# MOOSE-Chem: Large Language Models for Rediscovering Unseen Chemistry Scientific Hypotheses

arXiv: https://arxiv.org/abs/2410.07076 · HTML: https://mlsanity.com/paper/2410.07076/

## Key facts

- Cited by 72 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 41 references that are in the map.
- First posted on arXiv 9 Oct 2024.

## Builds on (most cited first, 20 of 20)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery](https://mlsanity.com/paper/2408.06292/) (2024)
- [Can LLMs Generate Novel Research Ideas? A Large-Scale Human Study with 100+ NLP Researchers](https://mlsanity.com/paper/2409.04109/) (2024)
- [Abductive Commonsense Reasoning](https://mlsanity.com/paper/1908.05739/) (2019)
- [Transformers as Soft Reasoners over Language](https://mlsanity.com/paper/2002.05867/) (2020)
- [ResearchAgent: Iterative Research Idea Generation over Scientific Literature with Large Language Models](https://mlsanity.com/paper/2404.07738/) (2024)
- [Universal Self-Consistency for Large Language Model Generation](https://mlsanity.com/paper/2311.17311/) (2023)
- [SciMON: Scientific Inspiration Machines Optimized for Novelty](https://mlsanity.com/paper/2305.14259/) (2023)
- [Large Language Models for Automated Open-domain Scientific Hypotheses Discovery](https://mlsanity.com/paper/2309.02726/) (2023)
- [MLR-Copilot: Autonomous Machine Learning Research based on Large Language Models Agents](https://mlsanity.com/paper/2408.14033/) (2024)
- [Goal Driven Discovery of Distributional Differences via Language Descriptions](https://mlsanity.com/paper/2302.14233/) (2023)
- [Large Language Models are Zero Shot Hypothesis Proposers](https://mlsanity.com/paper/2311.05965/) (2023)
- [ChemReasoner: Heuristic Search over a Large Language Model's Knowledge Space using Quantum-Chemical Feedback](https://mlsanity.com/paper/2402.10980/) (2024)
- [Language Models as Inductive Reasoners](https://mlsanity.com/paper/2212.10923/) (2022)
- [Logical Reasoning over Natural Language as Knowledge Representation: A Survey](https://mlsanity.com/paper/2303.12023/) (2023)
- [Can Large Language Models Unlock Novel Scientific Research Ideas?](https://mlsanity.com/paper/2409.06185/) (2024)
- [Monte Carlo Thought Search: Large Language Model Querying for Complex Scientific Reasoning in Catalyst Design](https://mlsanity.com/paper/2310.14420/) (2023)
- [Improving Event Duration Prediction via Time-aware Pre-training](https://mlsanity.com/paper/2011.02610/) (2020)

