FunctionEvolve: New Method Improves AI's Ability to Discover Scientific Laws from Data
Researchers have proposed FunctionEvolve, an evolutionary framework that uses expression trees and large language models to recover explicit mathematical formulas from data, achieving 82.9% accuracy on a standard benchmark. Existing LLM-driven symbolic regression methods lack explicit structural awareness, leading to poor local mutation and unreliable coefficient fitting. The work represents a substantial leap in automated scientific law discovery, with performance 4.5 times above same-backbone baselines.
FunctionEvolve is a new symbolic regression framework that combines large language models with explicit expression-tree structures to search for mathematical laws underlying scientific data. Unlike prior LLM-driven approaches that treat candidate expressions as opaque strings, FunctionEvolve uses structural summaries to diversify parent selection, local tree edits to preserve useful subexpressions, and a structure-aware coefficient fitting procedure that decomposes, constrains, and simplifies coefficients for more reliable scoring. Tested on the 129-task synthetic subset of LLM-SRBench using Claude Opus 4.6, the system recovers 107 exact symbolic forms, achieving 82.9% SA@50 and 55.8% SA@1—the latter being 3.6 times higher than the strongest previously published top-1 result. The framework relies only on elementary function families without domain-specific rules, which the authors argue improves generalizability across scientific domains. The paper also audits the LLM-SRBench benchmark itself, identifying collinearity issues in its materials-science subset that create identifiability problems, raising questions about evaluation reliability in that domain.
What's missing
The study evaluates primarily on a synthetic benchmark subset; performance on real-world noisy scientific datasets beyond the benchmark is not reported. It is unclear how computational cost and latency of the Claude Opus 4.6 backbone compare to prior methods, which is relevant for practical deployment. The authors note identifiability issues in the materials-science subset but do not provide corrected benchmark results for that domain.
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.