@inproceedings{imannulhakim-2026-tracing,
title = "Tracing Failures through Plant Topology: Propagation Reasoning by a Knowledge-Graph-Grounded {LLM} Agent",
author = "Imannulhakim, Muhamad",
editor = "Er-Rahmadi, Btissam and
Montella, S{\'e}bastien and
Graux, Damien and
Melo, Andr{\'e} and
Jabeen, Hajira",
booktitle = "Proceedings of the 3rd Workshop on {KNO}wledge {GR}aphs Agentic Systems Interplay ({NORA} 2026)",
month = nov,
year = "2026",
address = "Hengqin, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.nora-1.11/",
pages = "131--137",
ISBN = "979-8-89176-457-6",
abstract = "Diagnosing anomalies in process plants requires reasoning about how a failure at one unit propagates through interconnected equipment {---} knowledge that is scattered across engineering documents, and that unconstrained large language model (LLM) agents tend to fill with plausible but unsupported conclusions. We present an LLM agent, being piloted at an operating ammonia plant, whose domain memory is a knowledge graph of the plant{'}s process: a topology backbone translated from the process flow, enriched with knowledge from over 30 engineering documents. We evaluate its propagation reasoning against the graph itself using 46 generated probes, each run three times. Entity grounding holds at every depth: all 565 failure-mode attributions are correct, and the agent rejects every question that attaches a failure mode to the wrong unit. Mean path recall falls from 1.00 at two hops to 0.60 at eight, and 40{\%} of eight-hop answers deny a route the graph records. Scoping the same tools to the topology backbone, with model, prompt and graph unchanged, raises eight-hop recall to 0.81 and halves these denials, suggesting that unscoped neighbourhood queries struggle to reconstruct long process routes. Retrieval over the source documents matches the agent up to six hops but not at eight."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="imannulhakim-2026-tracing">
<titleInfo>
<title>Tracing Failures through Plant Topology: Propagation Reasoning by a Knowledge-Graph-Grounded LLM Agent</title>
</titleInfo>
<name type="personal">
<namePart type="given">Muhamad</namePart>
<namePart type="family">Imannulhakim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 3rd Workshop on KNOwledge GRaphs Agentic Systems Interplay (NORA 2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Btissam</namePart>
<namePart type="family">Er-Rahmadi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sébastien</namePart>
<namePart type="family">Montella</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Damien</namePart>
<namePart type="family">Graux</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">André</namePart>
<namePart type="family">Melo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hajira</namePart>
<namePart type="family">Jabeen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hengqin, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-457-6</identifier>
</relatedItem>
<abstract>Diagnosing anomalies in process plants requires reasoning about how a failure at one unit propagates through interconnected equipment — knowledge that is scattered across engineering documents, and that unconstrained large language model (LLM) agents tend to fill with plausible but unsupported conclusions. We present an LLM agent, being piloted at an operating ammonia plant, whose domain memory is a knowledge graph of the plant’s process: a topology backbone translated from the process flow, enriched with knowledge from over 30 engineering documents. We evaluate its propagation reasoning against the graph itself using 46 generated probes, each run three times. Entity grounding holds at every depth: all 565 failure-mode attributions are correct, and the agent rejects every question that attaches a failure mode to the wrong unit. Mean path recall falls from 1.00 at two hops to 0.60 at eight, and 40% of eight-hop answers deny a route the graph records. Scoping the same tools to the topology backbone, with model, prompt and graph unchanged, raises eight-hop recall to 0.81 and halves these denials, suggesting that unscoped neighbourhood queries struggle to reconstruct long process routes. Retrieval over the source documents matches the agent up to six hops but not at eight.</abstract>
<identifier type="citekey">imannulhakim-2026-tracing</identifier>
<location>
<url>https://aclanthology.org/2026.nora-1.11/</url>
</location>
<part>
<date>2026-11</date>
<extent unit="page">
<start>131</start>
<end>137</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Tracing Failures through Plant Topology: Propagation Reasoning by a Knowledge-Graph-Grounded LLM Agent
%A Imannulhakim, Muhamad
%Y Er-Rahmadi, Btissam
%Y Montella, Sébastien
%Y Graux, Damien
%Y Melo, André
%Y Jabeen, Hajira
%S Proceedings of the 3rd Workshop on KNOwledge GRaphs Agentic Systems Interplay (NORA 2026)
%D 2026
%8 November
%I Association for Computational Linguistics
%C Hengqin, China
%@ 979-8-89176-457-6
%F imannulhakim-2026-tracing
%X Diagnosing anomalies in process plants requires reasoning about how a failure at one unit propagates through interconnected equipment — knowledge that is scattered across engineering documents, and that unconstrained large language model (LLM) agents tend to fill with plausible but unsupported conclusions. We present an LLM agent, being piloted at an operating ammonia plant, whose domain memory is a knowledge graph of the plant’s process: a topology backbone translated from the process flow, enriched with knowledge from over 30 engineering documents. We evaluate its propagation reasoning against the graph itself using 46 generated probes, each run three times. Entity grounding holds at every depth: all 565 failure-mode attributions are correct, and the agent rejects every question that attaches a failure mode to the wrong unit. Mean path recall falls from 1.00 at two hops to 0.60 at eight, and 40% of eight-hop answers deny a route the graph records. Scoping the same tools to the topology backbone, with model, prompt and graph unchanged, raises eight-hop recall to 0.81 and halves these denials, suggesting that unscoped neighbourhood queries struggle to reconstruct long process routes. Retrieval over the source documents matches the agent up to six hops but not at eight.
%U https://aclanthology.org/2026.nora-1.11/
%P 131-137
Markdown (Informal)
[Tracing Failures through Plant Topology: Propagation Reasoning by a Knowledge-Graph-Grounded LLM Agent](https://aclanthology.org/2026.nora-1.11/) (Imannulhakim, NORA 2026)
ACL