{"id":"https://openalex.org/W7225269084","doi":"https://doi.org/10.48550/arxiv.2611.04504","title":"AttriSwarm: Orchestrating Agent Swarms for Cross-Page Visual Attribution","display_name":"AttriSwarm: Orchestrating Agent Swarms for Cross-Page Visual Attribution","publication_year":2026,"publication_date":"2026-11-03","ids":{"openalex":"https://openalex.org/W7225269084","doi":"https://doi.org/10.48550/arxiv.2611.04504"},"language":"en","primary_location":{"id":"doi:10.48550/arxiv.2611.04504","doi":"https://doi.org/10.48550/arxiv.2611.04504","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2611.04504","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"},"volume":null,"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2611.04504","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5111321040","display_name":"Suifeng Zhao","orcid":"https://orcid.org/0009-0004-9859-5782","observed_orcids":["https://orcid.org/0009-0004-9859-5782"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Suifeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038768852","display_name":"Zida Liu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Zida","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160728276","display_name":"Lei Sun","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sun, Lei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160718232","display_name":"Xun Wang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Xun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039880027","display_name":"Daojian Zeng","orcid":"https://orcid.org/0000-0002-3552-0685","observed_orcids":["https://orcid.org/0000-0002-3552-0685"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zeng, Daojian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160577052","display_name":"Jun Gao","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gao, Jun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5160584772","display_name":"Sujian Li","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Sujian","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":null,"has_fulltext":false,"cited_by_count":0,"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":0.9502000212669373,"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":0.9502000212669373,"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":0.027899999171495438,"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":0.005400000140070915,"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/agent-swarms","display_name":"agent swarms","score":0.7929999828338623},{"id":"https://openalex.org/keywords/multimodal-large-language-models","display_name":"multimodal large language models","score":0.972000002861023},{"id":"https://openalex.org/keywords/role-specific-training","display_name":"role-specific training","score":0.6169999837875366},{"id":"https://openalex.org/keywords/answer-verification","display_name":"answer verification","score":0.34299999475479126}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7853000164031982},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.6452999711036682},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6047000288963318},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5231999754905701},{"id":"https://openalex.org/C143299363","wikidata":"https://www.wikidata.org/wiki/Q900584","display_name":"Attribution","level":2,"score":0.5164999961853027},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49050000309944153},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.43059998750686646},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.3671000003814697},{"id":"https://openalex.org/C2775941552","wikidata":"https://www.wikidata.org/wiki/Q25212305","display_name":"Isolation (microbiology)","level":2,"score":0.3490000069141388},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34630000591278076},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3301999866962433},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.30809998512268066},{"id":"https://openalex.org/C115086926","wikidata":"https://www.wikidata.org/wiki/Q17004651","display_name":"Causal reasoning","level":3,"score":0.3005000054836273},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.27709999680519104},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2743000090122223},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.2687999904155731},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.26589998602867126},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.25529998540878296}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2611.04504","doi":"https://doi.org/10.48550/arxiv.2611.04504","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2611.04504","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":"doi:10.48550/arxiv.2611.04504","doi":"https://doi.org/10.48550/arxiv.2611.04504","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2611.04504","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"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7137959380","https://openalex.org/W7166855710","https://openalex.org/W4415537808","https://openalex.org/W7220726873","https://openalex.org/W7171640131","https://openalex.org/W4416365890","https://openalex.org/W7167262568","https://openalex.org/W4404351229","https://openalex.org/W7222654175","https://openalex.org/W7137883625"],"abstract_inverted_index":{"Multimodal":[0],"large":[1],"language":[2],"models":[3],"(MLLMs)":[4],"increasingly":[5],"address":[6],"knowledge-intensive":[7],"tasks":[8],"by":[9,167],"integrating":[10],"evidence":[11,38,61,82,145],"scattered":[12],"across":[13,178],"multiple":[14,76],"document":[15],"pages":[16,57,77,141],"into":[17],"a":[18,84,111,135],"final":[19],"answer.":[20],"Because":[21],"such":[22],"answers":[23],"are":[24],"synthesized":[25],"from":[26],"many":[27],"pages,":[28],"the":[29,32,55],"link":[30],"between":[31],"answer":[33,156],"and":[34,44,58,70,124,130,147,160,173,182],"its":[35,164],"supporting":[36,56,140],"visual":[37,47],"can":[39],"become":[40],"obscured,":[41],"hindering":[42],"verification":[43],"trust.":[45],"Cross-page":[46],"attribution":[48,121],"is":[49],"therefore":[50],"essential:":[51],"it":[52,149],"requires":[53],"identifying":[54],"localizing":[59],"fine-grained":[60],"regions":[62],"within":[63,83],"them,":[64],"thereby":[65],"making":[66],"multi-page":[67],"reasoning":[68],"transparent":[69],"auditable.":[71],"Existing":[72],"approaches":[73],"either":[74],"process":[75],"jointly":[78],"or":[79],"iteratively":[80],"refine":[81],"single":[85],"trajectory,":[86],"risking":[87],"cross-page":[88,115,136],"context":[89],"pollution":[90],"and,":[91],"for":[92,150],"interactive":[93],"methods,":[94],"substantial":[95],"sequential":[96],"overhead.":[97],"We":[98],"introduce":[99],"\\textbf{AttriSwarm},":[100],"an":[101,168],"agent-swarm":[102],"framework":[103],"that":[104],"assigns":[105],"these":[106],"concerns":[107],"to":[108,142],"separate":[109],"roles:":[110],"leader":[112],"handles":[113],"global":[114],"reasoning,":[116],"while":[117],"subagents":[118],"perform":[119],"page-wise":[120],"in":[122,125],"isolation":[123],"parallel.":[126],"To":[127],"support":[128],"training":[129,152],"evaluation,":[131],"we":[132],"construct":[133],"\\textbf{AttriDoc},":[134],"QA":[137],"dataset":[138],"linking":[139],"their":[143],"annotated":[144],"regions,":[146],"use":[148],"role-specific":[151],"of":[153,170],"AttriSwarm,":[154],"improving":[155],"accuracy,":[157],"page-level":[158],"$F_1$,":[159],"region-level":[161],"IoU":[162],"over":[163],"training-free":[165],"counterpart":[166],"average":[169],"18.94,":[171],"29.34,":[172],"23.04":[174],"percentage":[175],"points,":[176],"respectively,":[177],"three":[179,183],"open-source":[180],"backbones":[181],"datasets.":[184]},"counts_by_year":[],"updated_date":"2026-11-06T12:05:46.655746","created_date":"2026-11-05T00:00:00"}