@inproceedings{hu-etal-2026-foresight,
title = "Foresight-on-Graph: Vision-Guided Knowledge Graph Reasoning with Large Language Models",
author = "Hu, Yuwei and
Lei, Runlin and
Wei, Zhewei and
Liu, Yongchao and
Hong, Chuntao and
Zheng, Jiajun and
Zhang, Juelu",
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.2300/",
pages = "52294--52314",
ISBN = "979-8-89176-459-0",
abstract = "Large Language Models (LLMs) demonstrate strong reasoning ability but are constrained by outdated knowledge and hallucinations. Knowledge Graphs (KGs) can help mitigate these limitations by providing structured relational knowledge and capturing global multi-entity, multi-hop dependencies beyond linear text. However, existing KG-enhanced LLM reasoning methods mostly rely on hop-by-hop textual traversal, rather than making multi-hop decisions with a broader perspective as humans do, thus underusing the structural advantages of KGs. This leads to myopic exploration and fragmented reasoning, wasting effort on irrelevant entities while potentially missing critical ones. To address these limitations, we propose Foresight-on-Graph (FoG), a novel framework that introduces visual relation graphs to expand the reasoning horizon at each step. FoG enables Vision-Language Models (VLMs) to simultaneously attend to multi-entity, multi-hop contexts, supporting foresighted planning and more efficient graph exploration. To facilitate effective visual reasoning, we design relation-based fuzzy matching and union-find algorithms to filter out irrelevant relations and coarsen the graph, condensing subgraphs with millions of entities into compact relation graphs with only tens of nodes. Experiments on three real-world datasets demonstrate that FoG consistently outperforms existing methods while significantly improving reasoning efficiency. Code is available at https://github.com/hyworrywart/FoG."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hu-etal-2026-foresight">
<titleInfo>
<title>Foresight-on-Graph: Vision-Guided Knowledge Graph Reasoning with Large Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yuwei</namePart>
<namePart type="family">Hu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Runlin</namePart>
<namePart type="family">Lei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhewei</namePart>
<namePart type="family">Wei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yongchao</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chuntao</namePart>
<namePart type="family">Hong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiajun</namePart>
<namePart type="family">Zheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juelu</namePart>
<namePart type="family">Zhang</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>Large Language Models (LLMs) demonstrate strong reasoning ability but are constrained by outdated knowledge and hallucinations. Knowledge Graphs (KGs) can help mitigate these limitations by providing structured relational knowledge and capturing global multi-entity, multi-hop dependencies beyond linear text. However, existing KG-enhanced LLM reasoning methods mostly rely on hop-by-hop textual traversal, rather than making multi-hop decisions with a broader perspective as humans do, thus underusing the structural advantages of KGs. This leads to myopic exploration and fragmented reasoning, wasting effort on irrelevant entities while potentially missing critical ones. To address these limitations, we propose Foresight-on-Graph (FoG), a novel framework that introduces visual relation graphs to expand the reasoning horizon at each step. FoG enables Vision-Language Models (VLMs) to simultaneously attend to multi-entity, multi-hop contexts, supporting foresighted planning and more efficient graph exploration. To facilitate effective visual reasoning, we design relation-based fuzzy matching and union-find algorithms to filter out irrelevant relations and coarsen the graph, condensing subgraphs with millions of entities into compact relation graphs with only tens of nodes. Experiments on three real-world datasets demonstrate that FoG consistently outperforms existing methods while significantly improving reasoning efficiency. Code is available at https://github.com/hyworrywart/FoG.</abstract>
<identifier type="citekey">hu-etal-2026-foresight</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-main.2300/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>52294</start>
<end>52314</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Foresight-on-Graph: Vision-Guided Knowledge Graph Reasoning with Large Language Models
%A Hu, Yuwei
%A Lei, Runlin
%A Wei, Zhewei
%A Liu, Yongchao
%A Hong, Chuntao
%A Zheng, Jiajun
%A Zhang, Juelu
%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 hu-etal-2026-foresight
%X Large Language Models (LLMs) demonstrate strong reasoning ability but are constrained by outdated knowledge and hallucinations. Knowledge Graphs (KGs) can help mitigate these limitations by providing structured relational knowledge and capturing global multi-entity, multi-hop dependencies beyond linear text. However, existing KG-enhanced LLM reasoning methods mostly rely on hop-by-hop textual traversal, rather than making multi-hop decisions with a broader perspective as humans do, thus underusing the structural advantages of KGs. This leads to myopic exploration and fragmented reasoning, wasting effort on irrelevant entities while potentially missing critical ones. To address these limitations, we propose Foresight-on-Graph (FoG), a novel framework that introduces visual relation graphs to expand the reasoning horizon at each step. FoG enables Vision-Language Models (VLMs) to simultaneously attend to multi-entity, multi-hop contexts, supporting foresighted planning and more efficient graph exploration. To facilitate effective visual reasoning, we design relation-based fuzzy matching and union-find algorithms to filter out irrelevant relations and coarsen the graph, condensing subgraphs with millions of entities into compact relation graphs with only tens of nodes. Experiments on three real-world datasets demonstrate that FoG consistently outperforms existing methods while significantly improving reasoning efficiency. Code is available at https://github.com/hyworrywart/FoG.
%U https://aclanthology.org/2026.emnlp-main.2300/
%P 52294-52314
Markdown (Informal)
[Foresight-on-Graph: Vision-Guided Knowledge Graph Reasoning with Large Language Models](https://aclanthology.org/2026.emnlp-main.2300/) (Hu et al., EMNLP 2026)
ACL