@inproceedings{joshi-etal-2026-trace,
title = "{TRACE}: Traceable Root-cause Analysis with Calibrated Evidence-grounded agents",
author = "Joshi, Aniket and
DSouza, Cyrus Andre and
Jain, Sejal and
Channappagoudar, Manjunath",
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.135/",
pages = "2279--2289",
ISBN = "979-8-89176-460-6",
abstract = "Root Cause Analysis (RCA) for defects in large e-commerce enterprises is manual and slow: a single defect spanning thousands of microservices and SOPs takes experts one to two weeks to diagnose. Generic agentic RCA frameworks fail on this workload because they stop at proximate causes, cannot verify numeric claims, ignore past reviewer decisions, and return enumerated hypotheses rather than the quantified narratives business teams act on. We present Trace, an end-to-end agentic RCA system that combines supervised hypothesis-driven investigation with recursive why-drilling, an evidence-traceable multi-tool suite with stable artifact identifiers, a feedback retrieval and ingestion pipeline, and a two-layer confidence framework combining six mechanistic checks with an LLM judge - including a novel numerical-traceability score. Across several thousand cohorts spanning eight use cases in three metric categories (cost, quality, and inventory), Trace achieves 65.4{\%} expert acceptance; on a 240-cohort head-to-head benchmark it reaches 67.1{\%} vs. 38.8{\%} for a matched ReAct baseline (+28.3pp, p{\ensuremath{<}}0.001) with calibrated confidence (AUC 0.819, ECE 0.041)."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="joshi-etal-2026-trace">
<titleInfo>
<title>TRACE: Traceable Root-cause Analysis with Calibrated Evidence-grounded agents</title>
</titleInfo>
<name type="personal">
<namePart type="given">Aniket</namePart>
<namePart type="family">Joshi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cyrus</namePart>
<namePart type="given">Andre</namePart>
<namePart type="family">DSouza</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sejal</namePart>
<namePart type="family">Jain</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Manjunath</namePart>
<namePart type="family">Channappagoudar</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>Root Cause Analysis (RCA) for defects in large e-commerce enterprises is manual and slow: a single defect spanning thousands of microservices and SOPs takes experts one to two weeks to diagnose. Generic agentic RCA frameworks fail on this workload because they stop at proximate causes, cannot verify numeric claims, ignore past reviewer decisions, and return enumerated hypotheses rather than the quantified narratives business teams act on. We present Trace, an end-to-end agentic RCA system that combines supervised hypothesis-driven investigation with recursive why-drilling, an evidence-traceable multi-tool suite with stable artifact identifiers, a feedback retrieval and ingestion pipeline, and a two-layer confidence framework combining six mechanistic checks with an LLM judge - including a novel numerical-traceability score. Across several thousand cohorts spanning eight use cases in three metric categories (cost, quality, and inventory), Trace achieves 65.4% expert acceptance; on a 240-cohort head-to-head benchmark it reaches 67.1% vs. 38.8% for a matched ReAct baseline (+28.3pp, p\ensuremath<0.001) with calibrated confidence (AUC 0.819, ECE 0.041).</abstract>
<identifier type="citekey">joshi-etal-2026-trace</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-industry.135/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>2279</start>
<end>2289</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T TRACE: Traceable Root-cause Analysis with Calibrated Evidence-grounded agents
%A Joshi, Aniket
%A DSouza, Cyrus Andre
%A Jain, Sejal
%A Channappagoudar, Manjunath
%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 joshi-etal-2026-trace
%X Root Cause Analysis (RCA) for defects in large e-commerce enterprises is manual and slow: a single defect spanning thousands of microservices and SOPs takes experts one to two weeks to diagnose. Generic agentic RCA frameworks fail on this workload because they stop at proximate causes, cannot verify numeric claims, ignore past reviewer decisions, and return enumerated hypotheses rather than the quantified narratives business teams act on. We present Trace, an end-to-end agentic RCA system that combines supervised hypothesis-driven investigation with recursive why-drilling, an evidence-traceable multi-tool suite with stable artifact identifiers, a feedback retrieval and ingestion pipeline, and a two-layer confidence framework combining six mechanistic checks with an LLM judge - including a novel numerical-traceability score. Across several thousand cohorts spanning eight use cases in three metric categories (cost, quality, and inventory), Trace achieves 65.4% expert acceptance; on a 240-cohort head-to-head benchmark it reaches 67.1% vs. 38.8% for a matched ReAct baseline (+28.3pp, p\ensuremath<0.001) with calibrated confidence (AUC 0.819, ECE 0.041).
%U https://aclanthology.org/2026.emnlp-industry.135/
%P 2279-2289
Markdown (Informal)
[TRACE: Traceable Root-cause Analysis with Calibrated Evidence-grounded agents](https://aclanthology.org/2026.emnlp-industry.135/) (Joshi et al., EMNLP 2026)
ACL