{"id":"https://openalex.org/W4416331536","doi":"https://doi.org/10.18653/v1/2026.acl-long.1234","title":"DocLens: A Tool-Augmented Multi-Agent Framework for Long Visual Document Understanding","display_name":"DocLens: A Tool-Augmented Multi-Agent Framework for Long Visual Document Understanding","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W4416331536","doi":"https://doi.org/10.18653/v1/2026.acl-long.1234"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.acl-long.1234","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1234","pdf_url":"https://aclanthology.org/2026.acl-long.1234.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":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.acl-long.1234.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103158330","display_name":"Dawei Zhu","orcid":"https://orcid.org/0000-0003-1534-8854"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dawei Zhu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017371410","display_name":"Rui Meng","orcid":"https://orcid.org/0000-0001-5902-1787"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rui Meng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031965638","display_name":"J.-C. CHEN","orcid":"https://orcid.org/0009-0005-7454-5999"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiefeng Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058353424","display_name":"Sujian Li","orcid":"https://orcid.org/0000-0001-7493-0786"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sujian Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101265241","display_name":"Tomas Pfister","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tomas Pfister","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5002289527","display_name":"Jinsung Yoon","orcid":"https://orcid.org/0000-0002-5481-5171"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jinsung Yoon","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":0.02011258,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"26804","last_page":"26829"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9650999903678894,"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":0.9650999903678894,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.010400000028312206,"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":0.007899999618530273,"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/task","display_name":"Task (project management)","score":0.5609999895095825},{"id":"https://openalex.org/keywords/mechanism","display_name":"Mechanism (biology)","score":0.47189998626708984},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.35899999737739563},{"id":"https://openalex.org/keywords/power","display_name":"Power (physics)","score":0.336899995803833},{"id":"https://openalex.org/keywords/visual-analytics","display_name":"Visual analytics","score":0.2987000048160553},{"id":"https://openalex.org/keywords/human-visual-system-model","display_name":"Human visual system model","score":0.289900004863739}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7702999711036682},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5609999895095825},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.47189998626708984},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40299999713897705},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.35899999737739563},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3564999997615814},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.35510000586509705},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.336899995803833},{"id":"https://openalex.org/C59732488","wikidata":"https://www.wikidata.org/wiki/Q2528440","display_name":"Visual analytics","level":3,"score":0.2987000048160553},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2971000075340271},{"id":"https://openalex.org/C160086991","wikidata":"https://www.wikidata.org/wiki/Q5939193","display_name":"Human visual system model","level":3,"score":0.289900004863739},{"id":"https://openalex.org/C158495155","wikidata":"https://www.wikidata.org/wiki/Q2369151","display_name":"Visual search","level":2,"score":0.28610000014305115},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2669000029563904},{"id":"https://openalex.org/C185578843","wikidata":"https://www.wikidata.org/wiki/Q10609775","display_name":"Information visualization","level":3,"score":0.2612000107765198},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.25540000200271606}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.1234","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1234","pdf_url":"https://aclanthology.org/2026.acl-long.1234.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":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2511.11552","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2511.11552","pdf_url":"https://arxiv.org/pdf/2511.11552","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,"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.2511.11552","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2511.11552","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,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.acl-long.1234","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1234","pdf_url":"https://aclanthology.org/2026.acl-long.1234.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":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416331536.pdf","grobid_xml":"https://content.openalex.org/works/W4416331536.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Comprehending":[0],"long":[1],"visual":[2,14,45,80],"documents,":[3],"where":[4],"information":[5],"is":[6,16,111],"distributed":[7],"across":[8],"extensive":[9],"pages":[10,39],"of":[11,122],"text":[12],"and":[13,40,51,103,116],"elements,":[15,46],"a":[17,30,59,70,87,92],"critical":[18],"but":[19],"challenging":[20],"task":[21],"for":[22],"modern":[23],"Vision-Language":[24],"Models":[25],"(VLMs).Existing":[26],"approaches":[27],"falter":[28],"on":[29,67,82,101,114],"fundamental":[31],"challenge:":[32],"evidence":[33,68],"localization.They":[34],"struggle":[35],"to":[36,48,78,90],"retrieve":[37],"relevant":[38,83],"overlook":[41],"fine-grained":[42],"details":[43],"within":[44],"leading":[47],"limited":[49],"performance":[50,100],"model":[52],"hallucination.To":[53],"address":[54],"this,":[55],"we":[56],"propose":[57],"DOCLENS,":[58],"toolaugmented":[60],"multi-agent":[61],"framework":[62],"that":[63],"effectively":[64],"\"zooms":[65],"in\"":[66],"like":[69],"lens.It":[71],"first":[72],"navigates":[73],"from":[74],"the":[75,120],"full":[76],"document":[77],"specific":[79],"elements":[81],"pages,":[84],"then":[85],"employs":[86],"sampling-adjudication":[88],"mechanism":[89],"generate":[91],"single,":[93],"reliable":[94],"answer.Paired":[95],"with":[96],"Gemini-2.5-Pro,DOCLENS":[97],"achieves":[98],"stateof-the-art":[99],"MMLongBench-Doc":[102],"FinRAGBench-V,":[104],"surpassing":[105],"even":[106],"human":[107],"experts.The":[108],"framework's":[109],"superiority":[110],"particularly":[112],"evident":[113],"vision-centric":[115],"unanswerable":[117],"queries,":[118],"demonstrating":[119],"power":[121],"its":[123],"enhanced":[124],"localization":[125],"capabilities.":[126]},"counts_by_year":[],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2025-11-18T00:00:00"}