@inproceedings{lv-etal-2026-knsight,
title = "Knsight: Self-Evolving Agentic System for Production Cloud Root Cause Analysis",
author = "Lv, Bo and
He, Hongge and
Wang, Xueqi",
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.10/",
pages = "145--171",
ISBN = "979-8-89176-460-6",
abstract = "Cloud incident response increasingly relies on LLM agents that translate heterogeneous telemetry and natural-language alerts into operator-facing diagnoses. However, in production RCA workflows, LLM agents commonly serialize these structured signals into text, losing the temporal and topological structure that is critical for diagnosis. We present Knsight, an industry-deployed RCA agent that converts operational telemetry into chart-image canvases and uses a frozen multimodal LLM to reason directly over visual evidence. Knsight introduces Vision Recursive-of-Thought (V-RoT), an iterative diagnose-review-refine loop in which a Reviewer module inspects each canvas and decides whether to refine, zoom in, or stop. To adapt across recurring production failures, Knsight further converts Reviewer feedback into a shared, alias-substituted skill library used at inference time. Offline, on the OpenRCA benchmark, Knsight improves aggregate Correct by 7.0 points over the strongest text-only baseline and reduces timeouts from 117 to 11. Online, in a 90-day deployment across 1,284 production incidents, Knsight increases top-1 acceptance from 38.9{\%} to 71.4{\%} and reduces time-to-acknowledge and time-to-resolve by 59{\%} and 32{\%}, respectively."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lv-etal-2026-knsight">
<titleInfo>
<title>Knsight: Self-Evolving Agentic System for Production Cloud Root Cause Analysis</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bo</namePart>
<namePart type="family">Lv</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hongge</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xueqi</namePart>
<namePart type="family">Wang</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>Cloud incident response increasingly relies on LLM agents that translate heterogeneous telemetry and natural-language alerts into operator-facing diagnoses. However, in production RCA workflows, LLM agents commonly serialize these structured signals into text, losing the temporal and topological structure that is critical for diagnosis. We present Knsight, an industry-deployed RCA agent that converts operational telemetry into chart-image canvases and uses a frozen multimodal LLM to reason directly over visual evidence. Knsight introduces Vision Recursive-of-Thought (V-RoT), an iterative diagnose-review-refine loop in which a Reviewer module inspects each canvas and decides whether to refine, zoom in, or stop. To adapt across recurring production failures, Knsight further converts Reviewer feedback into a shared, alias-substituted skill library used at inference time. Offline, on the OpenRCA benchmark, Knsight improves aggregate Correct by 7.0 points over the strongest text-only baseline and reduces timeouts from 117 to 11. Online, in a 90-day deployment across 1,284 production incidents, Knsight increases top-1 acceptance from 38.9% to 71.4% and reduces time-to-acknowledge and time-to-resolve by 59% and 32%, respectively.</abstract>
<identifier type="citekey">lv-etal-2026-knsight</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-industry.10/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>145</start>
<end>171</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Knsight: Self-Evolving Agentic System for Production Cloud Root Cause Analysis
%A Lv, Bo
%A He, Hongge
%A Wang, Xueqi
%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 lv-etal-2026-knsight
%X Cloud incident response increasingly relies on LLM agents that translate heterogeneous telemetry and natural-language alerts into operator-facing diagnoses. However, in production RCA workflows, LLM agents commonly serialize these structured signals into text, losing the temporal and topological structure that is critical for diagnosis. We present Knsight, an industry-deployed RCA agent that converts operational telemetry into chart-image canvases and uses a frozen multimodal LLM to reason directly over visual evidence. Knsight introduces Vision Recursive-of-Thought (V-RoT), an iterative diagnose-review-refine loop in which a Reviewer module inspects each canvas and decides whether to refine, zoom in, or stop. To adapt across recurring production failures, Knsight further converts Reviewer feedback into a shared, alias-substituted skill library used at inference time. Offline, on the OpenRCA benchmark, Knsight improves aggregate Correct by 7.0 points over the strongest text-only baseline and reduces timeouts from 117 to 11. Online, in a 90-day deployment across 1,284 production incidents, Knsight increases top-1 acceptance from 38.9% to 71.4% and reduces time-to-acknowledge and time-to-resolve by 59% and 32%, respectively.
%U https://aclanthology.org/2026.emnlp-industry.10/
%P 145-171
Markdown (Informal)
[Knsight: Self-Evolving Agentic System for Production Cloud Root Cause Analysis](https://aclanthology.org/2026.emnlp-industry.10/) (Lv et al., EMNLP 2026)
ACL