{"id":"https://openalex.org/W4417328505","doi":"https://doi.org/10.1145/3774904.3792599","title":"Doc-Researcher: A Unified System for Multimodal Document Parsing and Deep Research","display_name":"Doc-Researcher: A Unified System for Multimodal Document Parsing and Deep Research","publication_year":2026,"publication_date":"2026-04-09","ids":{"openalex":"https://openalex.org/W4417328505","doi":"https://doi.org/10.1145/3774904.3792599"},"language":null,"primary_location":{"id":"doi:10.1145/3774904.3792599","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774904.3792599","pdf_url":null,"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 ACM Web Conference 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3774904.3792599","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5075136607","display_name":"Kuicai Dong","orcid":"https://orcid.org/0000-0002-5564-0641"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kuicai Dong","raw_affiliation_strings":["Huawei Technologies Co., Ltd., Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-5564-0641","affiliations":[{"raw_affiliation_string":"Huawei Technologies Co., Ltd., Shenzhen, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029794321","display_name":"Shurui Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shurui Huang","raw_affiliation_strings":["Huawei Technologies Co., Ltd., Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0004-0680-2845","affiliations":[{"raw_affiliation_string":"Huawei Technologies Co., Ltd., Shenzhen, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111130190","display_name":"Fangda Ye","orcid":null},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fangda Ye","raw_affiliation_strings":["Huawei Technologies Co., Ltd., Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0009-4774-5732","affiliations":[{"raw_affiliation_string":"Huawei Technologies Co., Ltd., Shenzhen, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Wei Han","orcid":"https://orcid.org/0000-0002-0005-4258"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Han","raw_affiliation_strings":["Huawei Technologies Co., Ltd., Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-0005-4258","affiliations":[{"raw_affiliation_string":"Huawei Technologies Co., Ltd., Shenzhen, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhi Zhang","orcid":"https://orcid.org/0009-0004-1290-7010"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhi Zhang","raw_affiliation_strings":["Huawei Technologies Co., Ltd., Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0004-1290-7010","affiliations":[{"raw_affiliation_string":"Huawei Technologies Co., Ltd., Shenzhen, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101368863","display_name":"Dexun Li","orcid":null},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dexun Li","raw_affiliation_strings":["Huawei Technologies Co., Ltd., Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-6579-3764","affiliations":[{"raw_affiliation_string":"Huawei Technologies Co., Ltd., Shenzhen, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Wenjun Li","orcid":"https://orcid.org/0000-0001-5042-7756"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenjun Li","raw_affiliation_strings":["Huawei Technologies Co., Ltd., Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0001-5042-7756","affiliations":[{"raw_affiliation_string":"Huawei Technologies Co., Ltd., Shenzhen, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Qu Yang","orcid":"https://orcid.org/0000-0002-3714-1814"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qu Yang","raw_affiliation_strings":["Huawei Technologies Co., Ltd., Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-3714-1814","affiliations":[{"raw_affiliation_string":"Huawei Technologies Co., Ltd., Shenzhen, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Gang Wang","orcid":"https://orcid.org/0000-0002-8795-8953"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gang Wang","raw_affiliation_strings":["Huawei Technologies Co., Ltd., Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-8795-8953","affiliations":[{"raw_affiliation_string":"Huawei Technologies Co., Ltd., Shenzhen, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061500617","display_name":"Yichao Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yichao Wang","raw_affiliation_strings":["Huawei Technologies Co., Ltd., Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0001-7053-8269","affiliations":[{"raw_affiliation_string":"Huawei Technologies Co., Ltd., Shenzhen, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Chen Zhang","orcid":"https://orcid.org/0000-0002-2406-8734"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen Zhang","raw_affiliation_strings":["Huawei Technologies Co., Ltd., Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-2406-8734","affiliations":[{"raw_affiliation_string":"Huawei Technologies Co., Ltd., Shenzhen, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"last","author":{"id":null,"display_name":"Yong Liu","orcid":"https://orcid.org/0000-0001-9031-9696"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yong Liu","raw_affiliation_strings":["Huawei Technologies Co., Ltd., Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0001-9031-9696","affiliations":[{"raw_affiliation_string":"Huawei Technologies