Evidence-informed belief updates make Bayesian surprise non-stationary in LLM hypothesis search, with embedding-based RAG identifying 37.5% spurious static surprisals and modified search (filtering plus diversity) yielding 30.62% higher accumulated non-stationary surprisal across five domains.
Generating Literature-Driven Scientific Theories at Scale
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
abstract
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
years
2026 2verdicts
UNVERDICTED 2representative citing papers
LLM-AutoSciLab proposes an LLM-driven closed-loop system for hypothesis generation and adaptive experiment selection that reports higher accuracy and 2-5x better sample efficiency than baselines on new chemistry and gene-network discovery benchmarks.
citing papers explorer
-
Evidence-Informed LLM Beliefs for Continual Scientific Discovery
Evidence-informed belief updates make Bayesian surprise non-stationary in LLM hypothesis search, with embedding-based RAG identifying 37.5% spurious static surprisals and modified search (filtering plus diversity) yielding 30.62% higher accumulated non-stationary surprisal across five domains.
-
LLM-AutoSciLab: Closed-Loop Scientific Discovery via Active Experimentation with LLMs
LLM-AutoSciLab proposes an LLM-driven closed-loop system for hypothesis generation and adaptive experiment selection that reports higher accuracy and 2-5x better sample efficiency than baselines on new chemistry and gene-network discovery benchmarks.