Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Murali, Vishnu, Gulati, Anmol, Lumer, Elias, Frank, Kevin, Campagna, Sindy, Subbiah, Vamse Kumar
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2604.09470
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866914464189644800
author Murali, Vishnu
Gulati, Anmol
Lumer, Elias
Frank, Kevin
Campagna, Sindy
Subbiah, Vamse Kumar
author_facet Murali, Vishnu
Gulati, Anmol
Lumer, Elias
Frank, Kevin
Campagna, Sindy
Subbiah, Vamse Kumar
contents Translating natural language into Jira Query Language (JQL) requires resolving ambiguous field references, instance-specific categorical values, and complex Boolean predicates. Single-pass LLMs cannot discover which categorical values (e.g., component names or fix versions) actually exist in a given Jira instance, nor can they verify generated queries against a live data source, limiting accuracy on paraphrased or ambiguous requests. No open, execution-based benchmark exists for mapping natural language to JQL. We introduce Jackal, the first large-scale, execution-based text-to-JQL benchmark comprising 100,000 validated NL-JQL pairs on a live Jira instance with over 200,000 issues. To establish baselines on Jackal, we propose Agentic Jackal, a tool-augmented agent that equips LLMs with live query execution via the Jira MCP server and JiraAnchor, a semantic retrieval tool that resolves natural-language mentions of categorical values through embedding-based similarity search. Among 9 frontier LLMs evaluated, single-pass models average only 43.4% execution accuracy on short natural-language queries, highlighting that text-to-JQL remains an open challenge. The agentic approach improves 7 of 9 models, with a 9.0% relative gain on the most linguistically challenging variant; in a controlled ablation isolating JiraAnchor, categorical-value accuracy rises from 48.7% to 71.7%, with component-field accuracy jumping from 16.9% to 66.2%. Our analysis identifies inherent semantic ambiguities, such as issue-type disambiguation and text-field selection, as the dominant failure modes rather than value-resolution errors, pointing to concrete directions for future work. We publicly release the benchmark, all agent transcripts, and evaluation code to support reproducibility.
format Preprint
id arxiv_https___arxiv_org_abs_2604_09470
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Agentic Jackal: Live Execution and Semantic Value Grounding for Text-to-JQL
Murali, Vishnu
Gulati, Anmol
Lumer, Elias
Frank, Kevin
Campagna, Sindy
Subbiah, Vamse Kumar
Computation and Language
Translating natural language into Jira Query Language (JQL) requires resolving ambiguous field references, instance-specific categorical values, and complex Boolean predicates. Single-pass LLMs cannot discover which categorical values (e.g., component names or fix versions) actually exist in a given Jira instance, nor can they verify generated queries against a live data source, limiting accuracy on paraphrased or ambiguous requests. No open, execution-based benchmark exists for mapping natural language to JQL. We introduce Jackal, the first large-scale, execution-based text-to-JQL benchmark comprising 100,000 validated NL-JQL pairs on a live Jira instance with over 200,000 issues. To establish baselines on Jackal, we propose Agentic Jackal, a tool-augmented agent that equips LLMs with live query execution via the Jira MCP server and JiraAnchor, a semantic retrieval tool that resolves natural-language mentions of categorical values through embedding-based similarity search. Among 9 frontier LLMs evaluated, single-pass models average only 43.4% execution accuracy on short natural-language queries, highlighting that text-to-JQL remains an open challenge. The agentic approach improves 7 of 9 models, with a 9.0% relative gain on the most linguistically challenging variant; in a controlled ablation isolating JiraAnchor, categorical-value accuracy rises from 48.7% to 71.7%, with component-field accuracy jumping from 16.9% to 66.2%. Our analysis identifies inherent semantic ambiguities, such as issue-type disambiguation and text-field selection, as the dominant failure modes rather than value-resolution errors, pointing to concrete directions for future work. We publicly release the benchmark, all agent transcripts, and evaluation code to support reproducibility.
title Agentic Jackal: Live Execution and Semantic Value Grounding for Text-to-JQL
topic Computation and Language
url https://arxiv.org/abs/2604.09470