Co., Ltd., Shenzhen, China","institution_ids":["https://openalex.org/I2250955327"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I2250955327"],"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":"2349","last_page":"2360"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.5534999966621399,"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":0.5534999966621399,"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":0.13930000364780426,"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":0.09179999679327011,"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/parsing","display_name":"Parsing","score":0.6004999876022339},{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.5038999915122986},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.49790000915527344},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4957999885082245},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.39800000190734863},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.3643999993801117},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.33219999074935913}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8300999999046326},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.6004999876022339},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5835999846458435},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.5038999915122986},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.49790000915527344},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4957999885082245},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.39800000190734863},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3783999979496002},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.3643999993801117},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3425000011920929},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.33219999074935913},{"id":"https://openalex.org/C143587482","wikidata":"https://www.wikidata.org/wiki/Q1543216","display_name":"Iterative and incremental development","level":2,"score":0.3206000030040741},{"id":"https://openalex.org/C203357204","wikidata":"https://www.wikidata.org/wiki/Q1089605","display_name":"Chunking (psychology)","level":2,"score":0.3140999972820282},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.28850001096725464},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.2741999924182892},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.272599995136261},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2632000148296356},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.250900000333786},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.2500999867916107}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3774904.3792599","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774904.3792599","pdf_url":null,"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 ACM Web Conference 2026","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2510.21603","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.21603","pdf_url":"https://arxiv.org/pdf/2510.21603","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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.2510.21603","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2510.21603","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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:10.1145/3774904.3792599","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774904.3792599","pdf_url":null,"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 ACM Web Conference 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Deep":[0],"Research":[1],"systems":[2,18],"have":[3],"revolutionized":[4],"how":[5],"LLMs":[6],"solve":[7],"complex":[8,136],"questions":[9,170],"through":[10,91],"iterative":[11,131,218],"reasoning":[12],"and":[13,38,49,67,103,122,129,141,147,163,216],"evidence":[14,173],"gathering.":[15],"However,":[16],"current":[17],"remain":[19],"fundamentally":[20,209],"constrained":[21],"to":[22,57,63,112],"textual":[23],"web":[24],"data,":[25],"overlooking":[26],"the":[27,156],"vast":[28],"knowledge":[29],"embedded":[30],"in":[31,45,76],"multimodal":[32,97,214,231],"documents:":[33],"scientific":[34],"papers,":[35],"technical":[36],"reports,":[37],"financial":[39],"documents":[40,53,146],"where":[41],"critical":[42],"information":[43],"exists":[44],"figures,":[46],"tables,":[47],"charts,":[48],"equations.":[50],"Processing":[51],"such":[52],"demands":[54],"sophisticated":[55],"parsing":[56,98,211],"preserve":[58,213],"visual":[59,104],"semantics,":[60],"intelligent":[61],"chunking":[62],"maintain":[64],"structural":[65],"coherence,":[66],"adaptive":[68],"retrieval":[69,117],"across":[70,145,175],"modalities,":[71],"which":[72],"are":[73],"capabilities":[74,180],"absent":[75],"existing":[77,182],"systems.":[78],"In":[79],"response,":[80],"we":[81,153],"present":[82],"Doc-Researcher,":[83],"a":[84,223],"unified":[85],"system":[86],"that":[87,99,134,181,188,199,212],"bridges":[88],"this":[89],"gap":[90],"three":[92],"integrated":[93],"components:":[94],"(i)":[95],"deep":[96,165,210,228],"preserves":[100],"layout":[101],"structure":[102],"semantics":[105],"while":[106],"creating":[107],"multi-granular":[108],"representations":[109],"from":[110],"chunk":[111],"document":[113,201,232],"level,":[114],"(ii)":[115],"systematic":[116],"architecture":[118],"supporting":[119],"text-only,":[120],"vision-only,":[121],"hybrid":[123],"paradigms":[124],"with":[125,171],"dynamic":[126],"granularity":[127],"selection,":[128],"(iii)":[130],"multi-agent":[132],"workflows":[133],"decompose":[135],"queries,":[137],"progressively":[138],"accumulate":[139],"evidence,":[140],"synthesize":[142],"comprehensive":[143],"answers":[144],"modalities.":[148],"To":[149],"enable":[150],"rigorous":[151],"evaluation,":[152],"introduce":[154],"M4DocBench,":[155],"first":[157],"benchmark":[158],"for":[159,226],"Multi-modal,":[160],"Multi-hop,":[161],"Multi-document,":[162],"Multi-turn":[164],"research.":[166,219],"Featuring":[167],"158":[168],"expert-annotated":[169],"complete":[172],"chains":[174],"304":[176],"documents,":[177],"M4DocBench":[178],"tests":[179],"benchmarks":[183],"cannot":[184],"assess.":[185],"Experiments":[186],"demonstrate":[187],"Doc-Researcher":[189],"achieves":[190],"50.6%":[191],"accuracy,":[192],"3.4\u00d7":[193],"better":[194,206],"than":[195],"state-of-the-art":[196],"baselines,":[197],"validating":[198],"effective":[200],"research":[202,229],"requires":[203],"not":[204],"just":[205],"retrieval,":[207],"but":[208],"integrity":[215],"support":[217],"Our":[220],"work":[221],"establishes":[222],"new":[224],"paradigm":[225],"conducting":[227],"on":[230],"collections.":[233]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-28T00:00:00"}