{"id":"https://openalex.org/W4415539809","doi":"https://doi.org/10.1145/3746027.3754761","title":"HM-RAG: Hierarchical Multi-Agent Multimodal Retrieval Augmented Generation","display_name":"HM-RAG: Hierarchical Multi-Agent Multimodal Retrieval Augmented Generation","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415539809","doi":"https://doi.org/10.1145/3746027.3754761"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3754761","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3754761","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5109235219","display_name":"Pei Liu","orcid":"https://orcid.org/0009-0004-6925-1833"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pei Liu","raw_affiliation_strings":["The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"],"raw_orcid":"https://orcid.org/0009-0004-6925-1833","affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xin Liu","orcid":"https://orcid.org/0009-0006-3906-8629"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xin Liu","raw_affiliation_strings":["The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"],"raw_orcid":"https://orcid.org/0009-0006-3906-8629","affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080403866","display_name":"Ruoyu Yao","orcid":"https://orcid.org/0000-0003-1754-1770"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ruoyu Yao","raw_affiliation_strings":["The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-1754-1770","affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108696084","display_name":"J. Liu","orcid":"https://orcid.org/0009-0000-9131-3245"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junming Liu","raw_affiliation_strings":["Tongji University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0000-9131-3245","affiliations":[{"raw_affiliation_string":"Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057123706","display_name":"Siyuan Meng","orcid":"https://orcid.org/0000-0001-5823-7340"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Siyuan Meng","raw_affiliation_strings":["East China Normal University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-5823-7340","affiliations":[{"raw_affiliation_string":"East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101885722","display_name":"Ding Wang","orcid":"https://orcid.org/0000-0002-2398-1409"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]},{"id":"https://openalex.org/I4391012619","display_name":"Shanghai Artificial Intelligence Laboratory","ror":"https://ror.org/03wkvpx79","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4391012619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ding Wang","raw_affiliation_strings":["Shanghai Artificial Intelligence Laboratory, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-2398-1409","affiliations":[{"raw_affiliation_string":"Shanghai Artificial Intelligence Laboratory, Shanghai, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I4391012619"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053340150","display_name":"Jun Ma","orcid":"https://orcid.org/0000-0002-9405-8232"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jun Ma","raw_affiliation_strings":["The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-9405-8232","affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":40.2434,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.99890292,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"2781","last_page":"2790"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9997000098228455,"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"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9997000098228455,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9977999925613403,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9954000115394592,"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/modular-design","display_name":"Modular design","score":0.5759999752044678},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.5568000078201294},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5131999850273132},{"id":"https://openalex.org/keywords/rewriting","display_name":"Rewriting","score":0.46889999508857727},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.45089998841285706},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.4413999915122986},{"id":"https://openalex.org/keywords/voting","display_name":"Voting","score":0.436599999666214},{"id":"https://openalex.org/keywords/query-language","display_name":"Query language","score":0.3391999900341034}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8253999948501587},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.5759999752044678},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5568000078201294},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5131999850273132},{"id":"https://openalex.org/C154690210","wikidata":"https://www.wikidata.org/wiki/Q1668499","display_name":"Rewriting","level":2,"score":0.46889999508857727},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.45089998841285706},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.4413999915122986},{"id":"https://openalex.org/C520049643","wikidata":"https://www.wikidata.org/wiki/Q189760","display_name":"Voting","level":3,"score":0.436599999666214},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43160000443458557},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4011000096797943},{"id":"https://openalex.org/C192028432","wikidata":"https://www.wikidata.org/wiki/Q845739","display_name":"Query