<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bako-etal-2026-frustratingly">
    <titleInfo>
        <title>Frustratingly Easy Agentic RAG via Portable Skills: A Case Study in Customer Support</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Istok</namePart>
        <namePart type="family">Bako</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Bonan</namePart>
        <namePart type="family">Min</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Qihong</namePart>
        <namePart type="family">Shao</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Claire</namePart>
        <namePart type="family">Cheng</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yashar</namePart>
        <namePart type="family">Mehdad</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 workflow automation typically requires retrieving a complete and accurate set of relevant information from large operational document corpora (SOPs, policy documents) given a specific scenario or request. In customer support (CS), for example, human specialists must determine the correct sequence of resolution steps for each case, a task that demands precise grounding in policy documentation. Meeting this bar in production typically requires complex document chunking, indexing, and retrieval pipelines, often layered with learned re-rankers, query rewriters, and bespoke agentic RAG infrastructure.\par We present a simpler alternative: a portable skill consisting of a natural-language instruction, lightweight tools (a retrieval API, format-checking scripts), and a corpus enriched with an LLM-generated navigation layer, which is a structured “Wikipedia-style” index over the underlying documents. This agentic RAG approach is straightforward to implement (1-2 engineer days), portable across capable agentic harnesses (e.g., Claude Code), and performs strongly on the challenging task of CS resolution workflow generation, achieving 99.2% procedural equivalence to human-approved ground truth and 83.3% evidence sufficiency. Our analysis yields a concrete deployment insight: a skill-based agentic RAG implementation over a corpus augmented with a lightweight navigation layer can substitute for complex RAG infrastructure, shifting the primary maintenance burden from model artifacts to text and data curation.</abstract>
    <identifier type="citekey">bako-etal-2026-frustratingly</identifier>
    <location>
        <url>https://aclanthology.org/2026.emnlp-industry.156/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>2647</start>
            <end>2661</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Frustratingly Easy Agentic RAG via Portable Skills: A Case Study in Customer Support
%A Bako, Istok
%A Min, Bonan
%A Shao, Qihong
%A Cheng, Claire
%A Mehdad, Yashar
%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 bako-etal-2026-frustratingly
%X Enterprise workflow automation typically requires retrieving a complete and accurate set of relevant information from large operational document corpora (SOPs, policy documents) given a specific scenario or request. In customer support (CS), for example, human specialists must determine the correct sequence of resolution steps for each case, a task that demands precise grounding in policy documentation. Meeting this bar in production typically requires complex document chunking, indexing, and retrieval pipelines, often layered with learned re-rankers, query rewriters, and bespoke agentic RAG infrastructure.\par We present a simpler alternative: a portable skill consisting of a natural-language instruction, lightweight tools (a retrieval API, format-checking scripts), and a corpus enriched with an LLM-generated navigation layer, which is a structured “Wikipedia-style” index over the underlying documents. This agentic RAG approach is straightforward to implement (1-2 engineer days), portable across capable agentic harnesses (e.g., Claude Code), and performs strongly on the challenging task of CS resolution workflow generation, achieving 99.2% procedural equivalence to human-approved ground truth and 83.3% evidence sufficiency. Our analysis yields a concrete deployment insight: a skill-based agentic RAG implementation over a corpus augmented with a lightweight navigation layer can substitute for complex RAG infrastructure, shifting the primary maintenance burden from model artifacts to text and data curation.
%U https://aclanthology.org/2026.emnlp-industry.156/
%P 2647-2661

Markdown (Informal)

[Frustratingly Easy Agentic RAG via Portable Skills: A Case Study in Customer Support](https://aclanthology.org/2026.emnlp-industry.156/) (Bako et al., EMNLP 2026)

• Frustratingly Easy Agentic RAG via Portable Skills: A Case Study in Customer Support (Bako et al., EMNLP 2026)

ACL

• Istok Bako, Bonan Min, Qihong Shao, Claire Cheng, and Yashar Mehdad. 2026. Frustratingly Easy Agentic RAG via Portable Skills: A Case Study in Customer Support. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track, pages 2647–2661, Budapest, Hungary. Association for Computational Linguistics.