# A Survey on Hypothesis Generation for Scientific Discovery in the Era of Large Language Models

arXiv: https://arxiv.org/abs/2504.05496 · HTML: https://mlsanity.com/paper/2504.05496/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Apr 2025.

## Built on by (most cited first, 18 of 18)

- [PiFlow: Principle-Aware Scientific Discovery with Multi-Agent Collaboration](https://mlsanity.com/paper/2505.15047/) (2025)
- [MatTools: Benchmarking Large Language Models for Materials Science Tools](https://mlsanity.com/paper/2505.10852/) (2025)
- [Autonomous Agents for Scientific Discovery: Orchestrating Scientists, Language, Code, and Physics](https://mlsanity.com/paper/2510.09901/) (2025)
- [GenoMAS: A Multi-Agent Framework for Scientific Discovery via Code-Driven Gene Expression Analysis](https://mlsanity.com/paper/2507.21035/) (2025)
- [Diversity Collapse in Multi-Agent LLM Systems: Structural Coupling and Collective Failure in Open-Ended Idea Generation](https://mlsanity.com/paper/2604.18005/) (2026)
- [From Reasoning to Learning: A Survey on Hypothesis Discovery and Rule Learning with Large Language Models](https://mlsanity.com/paper/2505.21935/) (2025)
- [BioDisco: Multi-agent hypothesis generation with dual-mode evidence, iterative feedback and temporal evaluation](https://mlsanity.com/paper/2508.01285/) (2025)
- [ARCHE: A Novel Task to Evaluate LLMs on Latent Reasoning Chain Extraction](https://mlsanity.com/paper/2511.12485/) (2025)
- [Towards Agentic Intelligence for Materials Science](https://mlsanity.com/paper/2602.00169/) (2026)
- [How Do LLMs Encode Scientific Quality? An Empirical Study Using Monosemantic Features from Sparse Autoencoders](https://mlsanity.com/paper/2602.19115/) (2026)
- [More Than Can Be Said: A Benchmark and Framework for Pre-Question Scientific Ideation](https://mlsanity.com/paper/2605.06345/) (2026)
- [Evidence-Grounded Frontier Mapping and Agentic Hypothesis Generation in Nanomedicine](https://mlsanity.com/paper/2605.18144/) (2026)
- [From Activation to Specificity: Automating Counterfactual Testing of Visual Representations in the Human Brain](https://mlsanity.com/paper/2605.23895/) (2026)
- [HALO: Interactive Co-abductive Reasoning in Scientific Hypothesis Generation](https://mlsanity.com/paper/2607.18564/) (2026)
- [Towards a new paradigm of scientific discovery with socialized artificial intelligence](https://mlsanity.com/paper/2608.02775/) (2026)
- [NxN E-valuation: Hypothesis Certification via a Conformal CRT Null](https://mlsanity.com/paper/2608.06621/) (2026)
- [MAIL: Memory-driven, Adaptive, Incremental, and Literature-grounded Framework for Hypothesis Generation in Chemistry](https://mlsanity.com/paper/2608.28315/) (2026)
- [Hakken: Predicting future discoveries to fill the gaps in today's knowledge](https://mlsanity.com/paper/2609.04494/) (2026)

## Abstract (arXiv)

Hypothesis generation is a fundamental step in scientific discovery, yet it is increasingly challenged by information overload and disciplinary fragmentation. Recent advances in Large Language Models (LLMs) have sparked growing interest in their potential to enhance and automate this process. This paper presents a comprehensive survey of hypothesis generation with LLMs by (i) reviewing existing methods, from simple prompting techniques to more complex frameworks, and proposing a taxonomy that categorizes these approaches; (ii) analyzing techniques for improving hypothesis quality, such as novelty boosting and structured reasoning; (iii) providing an overview of evaluation strategies; and (iv) discussing key challenges and future directions, including multimodal integration and human-AI collaboration. Our survey aims to serve as a reference for researchers exploring LLMs for hypothesis generation.