@inproceedings{liang-etal-2026-crog,
title = "{CROG}: Coverage-aware Reasoning Optimization on Graphs for Multi-hop Question Answering",
author = "Liang, Junli and
Zhou, Pengfei and
Lv, Rui and
Zhou, Wangqiu and
Song, Qi and
Li, Xiang-Yang",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-main.1164/",
pages = "26632--26645",
ISBN = "979-8-89176-459-0",
abstract = "Multi-hop question answering requires retrieving and integrating multiple pieces of evidence distributed across documents. Recent graph-based methods improve multi-hop reasoning through graph traversal over relational evidence structures. However, existing methods rely on independent path ranking during evidence organization, which often produces redundant and reasoning-incomplete evidence sets due to substantial structural overlap among selected graph paths. In this work, we argue that graph-based evidence organization may, to some extent, be formulated as a constrained evidence subgraph optimization problem. Based on this perspective, we propose CROG, a coverage-aware reasoning optimization framework that performs marginal-gain-based path selection to favor previously uncovered reasoning steps while suppressing redundant evidence, with node-budget and connectivity constraints to encourage compact and coherent evidence subgraphs. Experiments on multiple benchmarks demonstrate that CROG achieves superior reasoning performance while using fewer evidence units on average, and analysis based on exhaustive optimal search further validates the effectiveness of the greedy optimization strategy."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liang-etal-2026-crog">
<titleInfo>
<title>CROG: Coverage-aware Reasoning Optimization on Graphs for Multi-hop Question Answering</title>
</titleInfo>
<name type="personal">
<namePart type="given">Junli</namePart>
<namePart type="family">Liang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pengfei</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rui</namePart>
<namePart type="family">Lv</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wangqiu</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qi</namePart>
<namePart type="family">Song</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiang-Yang</namePart>
<namePart type="family">Li</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-hop question answering requires retrieving and integrating multiple pieces of evidence distributed across documents. Recent graph-based methods improve multi-hop reasoning through graph traversal over relational evidence structures. However, existing methods rely on independent path ranking during evidence organization, which often produces redundant and reasoning-incomplete evidence sets due to substantial structural overlap among selected graph paths. In this work, we argue that graph-based evidence organization may, to some extent, be formulated as a constrained evidence subgraph optimization problem. Based on this perspective, we propose CROG, a coverage-aware reasoning optimization framework that performs marginal-gain-based path selection to favor previously uncovered reasoning steps while suppressing redundant evidence, with node-budget and connectivity constraints to encourage compact and coherent evidence subgraphs. Experiments on multiple benchmarks demonstrate that CROG achieves superior reasoning performance while using fewer evidence units on average, and analysis based on exhaustive optimal search further validates the effectiveness of the greedy optimization strategy.</abstract>
<identifier type="citekey">liang-etal-2026-crog</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-main.1164/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>26632</start>
<end>26645</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CROG: Coverage-aware Reasoning Optimization on Graphs for Multi-hop Question Answering
%A Liang, Junli
%A Zhou, Pengfei
%A Lv, Rui
%A Zhou, Wangqiu
%A Song, Qi
%A Li, Xiang-Yang
%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 liang-etal-2026-crog
%X Multi-hop question answering requires retrieving and integrating multiple pieces of evidence distributed across documents. Recent graph-based methods improve multi-hop reasoning through graph traversal over relational evidence structures. However, existing methods rely on independent path ranking during evidence organization, which often produces redundant and reasoning-incomplete evidence sets due to substantial structural overlap among selected graph paths. In this work, we argue that graph-based evidence organization may, to some extent, be formulated as a constrained evidence subgraph optimization problem. Based on this perspective, we propose CROG, a coverage-aware reasoning optimization framework that performs marginal-gain-based path selection to favor previously uncovered reasoning steps while suppressing redundant evidence, with node-budget and connectivity constraints to encourage compact and coherent evidence subgraphs. Experiments on multiple benchmarks demonstrate that CROG achieves superior reasoning performance while using fewer evidence units on average, and analysis based on exhaustive optimal search further validates the effectiveness of the greedy optimization strategy.
%U https://aclanthology.org/2026.emnlp-main.1164/
%P 26632-26645
Markdown (Informal)
[CROG: Coverage-aware Reasoning Optimization on Graphs for Multi-hop Question Answering](https://aclanthology.org/2026.emnlp-main.1164/) (Liang et al., EMNLP 2026)
ACL