{"id":"https://openalex.org/W7166875416","doi":"https://doi.org/10.18653/v1/2026.findings-acl.2066","title":"See or Say Graphs: Agent-Driven Scalable Graph Understanding with Vision-Language Models","display_name":"See or Say Graphs: Agent-Driven Scalable Graph Understanding with Vision-Language Models","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166875416","doi":"https://doi.org/10.18653/v1/2026.findings-acl.2066"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.2066","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.2066","pdf_url":"https://aclanthology.org/2026.findings-acl.2066.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.findings-acl.2066.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139826900","display_name":"Shuo Han","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shuo Han","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139726095","display_name":"Yukun Cao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yukun Cao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139836422","display_name":"Zezhong Ding","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zezhong Ding","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139737017","display_name":"Zengyi Gao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zengyi Gao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139839077","display_name":"S Kevin Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"S Kevin Zhou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5037366245","display_name":"Xike Xie","orcid":"https://orcid.org/0000-0001-5290-5408"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xike Xie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.88162086,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"41565","last_page":"41589"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8712999820709229,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8712999820709229,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.029200000688433647,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12292","display_name":"Graph Theory and Algorithms","score":0.0203000009059906,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.46239998936653137},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.4065999984741211},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.25440001487731934},{"id":"https://openalex.org/keywords/graph-theory","display_name":"Graph theory","score":0.25429999828338623}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6480000019073486},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.46239998936653137},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4519999921321869},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.4065999984741211},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3255999982357025},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.25440001487731934},{"id":"https://openalex.org/C88230418","wikidata":"https://www.wikidata.org/wiki/Q131476","display_name":"Graph theory","level":2,"score":0.25429999828338623},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2500999867916107},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.24819999933242798},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.24250000715255737}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.2066","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.2066","pdf_url":"https://aclanthology.org/2026.findings-acl.2066.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-acl.2066","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.2066","pdf_url":"https://aclanthology.org/2026.findings-acl.2066.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3350212987","display_name":null,"funder_award_id":"62472400","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G378631614","display_name":null,"funder_award_id":"SYG202338","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5837042690","display_name":null,"funder_award_id":"2025YFC3408300","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7571408944","display_name":null,"funder_award_id":"62271465","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166875416.pdf","grobid_xml":"https://content.openalex.org/works/W7166875416.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Vision-language":[0],"models":[1],"(VLMs)":[2],"have":[3],"shown":[4],"promise":[5],"in":[6,45,115,133],"graph":[7,46,52,103,111],"structure":[8,47,112],"understanding,":[9],"but":[10],"remain":[11],"limited":[12],"by":[13,155],"input-token":[14],"constraints,":[15],"facing":[16],"scalability":[17,41],"bottlenecks":[18],"and":[19,26,42,66,87,105,136,142],"lacking":[20],"effective":[21],"mechanisms":[22],"to":[23,90,101,123,127,147],"coordinate":[24],"textual":[25,64],"visual":[27,68,107],"modalities.To":[28],"address":[29],"these":[30],"challenges,":[31],"we":[32],"propose":[33],"GraphVista,":[34],"a":[35,56,82],"unified":[36],"framework":[37],"that":[38,85,120],"enhances":[39],"both":[40,162],"modality":[43,78,97,108],"coordination":[44],"understanding.For":[48],"scalability,":[49],"GraphVista":[50,80,121],"organizes":[51],"information":[53],"hierarchically":[54],"into":[55],"lightweight":[57],"GraphRAG":[58],"base,":[59],"which":[60],"retrieves":[61],"only":[62],"task-relevant":[63],"descriptions":[65],"high-resolution":[67],"subgraphs,":[69],"compressing":[70],"redundant":[71],"context":[72],"while":[73],"preserving":[74],"key":[75],"reasoning":[76,113],"elements.For":[77],"coordination,":[79],"introduces":[81],"planning":[83],"agent":[84],"decomposes":[86],"routes":[88],"tasks":[89],"the":[91,95,106,152,158],"most":[92],"suitable":[93],"modality-using":[94],"text":[96],"for":[98,109],"direct":[99],"access":[100],"explicit":[102,116],"properties":[104],"local":[110],"grounded":[114],"topology.Extensive":[117],"experiments":[118],"demonstrate":[119],"scales":[122],"large":[124],"graphs,":[125],"up":[126,146],"200\u00d7":[128],"larger":[129],"than":[130],"those":[131],"used":[132],"existing":[134,139],"benchmarks,":[135],"consistently":[137],"outperforms":[138],"textual,":[140],"visual,":[141],"fusion-based":[143],"methods,":[144],"achieving":[145],"4.4\u00d7":[148],"quality":[149],"improvement":[150],"over":[151],"state-of-the-art":[153],"baselines":[154],"fully":[156],"exploiting":[157],"complementary":[159],"strengths":[160],"of":[161],"modalities.":[163]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}