QueryWeaver: LLM-Based System for Multi-Tool Query Execution Planning
Researchers have introduced QueryWeaver, a system that converts natural language queries into structured execution graphs to reliably coordinate multiple software tools. The system addresses a core limitation of large language models (LLMs): their difficulty in reliably planning and executing multi-step queries that span several applications or data sources. It demonstrates high accuracy even when using smaller or locally hosted LLMs, potentially lowering the infrastructure barrier for deployment.
QueryWeaver is a newly proposed system designed to handle complex queries over personal data that require information from multiple applications. Rather than relying on an LLM to directly orchestrate tool calls—an approach prone to errors in multi-step scenarios—the system uses an LLM to generate a structured dependency graph, which is then executed by a deterministic planner. The planner uses depth-first search to resolve dependencies between tools and combine their outputs in the correct order. This separation of graph generation from execution is intended to improve reliability and reproducibility. The approach goes beyond traditional keyword-based search by enabling structured, cross-tool reasoning. Notably, the authors report strong accuracy even with smaller or locally hosted models, suggesting the system is not exclusively dependent on large, cloud-based LLMs. The paper was submitted to arXiv in June 2026 and is currently under review.
What's missing
The paper's abstract does not detail specific benchmark datasets, evaluation metrics, or baseline comparisons used to establish 'high accuracy,' making independent assessment of the performance claims difficult. Limitations around failure modes, scalability to large numbers of tools, and privacy implications of processing personal data across applications are not addressed in the available abstract.
What different sources said
- arXiv cs.LGCenter
QueryWeaver: Reliable Multi-Tool Query Execution Planning via LLM-Based Graph Generation
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.