@inproceedings{lyu-etal-2026-segra,
title = "{SEGRA}: A Structured Experience Guided Reasoning Agent for Property Graph Question Answering",
author = "Lyu, Saiyue and
Dundua, Mariam and
Kapoor, Vishaal and
Ahuja, Sarthak and
Kordjazi, Neda and
Yortucboylu, Evren and
Amin, Harsh and
Steinert, Rebecca",
editor = "Atanasova, Pepa and
Haffari, Gholamreza and
Wang, Minghan",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-industry.164/",
pages = "2779--2793",
ISBN = "979-8-89176-460-6",
abstract = "Enterprise IT support knowledge graphs capture rich relationships among cases, users, devices, symptoms, taxonomic categories, root causes, and historical resolutions. Yet querying them in Gremlin requires knowledge of graph schemas, traversal semantics, edge directionality, and property-graph-specific constraints, making them difficult for non-expert operators to use. We introduce SEGRA, an experience-guided agent for enterprise text-to-Gremlin question answering. SEGRA integrates intent routing, schema- and taxonomy-grounded query generation, multi-shot decomposition, execution-aware verification, and a curriculum-bootstrapped skill library that reuses verified query patterns. On an enterprise IT support benchmark, SEGRA achieves a $7.0\times$ higher mean judge score than backbone-only chain-of-thought prompting. Its skill library further reduces LLM calls by 20{\%} and dollar cost by 18{\%} relative to SEGRA without skills, while preserving answer quality. These results show that schema-grounded agent design and reusable execution experience improve both accuracy and efficiency for enterprise graph QA."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lyu-etal-2026-segra">
<titleInfo>
<title>SEGRA: A Structured Experience Guided Reasoning Agent for Property Graph Question Answering</title>
</titleInfo>
<name type="personal">
<namePart type="given">Saiyue</namePart>
<namePart type="family">Lyu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mariam</namePart>
<namePart type="family">Dundua</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vishaal</namePart>
<namePart type="family">Kapoor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sarthak</namePart>
<namePart type="family">Ahuja</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Neda</namePart>
<namePart type="family">Kordjazi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Evren</namePart>
<namePart type="family">Yortucboylu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Harsh</namePart>
<namePart type="family">Amin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rebecca</namePart>
<namePart type="family">Steinert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track</title>
</titleInfo>
<name type="personal">
<namePart type="given">Pepa</namePart>
<namePart type="family">Atanasova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gholamreza</namePart>
<namePart type="family">Haffari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Minghan</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-460-6</identifier>
</relatedItem>
<abstract>Enterprise IT support knowledge graphs capture rich relationships among cases, users, devices, symptoms, taxonomic categories, root causes, and historical resolutions. Yet querying them in Gremlin requires knowledge of graph schemas, traversal semantics, edge directionality, and property-graph-specific constraints, making them difficult for non-expert operators to use. We introduce SEGRA, an experience-guided agent for enterprise text-to-Gremlin question answering. SEGRA integrates intent routing, schema- and taxonomy-grounded query generation, multi-shot decomposition, execution-aware verification, and a curriculum-bootstrapped skill library that reuses verified query patterns. On an enterprise IT support benchmark, SEGRA achieves a 7.0\times higher mean judge score than backbone-only chain-of-thought prompting. Its skill library further reduces LLM calls by 20% and dollar cost by 18% relative to SEGRA without skills, while preserving answer quality. These results show that schema-grounded agent design and reusable execution experience improve both accuracy and efficiency for enterprise graph QA.</abstract>
<identifier type="citekey">lyu-etal-2026-segra</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-industry.164/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>2779</start>
<end>2793</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SEGRA: A Structured Experience Guided Reasoning Agent for Property Graph Question Answering
%A Lyu, Saiyue
%A Dundua, Mariam
%A Kapoor, Vishaal
%A Ahuja, Sarthak
%A Kordjazi, Neda
%A Yortucboylu, Evren
%A Amin, Harsh
%A Steinert, Rebecca
%Y Atanasova, Pepa
%Y Haffari, Gholamreza
%Y Wang, Minghan
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-460-6
%F lyu-etal-2026-segra
%X Enterprise IT support knowledge graphs capture rich relationships among cases, users, devices, symptoms, taxonomic categories, root causes, and historical resolutions. Yet querying them in Gremlin requires knowledge of graph schemas, traversal semantics, edge directionality, and property-graph-specific constraints, making them difficult for non-expert operators to use. We introduce SEGRA, an experience-guided agent for enterprise text-to-Gremlin question answering. SEGRA integrates intent routing, schema- and taxonomy-grounded query generation, multi-shot decomposition, execution-aware verification, and a curriculum-bootstrapped skill library that reuses verified query patterns. On an enterprise IT support benchmark, SEGRA achieves a 7.0\times higher mean judge score than backbone-only chain-of-thought prompting. Its skill library further reduces LLM calls by 20% and dollar cost by 18% relative to SEGRA without skills, while preserving answer quality. These results show that schema-grounded agent design and reusable execution experience improve both accuracy and efficiency for enterprise graph QA.
%U https://aclanthology.org/2026.emnlp-industry.164/
%P 2779-2793
Markdown (Informal)
[SEGRA: A Structured Experience Guided Reasoning Agent for Property Graph Question Answering](https://aclanthology.org/2026.emnlp-industry.164/) (Lyu et al., EMNLP 2026)
ACL
- Saiyue Lyu, Mariam Dundua, Vishaal Kapoor, Sarthak Ahuja, Neda Kordjazi, Evren Yortucboylu, Harsh Amin, and Rebecca Steinert. 2026. SEGRA: A Structured Experience Guided Reasoning Agent for Property Graph Question Answering. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track, pages 2779–2793, Budapest, Hungary. Association for Computational Linguistics.