<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="banerjee-chadha-2026-routed">
    <titleInfo>
        <title>Routed Graph Handoff: Adaptive Format Selection for Multi-Agent LLM Delegation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Pratyay</namePart>
        <namePart type="family">Banerjee</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ankit</namePart>
        <namePart type="family">Chadha</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>Findings of the Association for Computational Linguistics: EMNLP 2026</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Hung-Yi</namePart>
            <namePart type="family">Lee</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Sunipa</namePart>
            <namePart type="family">Dev</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Jessy</namePart>
            <namePart type="family">Li</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Desmond</namePart>
            <namePart type="family">Elliott</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">979-8-89176-462-0</identifier>
    </relatedItem>
    <abstract>Multi-agent LLM systems coordinate through natural-language messages that consume 40–60% of their token budget. Replacing these with structured graphs reduces cost but fails on tasks requiring adaptive reasoning. We propose Routed Graph Handoff, where a lightweight LLM router (155 tokens, 0.15% overhead) selects between a typed dependency graph and natural language for each delegation. On four benchmarks (1,050+ trajectories), the routed system matches or exceeds NL-only on every task: +12.7,pp on Tau-retail at 3.2 X compression (p\ensuremath&lt;0.01), +8.7,pp on BrowseComp at 2.2 compression (p\ensuremath&lt;0.05), and parity on BFCL and AppWorld. Without the router, graph-only delegation regresses 14.6,pp on AppWorld—the router eliminates this at near-zero cost. A graph-aware executor prompt is load-bearing: the same schema without interpretation guidance yields no gain. An oracle analysis reveals 8.6,pp of additional headroom, motivating execution-time adaptive routing as future work.</abstract>
    <identifier type="citekey">banerjee-chadha-2026-routed</identifier>
    <location>
        <url>https://aclanthology.org/2026.findings-emnlp.2008/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>42756</start>
            <end>42765</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Routed Graph Handoff: Adaptive Format Selection for Multi-Agent LLM Delegation
%A Banerjee, Pratyay
%A Chadha, Ankit
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F banerjee-chadha-2026-routed
%X Multi-agent LLM systems coordinate through natural-language messages that consume 40–60% of their token budget. Replacing these with structured graphs reduces cost but fails on tasks requiring adaptive reasoning. We propose Routed Graph Handoff, where a lightweight LLM router (155 tokens, 0.15% overhead) selects between a typed dependency graph and natural language for each delegation. On four benchmarks (1,050+ trajectories), the routed system matches or exceeds NL-only on every task: +12.7,pp on Tau-retail at 3.2 X compression (p\ensuremath<0.01), +8.7,pp on BrowseComp at 2.2 compression (p\ensuremath<0.05), and parity on BFCL and AppWorld. Without the router, graph-only delegation regresses 14.6,pp on AppWorld—the router eliminates this at near-zero cost. A graph-aware executor prompt is load-bearing: the same schema without interpretation guidance yields no gain. An oracle analysis reveals 8.6,pp of additional headroom, motivating execution-time adaptive routing as future work.
%U https://aclanthology.org/2026.findings-emnlp.2008/
%P 42756-42765

Markdown (Informal)

[Routed Graph Handoff: Adaptive Format Selection for Multi-Agent LLM Delegation](https://aclanthology.org/2026.findings-emnlp.2008/) (Banerjee & Chadha, Findings 2026)

• Routed Graph Handoff: Adaptive Format Selection for Multi-Agent LLM Delegation (Banerjee & Chadha, Findings 2026)

ACL

• Pratyay Banerjee and Ankit Chadha. 2026. Routed Graph Handoff: Adaptive Format Selection for Multi-Agent LLM Delegation. In Findings of the Association for Computational Linguistics: EMNLP 2026, pages 42756–42765, Budapest, Hungary. Association for Computational Linguistics.