<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="stereciu-etal-2026-agent">
    <titleInfo>
        <title>Agent-Readiness of Synthesized API Tools: Parametric Gravity and the Limits of Documentation Grounding</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Teodora</namePart>
        <namePart type="family">Stereciu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Baohao</namePart>
        <namePart type="family">Liao</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Christian</namePart>
        <namePart type="family">Herold</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Shahram</namePart>
        <namePart type="family">Khadivi</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Christof</namePart>
        <namePart type="family">Monz</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 Second Workshop for REsearch on Agent Language Models (REALM 2026)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Ehsan</namePart>
            <namePart type="family">Kamalloo</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Nicolas</namePart>
            <namePart type="family">Gontier</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Nikolai</namePart>
            <namePart type="family">Rozanov</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Maryam</namePart>
            <namePart type="family">Hashemzadeh</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Akhil</namePart>
            <namePart type="family">Arora</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">979-8-89176-485-9</identifier>
    </relatedItem>
    <abstract>We study whether LLM agents can autonomously synthesize deployment-ready MCP (Model Context Protocol) servers from raw REST API documentation, and whether the resulting servers are reliable enough for downstream agentic task completion. Evaluating 8 synthesis models across 14 APIs under three documentation conditions — full docs, no docs, and counterfactually mutated docs — we find that synthesis is broadly feasible: 11 of 14 APIs achieve sufficient tool coverage, and synthesized servers match or exceed human-authored references. The dominant mediating factor is not model capability but parametric gravity: for well-known APIs (GitHub, Stripe, Shopify), training-time knowledge overrides in-context documentation, rendering documentation provision neutral or harmful. A counterfactual mutation study confirms this: high-familiarity APIs show near-zero adherence to renamed parameters, while low-familiarity APIs show near-complete adherence. Logit-lens probing shows the representations of memory and context become increasingly separable in the final transformer layers, consistent with deep feed-forward MLP modules as the site of parametric association storage. Synthesis coverage (SYNTH) correlates strongly with agent task completion (r = 0.937), providing a reliable pre-flight quality signal without requiring agent evaluation.</abstract>
    <identifier type="citekey">stereciu-etal-2026-agent</identifier>
    <location>
        <url>https://aclanthology.org/2026.realm-1.22/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>323</start>
            <end>340</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Agent-Readiness of Synthesized API Tools: Parametric Gravity and the Limits of Documentation Grounding
%A Stereciu, Teodora
%A Liao, Baohao
%A Herold, Christian
%A Khadivi, Shahram
%A Monz, Christof
%Y Kamalloo, Ehsan
%Y Gontier, Nicolas
%Y Rozanov, Nikolai
%Y Hashemzadeh, Maryam
%Y Arora, Akhil
%S Proceedings of the Second Workshop for REsearch on Agent Language Models (REALM 2026)
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-485-9
%F stereciu-etal-2026-agent
%X We study whether LLM agents can autonomously synthesize deployment-ready MCP (Model Context Protocol) servers from raw REST API documentation, and whether the resulting servers are reliable enough for downstream agentic task completion. Evaluating 8 synthesis models across 14 APIs under three documentation conditions — full docs, no docs, and counterfactually mutated docs — we find that synthesis is broadly feasible: 11 of 14 APIs achieve sufficient tool coverage, and synthesized servers match or exceed human-authored references. The dominant mediating factor is not model capability but parametric gravity: for well-known APIs (GitHub, Stripe, Shopify), training-time knowledge overrides in-context documentation, rendering documentation provision neutral or harmful. A counterfactual mutation study confirms this: high-familiarity APIs show near-zero adherence to renamed parameters, while low-familiarity APIs show near-complete adherence. Logit-lens probing shows the representations of memory and context become increasingly separable in the final transformer layers, consistent with deep feed-forward MLP modules as the site of parametric association storage. Synthesis coverage (SYNTH) correlates strongly with agent task completion (r = 0.937), providing a reliable pre-flight quality signal without requiring agent evaluation.
%U https://aclanthology.org/2026.realm-1.22/
%P 323-340

Markdown (Informal)

[Agent-Readiness of Synthesized API Tools: Parametric Gravity and the Limits of Documentation Grounding](https://aclanthology.org/2026.realm-1.22/) (Stereciu et al., REALM 2026)

• Agent-Readiness of Synthesized API Tools: Parametric Gravity and the Limits of Documentation Grounding (Stereciu et al., REALM 2026)

ACL

• Teodora Stereciu, Baohao Liao, Christian Herold, Shahram Khadivi, and Christof Monz. 2026. Agent-Readiness of Synthesized API Tools: Parametric Gravity and the Limits of Documentation Grounding. In Proceedings of the Second Workshop for REsearch on Agent Language Models (REALM 2026), pages 323–340, Budapest, Hungary. Association for Computational Linguistics.