language","level":2,"score":0.3391999900341034},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.32850000262260437},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.3142000138759613},{"id":"https://openalex.org/C99016210","wikidata":"https://www.wikidata.org/wiki/Q5488129","display_name":"Query expansion","level":2,"score":0.30809998512268066},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.3075000047683716},{"id":"https://openalex.org/C157170001","wikidata":"https://www.wikidata.org/wiki/Q4781507","display_name":"Applications of artificial intelligence","level":2,"score":0.2777000069618225},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.27630001306533813},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.26649999618530273},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.2644999921321869},{"id":"https://openalex.org/C98025372","wikidata":"https://www.wikidata.org/wiki/Q477538","display_name":"Systems architecture","level":3,"score":0.2621999979019165},{"id":"https://openalex.org/C551230270","wikidata":"https://www.wikidata.org/wiki/Q4368942","display_name":"Data retrieval","level":2,"score":0.2606000006198883},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.26019999384880066},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.26019999384880066},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2597000002861023}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3754761","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3746027.3754761","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2798683079","https://openalex.org/W3021397474","https://openalex.org/W3138516171","https://openalex.org/W4402702988","https://openalex.org/W4403458599","https://openalex.org/W4403899386","https://openalex.org/W4405845669","https://openalex.org/W4409203786"],"related_works":[],"abstract_inverted_index":{"While":[0],"Retrieval-Augmented":[1],"Generation":[2],"(RAG)":[3],"augments":[4],"Large":[5],"Language":[6],"Models":[7],"(LLMs)":[8],"with":[9,61],"external":[10],"knowledge,":[11],"conventional":[12],"single-agent":[13],"RAG":[14,37,156,206],"remains":[15],"fundamentally":[16],"limited":[17],"in":[18,117,138,143,150,169,194,205],"resolving":[19],"complex":[20,69],"queries":[21,70],"demanding":[22],"coordinated":[23],"reasoning":[24,201],"across":[25,47],"heterogeneous":[26],"data":[27,183,188],"ecosystems.":[28],"We":[29],"present":[30],"HM-RAG,":[31],"a":[32,58,64,103,139,147,191],"novel":[33],"Hierarchical":[34],"Multi-agent":[35],"Multimodal":[36],"framework":[38,54],"that":[39,67,86,106],"pioneers":[40],"collaborative":[41],"intelligence":[42],"for":[43,96],"dynamic":[44],"knowledge":[45,203],"synthesis":[46,204],"structured,":[48],"unstructured,":[49],"and":[50,79,99,102,114,134,146,161,202],"graph-based":[51],"data.":[52],"The":[53],"is":[55],"composed":[56],"of":[57,181,199],"three-tiered":[59],"architecture":[60,125,177],"specialized":[62],"agents:":[63],"Decomposition":[65],"Agent":[66,105],"dissects":[68],"into":[71],"contextually":[72],"coherent":[73],"sub-tasks":[74],"via":[75],"semantic-aware":[76],"query":[77,128],"rewriting":[78],"schema-guided":[80],"context":[81],"augmentation;":[82],"Multi-source":[83],"Retrieval":[84],"Agents":[85],"carry":[87],"out":[88],"parallel,":[89],"modality-specific":[90],"retrieval":[91,118],"using":[92],"plug-and-play":[93],"modules":[94],"designed":[95],"vector,":[97],"graph,":[98],"web-based":[100],"databases;":[101],"Decision":[104],"uses":[107],"consistency":[108],"voting":[109],"to":[110],"integrate":[111],"multi-source":[112],"answers":[113],"resolve":[115],"discrepancies":[116],"results":[119,168],"through":[120],"Expert":[121],"Model":[122],"Refinement.":[123],"This":[124],"attains":[126],"comprehensive":[127],"understanding":[129],"by":[130],"combining":[131],"textual,":[132],"graph-relational,":[133],"web-derived":[135],"evidence,":[136],"resulting":[137],"remarkable":[140],"12.95%":[141],"improvement":[142],"answer":[144],"accuracy":[145,153],"3.56%":[148],"boost":[149],"question":[151],"classification":[152],"over":[154],"baseline":[155],"systems":[157],"on":[158,172],"the":[159,196],"ScienceQA":[160],"CrisisMMD":[162],"benchmarks.":[163],"Notably,":[164],"HM-RAG":[165],"establishes":[166],"state-of-the-art":[167],"zero-shot":[170],"settings":[171],"both":[173],"datasets.":[174],"Its":[175],"modular":[176],"ensures":[178],"seamless":[179],"integration":[180],"new":[182],"modalities":[184],"while":[185],"maintaining":[186],"strict":[187],"governance,":[189],"marking":[190],"significant":[192],"advancement":[193],"addressing":[195],"critical":[197],"challenges":[198],"multimodal":[200],"systems.":[207]},"counts_by_year":[{"year":2026,"cited_by_count":18},{"year":2025,"cited_by_count":6}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-25T00:00:00"}
