2026
Towards Diverse Scientific Hypothesis Search with Large Language Models
Haorui Wang, Parshin Shojaee, Kazem Meidani, Kunyang Sun, Jose Miguel Hernandez-Lobato, Teresa Head-Gordon +4
ICML 2026poster
Large language models are increasingly used to accelerate scientific discovery, especially in iteratively searching scientific hypotheses. Yet in many discovery settings the goal is not to identify a single ``best'' hypothesis: validation is noisy and expensive, multiple hypotheses can remain plausi…