<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lin-etal-2026-prompt">
    <titleInfo>
        <title>When Do Prompt-Side Agent Playbooks Transfer?Accuracy, Cost, and Runtime Shift in Agent Deployment</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Weihong</namePart>
        <namePart type="family">Lin</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Xiangzheng</namePart>
        <namePart type="family">Zhang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Lin</namePart>
        <namePart type="family">Sun</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>Prompt-side playbooks can improve tool-using language agents without retraining, but their portability beyond the source setting is unclear. We study frozen playbook transfer under a shared distill–validate–transfer protocol. On ALFWorld, transfer is beneficial under controlled greedy decoding and, in one near-budget-matched comparison, distilled guidance outperforms five fixed demonstrations. On TAU2-Bench, a prespecified aggregate contrast supports a modest average matched-domain advantage, but global Holm correction retains only one of 135 route-level effects; the remaining grid provides descriptive evidence of compatibility-sensitive heterogeneity. On XBench-DeepSearch, one artifact–runtime pairing preserves useful first-try heuristics while producing repeated queries, delayed stopping, and substantial cost inflation after a context-runtime shift. Across benchmarks, transferred and target-derived playbooks both require target-side validation of success, termination, protocol compatibility, and cost. Frozen transfer is therefore a conditional cold-start option, not a reuse-by-default strategy or a universally preferable alternative to target-side redistillation.</abstract>
    <identifier type="citekey">lin-etal-2026-prompt</identifier>
    <location>
        <url>https://aclanthology.org/2026.emnlp-industry.251/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>4243</start>
            <end>4263</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T When Do Prompt-Side Agent Playbooks Transfer?Accuracy, Cost, and Runtime Shift in Agent Deployment
%A Lin, Weihong
%A Zhang, Xiangzheng
%A Sun, Lin
%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 lin-etal-2026-prompt
%X Prompt-side playbooks can improve tool-using language agents without retraining, but their portability beyond the source setting is unclear. We study frozen playbook transfer under a shared distill–validate–transfer protocol. On ALFWorld, transfer is beneficial under controlled greedy decoding and, in one near-budget-matched comparison, distilled guidance outperforms five fixed demonstrations. On TAU2-Bench, a prespecified aggregate contrast supports a modest average matched-domain advantage, but global Holm correction retains only one of 135 route-level effects; the remaining grid provides descriptive evidence of compatibility-sensitive heterogeneity. On XBench-DeepSearch, one artifact–runtime pairing preserves useful first-try heuristics while producing repeated queries, delayed stopping, and substantial cost inflation after a context-runtime shift. Across benchmarks, transferred and target-derived playbooks both require target-side validation of success, termination, protocol compatibility, and cost. Frozen transfer is therefore a conditional cold-start option, not a reuse-by-default strategy or a universally preferable alternative to target-side redistillation.
%U https://aclanthology.org/2026.emnlp-industry.251/
%P 4243-4263

Markdown (Informal)

[When Do Prompt-Side Agent Playbooks Transfer?Accuracy, Cost, and Runtime Shift in Agent Deployment](https://aclanthology.org/2026.emnlp-industry.251/) (Lin et al., EMNLP 2026)

• When Do Prompt-Side Agent Playbooks Transfer?Accuracy, Cost, and Runtime Shift in Agent Deployment (Lin et al., EMNLP 2026)

ACL

• Weihong Lin, Xiangzheng Zhang, and Lin Sun. 2026. When Do Prompt-Side Agent Playbooks Transfer?Accuracy, Cost, and Runtime Shift in Agent Deployment. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track, pages 4243–4263, Budapest, Hungary. Association for Computational Linguistics.