## Built on by (most cited first, 30 of 72)

- [AlphaEvolve: A coding agent for scientific and algorithmic discovery](https://mlsanity.com/paper/2506.13131/) (2025)
- [Agentic AI for Scientific Discovery: A Survey of Progress, Challenges, and Future Directions](https://mlsanity.com/paper/2503.08979/) (2025)
- [From AI for Science to Agentic Science: A Survey on Autonomous Scientific Discovery](https://mlsanity.com/paper/2508.14111/) (2025)
- [AgentRxiv: Towards Collaborative Autonomous Research](https://mlsanity.com/paper/2503.18102/) (2025)
- [ResearchBench: Benchmarking LLMs in Scientific Discovery via Inspiration-Based Task Decomposition](https://mlsanity.com/paper/2503.21248/) (2025)
- [LLM Agents for Education: Advances and Applications](https://mlsanity.com/paper/2503.11733/) (2025)
- [A Survey of Scientific Large Language Models: From Data Foundations to Agent Frontiers](https://mlsanity.com/paper/2508.21148/) (2025)
- [NewtonBench: Benchmarking Generalizable Scientific Law Discovery in LLM Agents](https://mlsanity.com/paper/2510.07172/) (2025)
- [Position: Multimodal Large Language Models Can Significantly Advance Scientific Reasoning](https://mlsanity.com/paper/2502.02871/) (2025)
- [Hypothesis Generation for Materials Discovery and Design Using Goal-Driven and Constraint-Guided LLM Agents](https://mlsanity.com/paper/2501.13299/) (2025)
- [PiFlow: Principle-Aware Scientific Discovery with Multi-Agent Collaboration](https://mlsanity.com/paper/2505.15047/) (2025)
- [Attention Reallocation: Towards Zero-cost and Controllable Hallucination Mitigation of MLLMs](https://mlsanity.com/paper/2503.08342/) (2025)
- [AI Scientists Fail Without Strong Implementation Capability](https://mlsanity.com/paper/2506.01372/) (2025)
- [OmniScientist: Toward a Co-evolving Ecosystem of Human and AI Scientists](https://mlsanity.com/paper/2511.16931/) (2025)
- [PhysUniBench: A Multi-Modal Physics Reasoning Benchmark at Undergraduate Level](https://mlsanity.com/paper/2506.17667/) (2025)
- [MOOSE-Chem2: Exploring LLM Limits in Fine-Grained Scientific Hypothesis Discovery via Hierarchical Search](https://mlsanity.com/paper/2505.19209/) (2025)
- [How Far Are AI Scientists from Changing the World?](https://mlsanity.com/paper/2507.23276/) (2025)
- [A Survey of Large Language Models for Text-Guided Molecular Discovery: from Molecule Generation to Optimization](https://mlsanity.com/paper/2505.16094/) (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)
- [A Survey of AI Scientists](https://mlsanity.com/paper/2510.23045/) (2025)
- [AI for Auto-Research: Roadmap & User Guide](https://mlsanity.com/paper/2605.18661/) (2026)
- [Toward Reliable Scientific Hypothesis Generation: Evaluating Truthfulness and Hallucination in Large Language Models](https://mlsanity.com/paper/2505.14599/) (2025)
- [Evolving Roles of LLMs in Scientific Innovation: Assistant, Collaborator, Scientist, and Evaluator](https://mlsanity.com/paper/2507.11810/) (2025)
- [Autonomous Research Agents: A Survey of AI Scientists and the Verification Gap](https://mlsanity.com/paper/2608.05179/) (2026)
- [Can Knowledge-Graph-based Retrieval Augmented Generation Really Retrieve What You Need?](https://mlsanity.com/paper/2510.16582/) (2025)
- [El Agente Quntur: A research collaborator agent for quantum chemistry](https://mlsanity.com/paper/2602.04850/) (2026)
- [PriM: Principle-Inspired Material Discovery through Multi-Agent Collaboration](https://mlsanity.com/paper/2504.08810/) (2025)
- [EarthSE: A Benchmark for Evaluating Earth Scientific Exploration Capability of LLMs](https://mlsanity.com/paper/2505.17139/) (2025)
- [The Need for Verification in AI-Driven Scientific Discovery](https://mlsanity.com/paper/2509.01398/) (2025)

## Abstract (arXiv)

Scientific discovery plays a pivotal role in advancing human society, and recent progress in large language models (LLMs) suggests their potential to accelerate this process. However, it remains unclear whether LLMs can autonomously generate novel and valid hypotheses in chemistry. In this work, we investigate whether LLMs can discover high-quality chemistry hypotheses given only a research background-comprising a question and/or a survey-without restriction on the domain of the question. We begin with the observation that hypothesis discovery is a seemingly intractable task. To address this, we propose a formal mathematical decomposition grounded in a fundamental assumption: that most chemistry hypotheses can be composed from a research background and a set of inspirations. This decomposition leads to three practical subtasks-retrieving inspirations, composing hypotheses with inspirations, and ranking hypotheses - which together constitute a sufficient set of subtasks for the overall scientific discovery task. We further develop an agentic LLM framework, MOOSE-Chem, that is a direct implementation of this mathematical decomposition. To evaluate this framework, we construct a benchmark of 51 high-impact chemistry papers published and online after January 2024, each manually annotated by PhD chemists with background, inspirations, and hypothesis. The framework is able to rediscover many hypotheses with high similarity to the groundtruth, successfully capturing the core innovations-while ensuring no data contamination since it uses an LLM with knowledge cutoff date prior to 2024. Finally, based on LLM's surprisingly high accuracy on inspiration retrieval, a task with inherently out-of-distribution nature, we propose a bold assumption: that LLMs may already encode latent scientific knowledge associations not yet recognized by humans.