{"id":"https://openalex.org/W7204890885","doi":"https://doi.org/10.48550/arxiv.2608.28701","title":"TopoAgent: A Structure-Aware Perception-to-Reasoning Framework for Diagram-to-Graph Topology Extraction with Large Vision-Language Models","display_name":"TopoAgent: A Structure-Aware Perception-to-Reasoning Framework for Diagram-to-Graph Topology Extraction with Large Vision-Language Models","publication_year":2026,"publication_date":"2026-08-27","ids":{"openalex":"https://openalex.org/W7204890885","doi":"https://doi.org/10.48550/arxiv.2608.28701"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.28701","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.28701","pdf_url":"https://arxiv.org/pdf/2608.28701","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.28701","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5001757884","display_name":"Bangwei Guo","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Guo, Bangwei","raw_affiliation_strings":["Rutgers University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rutgers University","institution_ids":["https://openalex.org/I102322142"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036221931","display_name":"Xujiang Zhao","orcid":"https://orcid.org/0000-0003-4950-4018","observed_orcids":["https://orcid.org/0000-0003-4950-4018"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Xujiang","raw_affiliation_strings":["Meta"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5143275780","display_name":"Yanchi Liu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210107353","display_name":"NEC (United States)","ror":"https://ror.org/01v791m31","country_code":"US","type":"company","lineage":["https://openalex.org/I118347220","https://openalex.org/I4210107353"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Liu, Yanchi","raw_affiliation_strings":["NEC Labs America"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NEC Labs America","institution_ids":["https://openalex.org/I4210107353"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5144174005","display_name":"Wei Cheng","orcid":"https://orcid.org/0009-0007-9418-5753","observed_orcids":["https://orcid.org/0009-0007-9418-5753","https://orcid.org/0000-0001-9433-7576"]},"institutions":[{"id":"https://openalex.org/I4210107353","display_name":"NEC (United States)","ror":"https://ror.org/01v791m31","country_code":"US","type":"company","lineage":["https://openalex.org/I118347220","https://openalex.org/I4210107353"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cheng, Wei","raw_affiliation_strings":["NEC Labs America"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NEC Labs America","institution_ids":["https://openalex.org/I4210107353"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103181412","display_name":"Shengyu Chen","orcid":"https://orcid.org/0009-0006-9576-9841","observed_orcids":["https://orcid.org/0009-0006-9576-9841"]},"institutions":[{"id":"https://openalex.org/I4210107353","display_name":"NEC (United States)","ror":"https://ror.org/01v791m31","country_code":"US","type":"company","lineage":["https://openalex.org/I118347220","https://openalex.org/I4210107353"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chen, Shengyu","raw_affiliation_strings":["NEC Labs America"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NEC Labs America","institution_ids":["https://openalex.org/I4210107353"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148910661","display_name":"Dongyue Li","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I20529979","display_name":"University of Electro-Communications","ror":"https://ror.org/02x73b849","country_code":"JP","type":"education","lineage":["https://openalex.org/I20529979"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Li, Dongyue","raw_affiliation_strings":["University of Electro-Communications"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electro-Communications","institution_ids":["https://openalex.org/I20529979"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5159931271","display_name":"Masaharu Morimoto","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I118347220","display_name":"NEC (Japan)","ror":"https://ror.org/04jndar25","country_code":"JP","type":"company","lineage":["https://openalex.org/I118347220"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Morimoto, Masaharu","raw_affiliation_strings":["NEC Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NEC Corporation","institution_ids":["https://openalex.org/I118347220"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5159939399","display_name":"Takayuki Kuroda","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I118347220","display_name":"NEC (Japan)","ror":"https://ror.org/04jndar25","country_code":"JP","type":"company","lineage":["https://openalex.org/I118347220"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kuroda, Takayuki","raw_affiliation_strings":["NEC Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NEC Corporation","institution_ids":["https://openalex.org/I118347220"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125538262","display_name":"Dimitris Metaxas","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I102322142","display_name":"Rutgers, The State University of New Jersey","ror":"https://ror.org/05vt9qd57","country_code":"US","type":"education","lineage":["https://openalex.org/I102322142"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Metaxas, Dimitris","raw_affiliation_strings":["Rutgers University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rutgers University","institution_ids":["https://openalex.org/I102322142"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5148847216","display_name":"Haifeng Chen","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210107353","display_name":"NEC (United States)","ror":"https://ror.org/01v791m31","country_code":"US","type":"company","lineage":["https://openalex.org/I118347220","https://openalex.org/I4210107353"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chen, Haifeng","raw_affiliation_strings":["NEC Labs America"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NEC Labs America","institution_ids":["https://openalex.org/I4210107353"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9984999895095825,"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":0.9984999895095825,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.00039999998989515007,"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/T10028","display_name":"Topic Modeling","score":0.00019999999494757503,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/structural-diagrams","display_name":"structural diagrams","score":0.7609999775886536},{"id":"https://openalex.org/keywords/large-vision-language-models","display_name":"large vision-language models","score":0.8550000190734863},{"id":"https://openalex.org/keywords/graph-extraction","display_name":"graph