<?xml version="1.0" encoding="utf-8"?>
<TEI xmlns="http://www.tei-c.org/ns/1.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:hal="http://hal.archives-ouvertes.fr/" xmlns:gml="http://www.opengis.net/gml/3.3/" xmlns:gmlce="http://www.opengis.net/gml/3.3/ce" version="1.1" xsi:schemaLocation="http://www.tei-c.org/ns/1.0 http://api.archives-ouvertes.fr/documents/aofr-sword.xsd">
  <teiHeader>
    <fileDesc>
      <titleStmt>
        <title>HAL TEI export of hal-05466131</title>
      </titleStmt>
      <publicationStmt>
        <distributor>CCSD</distributor>
        <availability status="restricted">
          <licence target="https://creativecommons.org/publicdomain/zero/1.0/">CC0 1.0 - Universal</licence>
        </availability>
        <date when="2026-05-26T06:15:03+02:00"/>
      </publicationStmt>
      <sourceDesc>
        <p part="N">HAL API Platform</p>
      </sourceDesc>
    </fileDesc>
  </teiHeader>
  <text>
    <body>
      <listBibl>
        <biblFull>
          <titleStmt>
            <title xml:lang="en">Human-in-Command Governance for Multi-Agent Scientific Workflows</title>
            <author role="aut">
              <persName>
                <forename type="first">Samed</forename>
                <surname>Bayer</surname>
              </persName>
              <email type="md5">60521c69fcf2d6b17208aa63d4487ac4</email>
              <email type="domain">tum.de</email>
              <idno type="idhal" notation="numeric">1634538</idno>
              <idno type="halauthorid" notation="string">3991470-1634538</idno>
              <idno type="ORCID">https://orcid.org/0009-0007-9318-3406</idno>
              <affiliation ref="#struct-132871"/>
              <affiliation ref="#struct-330453"/>
            </author>
            <author role="aut">
              <persName>
                <forename type="first">Ingo</forename>
                <surname>Weber</surname>
              </persName>
              <email type="md5">ac1c9df3517fcf02528da8165c796126</email>
              <email type="domain">tum.de</email>
              <idno type="idhal" notation="numeric">1634539</idno>
              <idno type="halauthorid" notation="string">426300-1634539</idno>
              <idno type="ORCID">https://orcid.org/0000-0002-4833-5921</idno>
              <affiliation ref="#struct-132871"/>
              <affiliation ref="#struct-330453"/>
            </author>
            <editor role="depositor">
              <persName>
                <forename>Bayer</forename>
                <surname>Samed</surname>
              </persName>
              <email type="md5">60521c69fcf2d6b17208aa63d4487ac4</email>
              <email type="domain">tum.de</email>
            </editor>
          </titleStmt>
          <editionStmt>
            <edition n="v1" type="current">
              <date type="whenSubmitted">2026-01-19 16:37:14</date>
              <date type="whenModified">2026-02-12 08:23:26</date>
              <date type="whenReleased">2026-02-12 08:23:26</date>
              <date type="whenProduced">2026-01-19</date>
              <date type="whenEndEmbargoed">2026-01-19</date>
              <ref type="file" target="https://hal.science/hal-05466131v1/document">
                <date notBefore="2026-01-19"/>
              </ref>
              <ref type="file" subtype="author" n="1" target="https://hal.science/hal-05466131v1/file/Human-in-Command%20Governance%20for%20Multi-Agent%20Scientific%20Workflows.pdf" id="file-5466131-4671891">
                <date notBefore="2026-01-19"/>
              </ref>
            </edition>
            <respStmt>
              <resp>contributor</resp>
              <name key="1760873">
                <persName>
                  <forename>Bayer</forename>
                  <surname>Samed</surname>
                </persName>
                <email type="md5">60521c69fcf2d6b17208aa63d4487ac4</email>
                <email type="domain">tum.de</email>
              </name>
            </respStmt>
          </editionStmt>
          <publicationStmt>
            <distributor>CCSD</distributor>
            <idno type="halId">hal-05466131</idno>
            <idno type="halUri">https://hal.science/hal-05466131</idno>
            <idno type="halBibtex">bayer:hal-05466131</idno>
            <idno type="halRefHtml">2026</idno>
            <idno type="halRef">2026</idno>
            <availability status="restricted">
              <licence target="https://creativecommons.org/licenses/by/4.0/">CC BY 4.0 - Attribution<ref corresp="#file-5466131-4671891"/></licence>
            </availability>
          </publicationStmt>
          <seriesStmt/>
          <notesStmt>
            <note type="commentary">Accepted at AAAI 2026 Workshop on AI for Scientific Research (AI4Research)</note>
          </notesStmt>
          <sourceDesc>
            <biblStruct>
              <analytic>
                <title xml:lang="en">Human-in-Command Governance for Multi-Agent Scientific Workflows</title>
                <author role="aut">
                  <persName>
                    <forename type="first">Samed</forename>
                    <surname>Bayer</surname>
                  </persName>
                  <email type="md5">60521c69fcf2d6b17208aa63d4487ac4</email>
                  <email type="domain">tum.de</email>
