# Generating Literature-Driven Scientific Theories at Scale

arXiv: https://arxiv.org/abs/2601.16282 · HTML: https://mlsanity.com/paper/2601.16282/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 68 references that are in the map.
- First posted on arXiv 22 Jan 2026.

## Builds on (most cited first, 22 of 22)

- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [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)
- [COMET: Commonsense Transformers for Automatic Knowledge Graph Construction](https://mlsanity.com/paper/1906.05317/) (2019)
- [Agent Laboratory: Using LLM Agents as Research Assistants](https://mlsanity.com/paper/2501.04227/) (2025)
- [Can LLMs Generate Novel Research Ideas? A Large-Scale Human Study with 100+ NLP Researchers](https://mlsanity.com/paper/2409.04109/) (2024)
- [ResearchAgent: Iterative Research Idea Generation over Scientific Literature with Large Language Models](https://mlsanity.com/paper/2404.07738/) (2024)
- [SciMON: Scientific Inspiration Machines Optimized for Novelty](https://mlsanity.com/paper/2305.14259/) (2023)
- [Construction of the Literature Graph in Semantic Scholar](https://mlsanity.com/paper/1805.02262/) (2018)
- [BLADE: Benchmarking Language Model Agents for Data-Driven Science](https://mlsanity.com/paper/2408.09667/) (2024)
- [Inducing Relational Knowledge from BERT](https://mlsanity.com/paper/1911.12753/) (2019)
- [Robin: A multi-agent system for automating scientific discovery](https://mlsanity.com/paper/2505.13400/) (2025)
- [CodeScientist: End-to-End Semi-Automated Scientific Discovery with Code-based Experimentation](https://mlsanity.com/paper/2503.22708/) (2025)
- [Automated Statistical Model Discovery with Language Models](https://mlsanity.com/paper/2402.17879/) (2024)
- [HypoBench: Towards Systematic and Principled Benchmarking for Hypothesis Generation](https://mlsanity.com/paper/2504.11524/) (2025)
- [Data-driven Discovery with Large Generative Models](https://mlsanity.com/paper/2402.13610/) (2024)
- [AutoDiscovery: Open-ended Scientific Discovery via Bayesian Surprise](https://mlsanity.com/paper/2507.00310/) (2025)
- [Language Models as Inductive Reasoners](https://mlsanity.com/paper/2212.10923/) (2022)
- [Literature Meets Data: A Synergistic Approach to Hypothesis Generation](https://mlsanity.com/paper/2410.17309/) (2024)
- [HypER: Literature-grounded Hypothesis Generation and Distillation with Provenance](https://mlsanity.com/paper/2506.12937/) (2025)
- [HARPA: A Testability-Driven, Literature-Grounded Framework for Research Ideation](https://mlsanity.com/paper/2510.00620/) (2025)

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

- [LLM-AutoSciLab: Closed-Loop Scientific Discovery via Active Experimentation with LLMs](https://mlsanity.com/paper/2605.24043/) (2026)
- [Evidence-Informed LLM Beliefs for Continual Scientific Discovery](https://mlsanity.com/paper/2606.29182/) (2026)
- [Site4Drug: Predicting Drug-Binding Target Sites with an AI Agent](https://mlsanity.com/paper/2606.01816/) (2026)
- [Asterism: Exploring and Synthesizing Scattered Observations into Literature-Grounded Hypotheses and Theories](https://mlsanity.com/paper/2610.02673/) (2026)

## Abstract (arXiv)

Contemporary automated scientific discovery has focused on agents for generating scientific experiments, while systems that perform higher-level scientific activities such as theory building remain underexplored. In this work, we formulate the problem of synthesizing theories consisting of qualitative and quantitative laws from large corpora of scientific literature. We study theory generation at scale, using 13.7k source papers to synthesize 2.9k theories, examining how generation using literature-grounding versus parametric knowledge, and accuracy-focused versus novelty-focused generation objectives change theory properties. Our experiments show that, compared to using parametric LLM memory for generation, our literature-supported method creates theories that are significantly better at both matching existing evidence and at predicting future results from 4.6k subsequently-written papers