extraction","score":0.41600000858306885},{"id":"https://openalex.org/keywords/benchmark","display_name":"benchmark","score":0.7360000014305115},{"id":"https://openalex.org/keywords/edge-detection","display_name":"edge detection","score":0.6349999904632568},{"id":"https://openalex.org/keywords/topological-consistency","display_name":"topological consistency","score":0.8339999914169312},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"visual reasoning","score":0.5839999914169312}],"concepts":[{"id":"https://openalex.org/C184720557","wikidata":"https://www.wikidata.org/wiki/Q7825049","display_name":"Topology (electrical circuits)","level":2,"score":0.6861000061035156},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6614999771118164},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6506999731063843},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.6046000123023987},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5389999747276306},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.4699000120162964},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4609000086784363},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4027999937534332},{"id":"https://openalex.org/C181576044","wikidata":"https://www.wikidata.org/wiki/Q4129926","display_name":"Computational topology","level":3,"score":0.37139999866485596},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.3652999997138977},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3492000102996826},{"id":"https://openalex.org/C88230418","wikidata":"https://www.wikidata.org/wiki/Q131476","display_name":"Graph theory","level":2,"score":0.3425000011920929},{"id":"https://openalex.org/C199845137","wikidata":"https://www.wikidata.org/wiki/Q145490","display_name":"Network topology","level":2,"score":0.3228999972343445},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30550000071525574},{"id":"https://openalex.org/C106937863","wikidata":"https://www.wikidata.org/wiki/Q7236518","display_name":"Power graph analysis","level":3,"score":0.29820001125335693},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.28859999775886536},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.2802000045776367},{"id":"https://openalex.org/C2776477805","wikidata":"https://www.wikidata.org/wiki/Q4460773","display_name":"Topological data analysis","level":2,"score":0.27810001373291016},{"id":"https://openalex.org/C70940072","wikidata":"https://www.wikidata.org/wiki/Q2739990","display_name":"Subbase","level":5,"score":0.26930001378059387},{"id":"https://openalex.org/C143913944","wikidata":"https://www.wikidata.org/wiki/Q5421952","display_name":"Extension topology","level":4,"score":0.25949999690055847},{"id":"https://openalex.org/C93361087","wikidata":"https://www.wikidata.org/wiki/Q4426698","display_name":"Data consistency","level":2,"score":0.2556999921798706}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.28701","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.28701","pdf_url":"https://arxiv.org/pdf/2608.28701","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2608.28701","doi":"https://doi.org/10.48550/arxiv.2608.28701","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.28701","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2608.28701","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.28701","pdf_url":"https://arxiv.org/pdf/2608.28701","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204890885.pdf","grobid_xml":"https://content.openalex.org/works/W7204890885.grobid-xml"},"referenced_works_count":20,"referenced_works":["https://openalex.org/W2951298542","https://openalex.org/W4393055591","https://openalex.org/W4403853618","https://openalex.org/W4404330874","https://openalex.org/W4404782963","https://openalex.org/W4406879573","https://openalex.org/W4414281281","https://openalex.org/W4414458387","https://openalex.org/W4414565054","https://openalex.org/W4414580753","https://openalex.org/W4415854763","https://openalex.org/W4416053382","https://openalex.org/W4416060568","https://openalex.org/W4416623251","https://openalex.org/W4417095648","https://openalex.org/W4417298375","https://openalex.org/W4417298859","https://openalex.org/W4417517088","https://openalex.org/W6891962350","https://openalex.org/W6929541986"],"related_works":["https://openalex.org/W7220675544","https://openalex.org/W7204453147","https://openalex.org/W7215106728","https://openalex.org/W7202362140","https://openalex.org/W7160102556","https://openalex.org/W7204461501","https://openalex.org/W7160251639","https://openalex.org/W7151504492","https://openalex.org/W7133553788","https://openalex.org/W3134048936"],"abstract_inverted_index":{"Diagram-to-graph":[0],"topology":[1,46,56,142],"extraction":[2,57],"aims":[3],"to":[4],"extract":[5],"a":[6,14,41,50,136],"graph":[7,75,82],"of":[8],"entities":[9],"and":[10,32,48,69,98,113,138,146],"their":[11],"connections":[12],"from":[13],"structural":[15,65,88],"diagram.":[16],"This":[17],"task":[18],"remains":[19],"challenging":[20],"for":[21,44,54,140],"current":[22],"vision-language":[23,60,110],"models":[24],"because":[25],"it":[26],"requires":[27],"both":[28],"fine-grained":[29],"perceptual":[30],"grounding":[31],"topology-aware":[33],"reasoning":[34,116],"with":[35,73],"global":[36,87],"consistency.":[37],"We":[38],"present":[39],"TopoBench-180,":[40],"human-verified":[42],"benchmark":[43,137,145],"diagram-to-graph":[45,141],"extraction,":[47],"TopoAgent,":[49],"structure-aware":[51],"perception-to-reasoning":[52],"framework":[53,139],"reliable":[55],"using":[58],"large":[59],"models.":[61],"TopoBench-180":[62,104],"contains":[63],"180":[64],"diagrams":[66],"spanning":[67],"Web-style":[68],"Network-style":[70],"categories,":[71],"paired":[72],"canonical":[74,90],"annotations.":[76],"TopoAgent":[77,107],"progressively":[78],"extracts":[79],"the":[80],"target":[81],"by":[83,134],"combining":[84],"grounded":[85],"perception,":[86],"priors,":[89],"node":[91],"inventory":[92],"construction,":[93],"node-centric":[94],"local-to-global":[95],"relation":[96],"reasoning,":[97],"topological":[99],"consistency":[100],"enforcement.":[101],"Experiments":[102],"on":[103,119],"show":[105],"that":[106],"outperforms":[108],"strong":[109],"model":[111],"baselines":[112],"recent":[114],"visual":[115],"frameworks,":[117],"especially":[118],"edge":[120],"extraction.":[121,143],"More":[122],"broadly,":[123],"this":[124],"work":[125],"fills":[126],"an":[127],"important":[128],"gap":[129],"in":[130],"multimodal":[131],"structured":[132],"understanding":[133],"establishing":[135],"The":[144],"associated":[147],"resources":[148],"will":[149],"be":[150],"publicly":[151],"released":[152],"at":[153],"https://huggingface.co/datasets/WayneGuo0011/TopoBench-180.":[154]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-09-02T00:00:00"}
