{"id":"https://openalex.org/W7124205336","doi":"https://doi.org/10.1109/icpads67057.2025.11323162","title":"MMM-RAG: A Multi-Agent Multi-Feature Method for Multimodal Retrieval-Augmented Generation","display_name":"MMM-RAG: A Multi-Agent Multi-Feature Method for Multimodal Retrieval-Augmented Generation","publication_year":2025,"publication_date":"2025-12-14","ids":{"openalex":"https://openalex.org/W7124205336","doi":"https://doi.org/10.1109/icpads67057.2025.11323162"},"language":null,"primary_location":{"id":"doi:10.1109/icpads67057.2025.11323162","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpads67057.2025.11323162","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 31th International Conference on Parallel and Distributed Systems (ICPADS)","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/A5068331234","display_name":"Tianyou Chang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210153230","display_name":"Shanghai Academy of Spaceflight Technology","ror":"https://ror.org/050qhwt21","country_code":"CN","type":"government","lineage":["https://openalex.org/I2802615301","https://openalex.org/I4210153230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianyou Chang","raw_affiliation_strings":["Shanghai Spacelight Precision Machinery Institute,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Spacelight Precision Machinery Institute,Shanghai,China","institution_ids":["https://openalex.org/I4210153230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033729984","display_name":"Yujie Fang","orcid":"https://orcid.org/0009-0003-9126-9733"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yujie Fang","raw_affiliation_strings":["College of Intelligence and Computing, Tianjin University,Tianjin,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University,Tianjin,China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5123051142","display_name":"Yupeng Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yupeng Zhang","raw_affiliation_strings":["College of Intelligence and Computing, Tianjin University,Tianjin,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University,Tianjin,China","institution_ids":["https://openalex.org/I162868743"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9919999837875366,"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":0.9919999837875366,"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":0.002099999925121665,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.0007999999797903001,"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/feature","display_name":"Feature (linguistics)","score":0.5374000072479248},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.4966999888420105},{"id":"https://openalex.org/keywords/semantic-feature","display_name":"Semantic feature","score":0.41679999232292175},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4163999855518341},{"id":"https://openalex.org/keywords/knowledge-base","display_name":"Knowledge base","score":0.38089999556541443},{"id":"https://openalex.org/keywords/voting","display_name":"Voting","score":0.37630000710487366},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.33809998631477356},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.32030001282691956},{"id":"https://openalex.org/keywords/conjunction","display_name":"Conjunction (astronomy)","score":0.3197999894618988}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8041999936103821},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5622000098228455},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5374000072479248},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.4966999888420105},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.41679999232292175},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4163999855518341},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.38089999556541443},{"id":"https://openalex.org/C520049643","wikidata":"https://www.wikidata.org/wiki/Q189760","display_name":"Voting","level":3,"score":0.37630000710487366},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3596000075340271},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.33809998631477356},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.32030001282691956},{"id":"https://openalex.org/C59656382","wikidata":"https://www.wikidata.org/wiki/Q191536","display_name":"Conjunction (astronomy)","level":2,"score":0.3197999894618988},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.3179999887943268},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.3156000077724457},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3138999938964844},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.31130000948905945},{"id":"https://openalex.org/C2775955345","wikidata":"https://www.wikidata.org/wiki/Q7449071","display_name":"Semantic mapping","level":2,"score":0.3109000027179718},{"id":"https://openalex.org/C42058472","wikidata":"https://www.wikidata.org/wiki/Q810214","display_name":"Base (topology)","level":2,"score":0.2913999855518341},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.28630000352859497},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.27390000224113464},{"id":"https://openalex.org/C199579030","wikidata":"https://www.wikidata.org/wiki/Q2851778","display_name":"Automatic image annotation","level":4,"score":0.26820001006126404},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.26660001277923584},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2660999894142151},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2639000117778778},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.26010000705718994},{"id":"https://openalex.org/C90312973","wikidata":"https://www.wikidata.org/wiki/Q7449052","display_name":"Semantic data model","level":2,"score":0.25999999046325684},{"id":"https://openalex.org/C135641252","wikidata":"https://www.wikidata.org/wiki/Q738567","display_name":"Multimodal interaction","level":2,"score":0.2538999915122986}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icpads67057.2025.11323162","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpads67057.2025.11323162","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 31th International Conference on Parallel and Distributed Systems (ICPADS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.41863900423049927}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W2798683079","https://openalex.org/W4389519118","https://openalex.org/W4391876619","https://openalex.org/W4404954244","https://openalex.org/W4413147124"],"related_works":[],"abstract_inverted_index":{"Retrieval-augmented":[0],"generation":[1,44],"(RAG)":[2],"enhances":[3],"large":[4],"language":[5],"models":[6],"via":[7,129],"external":[8],"knowledge,":[9],"but":[10],"struggles":[11],"with":[12,76],"text-image":[13],"multimodal":[14,18,63,95],"heterogeneous":[15],"data.":[16],"Existing":[17],"RAG":[19,160],"methods":[20],"extract":[21],"only":[22],"single-type":[23],"image":[24,139],"features":[25,93],"(e.g.,":[26],"visual":[27,92],"or":[28,124],"semantic),":[29],"failing":[30],"to":[31,39,116,132],"capture":[32],"both":[33],"structural":[34],"and":[35,42,73,94,141,147,153,176],"semantic":[36,97,142],"information,":[37,143],"leading":[38],"partial":[40],"retrieval":[41,72,145],"degraded":[43],"quality.":[45,149],"This":[46],"paper":[47],"proposes":[48],"MMM-RAG:":[49],"A":[50],"Multi-Agent":[51],"MultiFeature":[52],"Method":[53],"for":[54,62,90,109],"Multimodal":[55],"Retrieval-Augmented":[56],"Generation,":[57],"a":[58,81,100],"multi-agent":[59,74],"collaborative":[60],"framework":[61,136],"question":[64],"answering.":[65],"Its":[66],"core":[67],"innovations":[68],"are":[69],"multi-feature":[70,82],"fusion":[71],"coordination,":[75],"four":[77],"modules:":[78],"1)":[79],"constructing":[80],"knowledge":[83],"base":[84],"(text":[85],"embedded":[86],"directly;":[87],"images":[88],"processed":[89],"ViT-extracted":[91],"model-generated":[96],"descriptions,":[98],"forming":[99],"dual-feature":[101],"database);":[102],"2)":[103],"decomposing":[104],"complex":[105],"queries":[106],"into":[107],"subtasks":[108],"different":[110],"agents;":[111],"3)":[112],"enabling":[113],"each":[114],"agent":[115],"retrieve":[117],"from":[118],"its":[119],"corresponding":[120],"feature":[121],"database":[122],"(visual":[123],"semantic);":[125],"4)":[126],"fusing":[127],"results":[128],"consensus":[130],"voting":[131],"generate":[133],"answers.":[134],"The":[135],"deeply":[137],"integrates":[138],"visual-structural":[140],"improving":[144],"comprehensiveness":[146],"response":[148],"Experiments":[150],"on":[151,174,179],"ScienceQA":[152,175],"CrisisMM-D":[154],"show":[155],"MMM-RAG":[156],"outperforms":[157],"traditional":[158],"unimodal/multimodal":[159],"in":[161,164],"accuracy,":[162],"especially":[163],"cross-modal":[165],"reasoning.":[166],"Specifically,":[167],"it":[168],"surpasses":[169],"GPT-4o":[170],"by":[171],"2.66":[172],"%":[173,178],"6.29":[177],"CrisisMMD,":[180],"confirming":[181],"robustness.":[182]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-01-15T00:00:00"}