideas](https://mlsanity.com/paper/2506.22026/) (2025)
- [Relevant or Random: Can LLMs Truly Perform Analogical Reasoning?](https://mlsanity.com/paper/2404.12728/) (2024)

## Built on by (most cited first, 6 of 6)

- [Playing with Words, Improving with Rewards: Training Language Models for Creative Association](https://mlsanity.com/paper/2605.27832/) (2026)
- [Discovery by Dreaming: Cross-Domain Recombination in Artificial Memory](https://mlsanity.com/paper/2607.16256/) (2026)
- [On the Diversity of Analogy Making in Large Language Models](https://mlsanity.com/paper/2608.03233/) (2026)
- [Toward Auto-Research: Mining Falsifiable Research Ideas from Paper Knowledge Graphs with Categorical Structure](https://mlsanity.com/paper/2608.20361/) (2026)
- [Measuring the Creativity of Frontier LLMs in Automated Research](https://mlsanity.com/paper/2609.14057/) (2026)
- [Old Ideas, Novel Problems: The Instability of LLM-Based Novelty Evaluation](https://mlsanity.com/paper/2610.02022/) (2026)

## Abstract (arXiv)

Autonomous science promises to augment scientific discovery, particularly in complex fields like biomedicine. However, this requires AI systems that can consistently generate novel and diverse solutions to open-ended problems. We evaluate LLMs on the task of open-ended solution generation and quantify their tendency to mode collapse into low-diversity generations. To mitigate this mode collapse, we introduce analogical reasoning (AR) as a new approach to solution generation. AR generates analogies to cross-domain problems based on shared relational structure, then uses those analogies to search for novel solutions. Compared to baselines, AR discovers significantly more diverse generations (improving solution diversity metrics by 90-173%), generates novel solutions over 50% of the time (compared to as little as 1.6% for baselines), and produces high-quality analogies. To validate the real-world feasibility of AR, we implement AR-generated solutions across four biomedical problems, yielding consistent quantitative gains. AR-generated approaches achieve a nearly 13-fold improvement on distributional metrics for perturbation effect prediction, outperform all baselines on AUPRC when predicting cell-cell communication, infer brain region interactions with a high Spearman correlation (ρ=0.729) to published methods, and establish state-of-the-art performance on 2 datasets for oligonucleotide property prediction. The novel and diverse solutions produced by AR can be used to augment the search space of existing solution generation methods.