Abstract
Scientific equation discovery must combine broad domain priors with strict numerical testing. Symbolic regression supplies numerical grounding but faces a combinatorial search space, whereas many language-model systems ask the model to propose or select formulas directly. We test a different division of labour.
We compare role specifications in which the language model acts as equation author, candidate decider, or search controller, alongside end-to-end language-model and purely numerical baselines. In the controller setting proposed here, implemented as LLM-PySR, language models specify variables, operators, transformations, and search depth; symbolic regression enumerates and fits expressions; and deterministic metrics govern retention.
Across 74 AI-Feynman equations and seven complex formula-recovery tasks, search control achieved the strongest observed balance of accuracy, complexity, stability, and cost. On an independent battery dataset, LLM-PySR identified a compact piecewise-linear relation between early voltage-curve displacement and cycle life. The results suggest that language models should shape hypothesis exploration rather than decide which equations survive.
Blogger's Review: This research demonstrates the potential of language models in scientific discovery. By optimizing search control, it effectively explores complex equation spaces. Future work should further integrate domain knowledge with model capabilities to push the boundaries of scientific research.