<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yang-etal-2026-dianoia">
    <titleInfo>
        <title>DIANOIA: Diagnostic Decomposition and Joint Optimization for Multi-Agent Reasoning</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Yiming</namePart>
        <namePart type="family">Yang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Zhuoyuan</namePart>
        <namePart type="family">Li</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Fanxiang</namePart>
        <namePart type="family">Zeng</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Hao</namePart>
        <namePart type="family">Fu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yue</namePart>
        <namePart type="family">Liu</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</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">979-8-89176-459-0</identifier>
    </relatedItem>
    <abstract>Multi-agent LLM systems can outperform single-agent baselines, yet practitioners still cannot predict which design works for a new task or diagnose why one fails. We argue this gap persists largely because the field lacks a diagnostic framework with measurable primitives and testable predictions. We introduce DIANOIA, a three-channel decomposition of multi-agent reasoning gain into coverage, fidelity, and synthesis, each of which is empirically measurable. From this decomposition, we propose a diagnostic protocol that forms qualitative hypotheses about bottleneck channels for tasks with measurable quality signals. We instantiate the protocol as a multi-agent system whose three components mirror the channels: role-diverse proposers for coverage, execution- or pseudo-verification-grounded review for fidelity, and iterative synthesis. On GSM8K, MBPP, and BFCL-SP, our method outperforms strong multi-agent baselines under matched standard configurations; on MBPP, it matches the strongest baseline with approximately 5\times fewer tokens and dominates the measured accuracy–token Pareto frontier. Full-scale MBPP replications on Qwen, DeepSeek, and Gemini consistently improve over the corresponding single-model baseline. A prospective held-out evaluation on VitaBench, whose bottleneck hypothesis was recorded before running DIANOIA, improves pass rate from 29.5% to 45.0%. DIANOIA reframes multi-agent design as channel-aware resource allocation: diagnose the likely bottleneck, then invest tokens accordingly.</abstract>
    <identifier type="citekey">yang-etal-2026-dianoia</identifier>
    <location>
        <url>https://aclanthology.org/2026.emnlp-main.1446/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>33019</start>
            <end>33053</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T DIANOIA: Diagnostic Decomposition and Joint Optimization for Multi-Agent Reasoning
%A Yang, Yiming
%A Li, Zhuoyuan
%A Zeng, Fanxiang
%A Fu, Hao
%A Liu, Yue
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F yang-etal-2026-dianoia
%X Multi-agent LLM systems can outperform single-agent baselines, yet practitioners still cannot predict which design works for a new task or diagnose why one fails. We argue this gap persists largely because the field lacks a diagnostic framework with measurable primitives and testable predictions. We introduce DIANOIA, a three-channel decomposition of multi-agent reasoning gain into coverage, fidelity, and synthesis, each of which is empirically measurable. From this decomposition, we propose a diagnostic protocol that forms qualitative hypotheses about bottleneck channels for tasks with measurable quality signals. We instantiate the protocol as a multi-agent system whose three components mirror the channels: role-diverse proposers for coverage, execution- or pseudo-verification-grounded review for fidelity, and iterative synthesis. On GSM8K, MBPP, and BFCL-SP, our method outperforms strong multi-agent baselines under matched standard configurations; on MBPP, it matches the strongest baseline with approximately 5\times fewer tokens and dominates the measured accuracy–token Pareto frontier. Full-scale MBPP replications on Qwen, DeepSeek, and Gemini consistently improve over the corresponding single-model baseline. A prospective held-out evaluation on VitaBench, whose bottleneck hypothesis was recorded before running DIANOIA, improves pass rate from 29.5% to 45.0%. DIANOIA reframes multi-agent design as channel-aware resource allocation: diagnose the likely bottleneck, then invest tokens accordingly.
%U https://aclanthology.org/2026.emnlp-main.1446/
%P 33019-33053

Markdown (Informal)

[DIANOIA: Diagnostic Decomposition and Joint Optimization for Multi-Agent Reasoning](https://aclanthology.org/2026.emnlp-main.1446/) (Yang et al., EMNLP 2026)

• DIANOIA: Diagnostic Decomposition and Joint Optimization for Multi-Agent Reasoning (Yang et al., EMNLP 2026)

ACL

• Yiming Yang, Zhuoyuan Li, Fanxiang Zeng, Hao Fu, and Yue Liu. 2026. DIANOIA: Diagnostic Decomposition and Joint Optimization for Multi-Agent Reasoning. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing, pages 33019–33053, Budapest, Hungary. Association for Computational Linguistics.