FunctionEvolve: New Method Improves AI's Ability to Discover Scientific Laws from Data
Researchers introduced FunctionEvolve, a framework that combines large language models with evolutionary algorithms to recover exact mathematical equations from data more reliably than previous methods. The approach uses expression trees to organize the search space and structure-aware coefficient fitting, achieving 82.9% success on a benchmark of 129 synthetic tasks. This advancement matters because discovering explicit scientific laws from data is fundamental to scientific discovery and could accelerate research across multiple domains.
FunctionEvolve addresses a key limitation in symbolic regression—the process of uncovering explicit mathematical laws from experimental data. While recent methods use large language models (LLMs) to guide the search more intelligently than random approaches, they lack explicit structural understanding of candidate equations. The new framework organizes the entire search using expression trees, which allows for diverse parent selection, local mutations that preserve useful mathematical subexpressions, and structure-aware coefficient fitting that more reliably scores candidate equations. Testing on 129 synthetic tasks, FunctionEvolve with Claude Opus 4.6 recovered 107 exact mathematical forms, achieving 82.9% success at finding correct equations within 50 attempts—4.5 times better than comparable baselines. The researchers also identified and documented collinearity issues in the benchmark's materials-science subset that affect result interpretation.
What's missing
The study does not discuss computational cost or runtime comparisons with baseline methods, limiting assessment of practical efficiency trade-offs. Additionally, while the method is tested on synthetic data, real-world applicability to noisy experimental data and performance on non-elementary function families remain unexplored in the abstract.
What different sources said
- arXiv cs.AICenter
FunctionEvolve: Structure-Guided Symbolic Regression with LLMs
Related
Gut Bacteria Enzyme Found to Break Down Heat-Processed Food Compounds, Producing Novel Biogenic Amines
Researchers have discovered that an enzyme in common gut bacteria can degrade N-epsilon-carboxymethyllysine (CML), a compound formed during thermal food processing, producing previously unknown biogenic amines. The enzyme, ornithine decarboxylase SpeC from enterobacteria, acts on CML and related modified lysine derivatives through a low-level 'underground' catalytic activity. This finding suggests a previously unrecognized communication axis between thermally processed dietary compounds and gut microbial physiology, with potential implications for host health.
Full-Length Gene Sequencing Reveals Two Distinct Bacterial Communities in Black-Legged Ticks Expanding Into Canada
Researchers used Oxford Nanopore full-length 16S rRNA gene sequencing to characterize the microbiome of Ixodes scapularis black-legged ticks collected in Nova Scotia, Canada, distinguishing between tick-adapted bacteria and environmentally acquired bacteria. The study comes as I. scapularis — the primary vector of Lyme disease — is rapidly expanding northward into Canada due to climate change. The findings suggest that environmentally derived bacteria in tick microbiomes are not mere contamination, which has implications for how tick microbiome data is collected and interpreted across surveillance studies.
Study Identifies Metabolic Link Between Cell Envelope Stress and Biofilm Formation in Bacteria
Researchers have discovered that the metabolite acetyl-CoA directly inhibits enzymes that degrade the bacterial signaling molecule c-di-GMP, connecting cell envelope biosynthesis stress to biofilm formation in Pseudomonas aeruginosa. The study found that sub-inhibitory concentrations of antibiotics targeting early peptidoglycan biosynthesis — but not other antibiotic classes — elevate c-di-GMP levels by reducing phosphodiesterase activity, with acetyl-CoA competing for the enzyme active site. Because the relevant enzyme domain is broadly conserved across bacterial species, this checkpoint mechanism may be widespread and could have implications for understanding antibiotic-induced biofilm responses.