← Back to all news
arXiv AI By Zikai Xie, Wenmei Li, Man Luo, Jun Jiang, Linjiang Chen

Language models guide symbolic equation discovery by controlling search

Read the original on arXiv AI →

arXiv:2607. 04156v1 Announce Type: new Abstract: Scientific equation discovery must combine broad domain priors with strict numerical testing.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

arXiv AI
Sep 1

Test-Time Scaling for Scientific Equation Discovery

The paper investigates Test‑Time Scaling (TTS) for large language models (LLMs) in the context of automated scientific equation discovery, an open‑ended task where models iteratively search candidate equations using observed data for feedback. It frames equation discovery as a unified iterative search that encompasses Best‑of‑N, sequential refinement, tree search, and evolutionary methods, and studies how compute allocation—particularly search width—affects performance under fixed budgets. Experiments on the LLM‑SRBench dataset show that increasing search width with more compute improves results, while other factors like population‑branching split and controller choice have smaller impacts, indicating that controlling exploration versus exploitation is key to scaling LLM‑based equation discovery.

By Haowei Lin, Hubert Lim, Xiangyu Wang, Letian Huang, Di He
llms
More like this →