<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pattnayak-2026-llm">
    <titleInfo>
        <title>When LLM Plans Fail: Solver-Verified Remediation Under Operational Constraints</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Priyaranjan</namePart>
        <namePart type="family">Pattnayak</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>We study postmortem remediation planning for large-scale cloud incidents, focusing on whether generated actions are feasible, safe, and executable under real operational constraints. While LLM-based systems can produce structured corrective actions, we find that 25–35% of generated plans across 8,200 real-world incidents violate at least one feasibility constraint due to hidden dependencies, policy limits, or risk budgets.\par We introduce Solver-Verified Remediation Planning (SVRP), a decision-centric framework that separates action proposal from feasibility verification. An LLM proposes candidate actions, which are verified using an explicit constraint system and satisfiability solving; minimal unsatisfiable cores guide targeted repair or abstention. SVRP raises feasibility from 62.4% to over 93.1%, reduces unsafe actions by more than 50%, and improves expert-rated executability from 3.7 to 4.7, while preserving semantic intent. These results suggest that remediation failures often reflect structural constraints that benefit from solver-backed verification in addition to improved prompting.</abstract>
    <identifier type="citekey">pattnayak-2026-llm</identifier>
    <location>
        <url>https://aclanthology.org/2026.emnlp-industry.146/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>2453</start>
            <end>2472</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T When LLM Plans Fail: Solver-Verified Remediation Under Operational Constraints
%A Pattnayak, Priyaranjan
%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 pattnayak-2026-llm
%X We study postmortem remediation planning for large-scale cloud incidents, focusing on whether generated actions are feasible, safe, and executable under real operational constraints. While LLM-based systems can produce structured corrective actions, we find that 25–35% of generated plans across 8,200 real-world incidents violate at least one feasibility constraint due to hidden dependencies, policy limits, or risk budgets.\par We introduce Solver-Verified Remediation Planning (SVRP), a decision-centric framework that separates action proposal from feasibility verification. An LLM proposes candidate actions, which are verified using an explicit constraint system and satisfiability solving; minimal unsatisfiable cores guide targeted repair or abstention. SVRP raises feasibility from 62.4% to over 93.1%, reduces unsafe actions by more than 50%, and improves expert-rated executability from 3.7 to 4.7, while preserving semantic intent. These results suggest that remediation failures often reflect structural constraints that benefit from solver-backed verification in addition to improved prompting.
%U https://aclanthology.org/2026.emnlp-industry.146/
%P 2453-2472

Markdown (Informal)

[When LLM Plans Fail: Solver-Verified Remediation Under Operational Constraints](https://aclanthology.org/2026.emnlp-industry.146/) (Pattnayak, EMNLP 2026)

• When LLM Plans Fail: Solver-Verified Remediation Under Operational Constraints (Pattnayak, EMNLP 2026)

ACL

• Priyaranjan Pattnayak. 2026. When LLM Plans Fail: Solver-Verified Remediation Under Operational Constraints. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track, pages 2453–2472, Budapest, Hungary. Association for Computational Linguistics.