<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yang-etal-2026-reloop">
    <titleInfo>
        <title>RELOOP: Recursive Retrieval with Multi-Hop Reasoner and Planners for Heterogeneous QA</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Ruiyi</namePart>
        <namePart type="family">Yang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Hao</namePart>
        <namePart type="family">Xue</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Imran</namePart>
        <namePart type="family">Razzak</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Hakim</namePart>
        <namePart type="family">Hacid</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Flora</namePart>
        <namePart type="given">D</namePart>
        <namePart type="family">Salim</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>Retrieval-augmented generation (RAG) remains challenging for multi-hop question answering when supporting evidence is distributed across heterogeneous sources, including text, tables, and knowledge graphs (KGs). Existing systems often rely on modality-specific retrieval pipelines or uncontrolled iterative search, making it difficult to preserve source structure while maintaining efficient evidence acquisition. We present **RELOOP**, a structure-aware retrieval framework built on **Hierarchical Sequence (HSEQ)**, a reversible representation that maps heterogeneous sources into provenance-preserving typed segments with lightweight structural links. Operating on this unified evidence interface, a lightweight iterator selects and expands candidate evidence through structure-respecting actions, while an explicit sufficiency signal determines when the accumulated evidence is adequate for answering. A head module then synthesizes the final answer from a compact, canonicalized evidence package, with an optional refinement step when inconsistent evidence is detected. Experiments on HotpotQA, HybridQA, TAT-QA, and MetaQA show that RELOOP consistently improves answer quality over strong single-pass and iterative RAG baselines while requiring substantially fewer retrieval steps than graph-expansion approaches. These results suggest that a reversible, structure-aware evidence interface provides an effective foundation for accurate and budget-controlled retrieval across heterogeneous QA settings.</abstract>
    <identifier type="citekey">yang-etal-2026-reloop</identifier>
    <location>
        <url>https://aclanthology.org/2026.findings-emnlp.1736/</url>
    </location>
    <part>
        <date>2026-10</date>
        <extent unit="page">
            <start>37120</start>
            <end>37138</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T RELOOP: Recursive Retrieval with Multi-Hop Reasoner and Planners for Heterogeneous QA
%A Yang, Ruiyi
%A Xue, Hao
%A Razzak, Imran
%A Hacid, Hakim
%A Salim, Flora D.
%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 yang-etal-2026-reloop
%X Retrieval-augmented generation (RAG) remains challenging for multi-hop question answering when supporting evidence is distributed across heterogeneous sources, including text, tables, and knowledge graphs (KGs). Existing systems often rely on modality-specific retrieval pipelines or uncontrolled iterative search, making it difficult to preserve source structure while maintaining efficient evidence acquisition. We present **RELOOP**, a structure-aware retrieval framework built on **Hierarchical Sequence (HSEQ)**, a reversible representation that maps heterogeneous sources into provenance-preserving typed segments with lightweight structural links. Operating on this unified evidence interface, a lightweight iterator selects and expands candidate evidence through structure-respecting actions, while an explicit sufficiency signal determines when the accumulated evidence is adequate for answering. A head module then synthesizes the final answer from a compact, canonicalized evidence package, with an optional refinement step when inconsistent evidence is detected. Experiments on HotpotQA, HybridQA, TAT-QA, and MetaQA show that RELOOP consistently improves answer quality over strong single-pass and iterative RAG baselines while requiring substantially fewer retrieval steps than graph-expansion approaches. These results suggest that a reversible, structure-aware evidence interface provides an effective foundation for accurate and budget-controlled retrieval across heterogeneous QA settings.
%U https://aclanthology.org/2026.findings-emnlp.1736/
%P 37120-37138

Markdown (Informal)

[RELOOP: Recursive Retrieval with Multi-Hop Reasoner and Planners for Heterogeneous QA](https://aclanthology.org/2026.findings-emnlp.1736/) (Yang et al., Findings 2026)

• RELOOP: Recursive Retrieval with Multi-Hop Reasoner and Planners for Heterogeneous QA (Yang et al., Findings 2026)

ACL

• Ruiyi Yang, Hao Xue, Imran Razzak, Hakim Hacid, and Flora D. Salim. 2026. RELOOP: Recursive Retrieval with Multi-Hop Reasoner and Planners for Heterogeneous QA. In Findings of the Association for Computational Linguistics: EMNLP 2026, pages 37120–37138, Budapest, Hungary. Association for Computational Linguistics.