<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="he-etal-2026-lost">
    <titleInfo>
        <title>Lost in the Handoff: Contract-Aware Compliance Checking for Multi-Agent LLM Systems</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Yang</namePart>
        <namePart type="family">He</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jinlin</namePart>
        <namePart type="family">Wang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yulong</namePart>
        <namePart type="family">Ji</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Jianwei</namePart>
        <namePart type="family">Zhang</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>When LLM agents exchange messages in a pipeline, abstractive compression discards task constraints. Routing tags get absorbed into prose, privacy fields get paraphrased, hard instructions get softened. Even exhaustive reminder-based prompting retains only 53% of required routing markers, as measured by RTD: constraint tokens are low-salience relative to task content and are dropped at generation step boundaries even when restated in full. We propose C2-FAIC (Contract-Claim Failure-Aware Inter-agent Compliance), which guards the handoff moment directly: it maintains task requirements in a contract ledger outside agent context and checks each candidate message before it enters the shared trace. On 916 task-metric slices across AgentCollabBench, C2-FAIC is strongest on tracer retention and cross-context leakage control, while also reducing instruction decay and claim propagation relative to no intervention. Critic agents remain stronger on pure IDR and CPR process scores, showing that contract enforcement and generic critique address different failure structures. Multi-agent reliability requires controlling what crosses communication boundaries, not only evaluating what the pipeline ultimately produces.</abstract>
    <identifier type="citekey">he-etal-2026-lost</identifier>
    <location>
        <url>https://aclanthology.org/2026.realm-1.89/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>1270</start>
            <end>1279</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Lost in the Handoff: Contract-Aware Compliance Checking for Multi-Agent LLM Systems
%A He, Yang
%A Wang, Jinlin
%A Ji, Yulong
%A Zhang, Jianwei
%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 he-etal-2026-lost
%X When LLM agents exchange messages in a pipeline, abstractive compression discards task constraints. Routing tags get absorbed into prose, privacy fields get paraphrased, hard instructions get softened. Even exhaustive reminder-based prompting retains only 53% of required routing markers, as measured by RTD: constraint tokens are low-salience relative to task content and are dropped at generation step boundaries even when restated in full. We propose C2-FAIC (Contract-Claim Failure-Aware Inter-agent Compliance), which guards the handoff moment directly: it maintains task requirements in a contract ledger outside agent context and checks each candidate message before it enters the shared trace. On 916 task-metric slices across AgentCollabBench, C2-FAIC is strongest on tracer retention and cross-context leakage control, while also reducing instruction decay and claim propagation relative to no intervention. Critic agents remain stronger on pure IDR and CPR process scores, showing that contract enforcement and generic critique address different failure structures. Multi-agent reliability requires controlling what crosses communication boundaries, not only evaluating what the pipeline ultimately produces.
%U https://aclanthology.org/2026.realm-1.89/
%P 1270-1279

Markdown (Informal)

[Lost in the Handoff: Contract-Aware Compliance Checking for Multi-Agent LLM Systems](https://aclanthology.org/2026.realm-1.89/) (He et al., REALM 2026)

• Lost in the Handoff: Contract-Aware Compliance Checking for Multi-Agent LLM Systems (He et al., REALM 2026)

ACL

• Yang He, Jinlin Wang, Yulong Ji, and Jianwei Zhang. 2026. Lost in the Handoff: Contract-Aware Compliance Checking for Multi-Agent LLM Systems. In Proceedings of the Second Workshop for REsearch on Agent Language Models (REALM 2026), pages 1270–1279, Budapest, Hungary. Association for Computational Linguistics.