QueryGraph: Reliable Multi-Tool Query Execution Planning via LLM-Based Graph Generation

Aishwarya Chakravarthy; Vidhi Kulkarni; Duen Horng Chau

Home/Archive/arXiv

arXiv · 2606.08300

QueryGraph: Reliable Multi-Tool Query Execution Planning via LLM-Based Graph Generation

Aishwarya Chakravarthy·Vidhi Kulkarni·Duen Horng Chau

View original source ↗Read source document ↗Export metadata ↓

Abstract

Many real-world queries over personal data span multiple applications and require structured planning, as individual tools expose only partial information. While LLMs show strong reasoning and tool use, reliably executing multi-step, cross-tool queries remains challenging. We introduce a system that converts natural language queries into structured graphs and executes them via a deterministic planner. Our approach uses depth-first search to resolve dependencies and combine results across tools, improving reliability and enabling queries beyond traditional keyword-based search. We demonstrate high accuracy even with smaller or locally hosted LLMs.

Explore related subjects

cs.LG

Keep this discovery

BibTeX RIS

Aishwarya Chakravarthy, Vidhi Kulkarni, Duen Horng Chau. 2026-08-29. QueryGraph: Reliable Multi-Tool Query Execution Planning via LLM-Based Graph Generation. https://arxiv.org/abs/2606.08300

Cite the original work for its findings. Save a collection to share your selection of sources.

Discover connections

cs.LG subject

Connections use source metadata and explicit phrase matches, not verified experimental comparisons.

KEEP EXPLORING

Related discoveries

arXiv2026

Rates of Convergence in the Central Limit Theorem for Markov Chains, with an Application to TD Learning

We prove a non-asymptotic central limit theorem for vector-valued martingale differences using Stein's method, and use Poisson's equation to extend the result to functions of Markov Chains. We then show that these results can be applied to establish a non-asymptotic central limit theorem for Temporal Difference (TD) learning with averaging.

math.PR↗

arXiv2026

Diffusion Distillation for Efficient Weather Ensembles

Diffusion models generate skillful weather ensembles but require costly iterative sampling. We introduce a supervised energy-distance distillation method that compresses a multi-step diffusion teacher into a single-step student by aligning student forecasts with teacher samples and ground-truth observations. Experiments on global forecasting and typhoon-track prediction show that our student outperforms existing distillation methods and preserves skill for extreme events. It matches or surpasses the teacher across key metrics using only one neural function evaluation per autoregressive step.

cs.LG↗

arXiv2026

Explanations, Prompts, and Formalizations: Arguments for New Norms in LLM-Enabled Mathematical Research

As several mathematical conjectures have recently been settled using large language models (LLMs), the mathematical community has formulated norms and recommendations regarding the publishing of such results. These norms do not cover the disclosure of the prompts and precise software setup used to obtain those results, nor do they require that results be formalized in a manner that allows for machine verification. I argue that both of these are essential. In addition, since LLM-obtained results may be hard to understand, human authors have the responsibility to invent intuitive explanations.

math.HO↗