                  <idno type="idhal" notation="numeric">1634538</idno>
                  <idno type="halauthorid" notation="string">3991470-1634538</idno>
                  <idno type="ORCID">https://orcid.org/0009-0007-9318-3406</idno>
                  <affiliation ref="#struct-132871"/>
                  <affiliation ref="#struct-330453"/>
                </author>
                <author role="aut">
                  <persName>
                    <forename type="first">Ingo</forename>
                    <surname>Weber</surname>
                  </persName>
                  <email type="md5">ac1c9df3517fcf02528da8165c796126</email>
                  <email type="domain">tum.de</email>
                  <idno type="idhal" notation="numeric">1634539</idno>
                  <idno type="halauthorid" notation="string">426300-1634539</idno>
                  <idno type="ORCID">https://orcid.org/0000-0002-4833-5921</idno>
                  <affiliation ref="#struct-132871"/>
                  <affiliation ref="#struct-330453"/>
                </author>
              </analytic>
              <monogr>
                <imprint/>
              </monogr>
            </biblStruct>
          </sourceDesc>
          <profileDesc>
            <langUsage>
              <language ident="en">English</language>
            </langUsage>
            <textClass>
              <keywords scheme="author">
                <term xml:lang="en">AI for Science</term>
                <term xml:lang="en">Multi-Agent Systems</term>
                <term xml:lang="en">Large Language Models</term>
                <term xml:lang="en">AI Governance</term>
                <term xml:lang="en">Human-in-Command</term>
              </keywords>
              <classCode scheme="halDomain" n="info.info-ai">Computer Science [cs]/Artificial Intelligence [cs.AI]</classCode>
              <classCode scheme="halDomain" n="info.info-hc">Computer Science [cs]/Human-Computer Interaction [cs.HC]</classCode>
              <classCode scheme="halTypology" n="UNDEFINED">Preprints, Working Papers, ...</classCode>
              <classCode scheme="halOldTypology" n="UNDEFINED">Preprints, Working Papers, ...</classCode>
              <classCode scheme="halTreeTypology" n="UNDEFINED">Preprints, Working Papers, ...</classCode>
            </textClass>
            <abstract xml:lang="en">
              <p>While AI can accelerate text-intensive research, unsupervised autonomous agents risk compounding errors and cannot be held accountable for the integrity of their findings. Accordingly, we propose a human-supervised, multi-agent model for Human-AI collaboration in science that reconciles the power of Large Language Models (LLMs) with the core principles of transparency and accountability. In our vision, a human researcher supervises a team of specialized AI agents that execute discrete tasks within a rigorously defined scientific methodology. Each step in the process is governed by human expert validation, in order to prevent error propagation and maintain conceptual integrity. We instantiate this model in an end-to-end framework for systematic taxonomy generation by operationalizing the Nickerson et al. (2013) methodology. We provide a proof-of-concept (PoC) implementation and a qualitative case study that validates our framework by re-deriving a recently published taxonomy. Our analysis documents the framework's fidelity to the original method and illustrates how human-gated oversight is crucial for ensuring the scientific rigor of the final taxonomy. To support reproducibility, we release our prompts, agent roles, and workflow design as a generalizable blueprint for structuring human-AI teams. This work argues that method-bounded human-in-command (HIC) supervision offers a principled and practical path to developing reliable and accountable AI research assistants.</p>
            </abstract>
          </profileDesc>
        </biblFull>
      </listBibl>
    </body>
    <back>
      <listOrg type="structures">
        <org type="institution" xml:id="struct-132871" status="VALID">
          <idno type="IdRef">031660150</idno>
          <idno type="ISNI">0000000123369749</idno>
          <idno type="ROR">https://ror.org/02kkvpp62</idno>
          <idno type="Wikidata">Q157808</idno>
          <orgName>Technische Universität Munchen = Technical University Munich = Université Technique de Munich</orgName>
          <orgName type="acronym">TUM</orgName>
          <date type="start">1868-01-01</date>
          <desc>
            <address>
              <addrLine>Arcisstrasse 21, D- 80333 München</addrLine>
              <country key="DE"/>
            </address>
            <ref type="url">https://www.tum.de</ref>
          </desc>
        </org>
        <org type="regroupinstitution" xml:id="struct-330453" status="VALID">
          <idno type="ISNI">0000 0000 9261 3939</idno>
          <idno type="ROR">https://ror.org/05hkkdn48</idno>
          <orgName>Fraunhofer</orgName>
          <orgName type="acronym">Fraunhofer-Gesellschaft</orgName>
          <desc>
            <address>
              <addrLine>Hansastraße 27c, 80686 München</addrLine>
              <country key="DE"/>
            </address>
            <ref type="url">https://www.fraunhofer.de/en.html</ref>
          </desc>
        </org>
      </listOrg>
    </back>
  </text>
</TEI>