Self-Harness: LLM Agents That Autonomously Improve Their Own Operating Systems
Researchers have developed AutoModSAT, a framework that uses large language models to automatically discover and optimize heuristics in SAT solvers. The system combines a modular solver design, unsupervised prompt optimization, and an evolutionary search algorithm to explore solution strategies without manual constraints. The work suggests LLMs can meaningfully advance optimization in a domain central to both theoretical computer science and industrial applications.
AutoModSAT is a new framework introduced by researchers that leverages large language models to automate the discovery of heuristics within complex SAT (Boolean Satisfiability) solvers. SAT solving is a foundational problem in computational complexity theory with broad industrial relevance, including hardware verification, planning, and cryptography. Existing automatic configuration tools for SAT solvers have been limited by manually defined search spaces, constraining their ability to find novel strategies. AutoModSAT addresses this by pairing an LLM-compatible modular solver architecture with unsupervised prompt optimization to diversify the functions the LLM generates, and a search procedure combining a presearch strategy with a (1+λ) evolutionary algorithm. Experiments across multiple datasets showed a 40% performance improvement over the baseline solver and a 30% improvement over state-of-the-art solvers, along with notable speedups compared to parameter-tuned alternatives. The results position LLM-guided heuristic discovery as a promising direction for tackling the complexity of modern SAT solver optimization.
What's missing
As a preprint, this work has not yet undergone formal peer review. The paper does not detail the computational cost of running AutoModSAT's LLM-based optimization pipeline, which could be a practical barrier to adoption. It is also unclear how performance generalizes beyond the tested datasets to industrial-scale or adversarial SAT instances.
What different sources said
- arXiv cs.LGCenter
In-Context Learning for Latent Space Bayesian Optimization
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.