{"id":"https://openalex.org/W7130375693","doi":"https://doi.org/10.48448/2psx-5r82","title":"Rethinking Information Synthesis in Multimodal Question Answering A Multi-Agent Perspective","display_name":"Rethinking Information Synthesis in Multimodal Question Answering A Multi-Agent Perspective","publication_year":2025,"publication_date":"2025-12-01","ids":{"openalex":"https://openalex.org/W7130375693","doi":"https://doi.org/10.48448/2psx-5r82"},"language":"en","primary_location":{"id":"doi:10.48448/2psx-5r82","doi":"https://doi.org/10.48448/2psx-5r82","is_oa":true,"landing_page_url":"https://doi.org/10.48448/2psx-5r82","pdf_url":null,"source":{"id":"https://openalex.org/S7407053148","display_name":"Underline Science Inc.","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Audiovisual"},"volume":null,"type":"other","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48448/2psx-5r82","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5126280765","display_name":"Association for Computational Linguistics 2025","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Association for Computational Linguistics 2025","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126311396","display_name":"Tejas Anvekar","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Anvekar, Tejas","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126310603","display_name":"Chitta Baral","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Baral, Chitta","raw_affiliation_strings":["Arizona State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Arizona State University","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140979528","display_name":"Vivek Gupta","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gupta, Vivek","raw_affiliation_strings":["University of Pennsylvania"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Pennsylvania","institution_ids":["https://openalex.org/I79576946"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5119938467","display_name":"Krishna Singh Rajput","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Singh Rajput, Krishna","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"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":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":1.0,"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":1.0,"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":0.0,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.0,"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/multimodal-question-answering","display_name":"multimodal question answering","score":1.0},{"id":"https://openalex.org/keywords/multi-agent-systems","display_name":"multi-agent systems","score":0.9179999828338623},{"id":"https://openalex.org/keywords/information-synthesis","display_name":"information synthesis","score":0.824999988079071},{"id":"https://openalex.org/keywords/cross-modal-reasoning","display_name":"cross-modal reasoning","score":0.8289999961853027},{"id":"https://openalex.org/keywords/vision-language-models","display_name":"vision-language models","score":0.9390000104904175},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.9210000038146973},{"id":"https://openalex.org/keywords/query-decomposition","display_name":"query decomposition","score":0.6079999804496765},{"id":"https://openalex.org/keywords/interpretability","display_name":"interpretability","score":0.6869999766349792}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.8385999798774719},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7985000014305115},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.722000002861023},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.6995999813079834},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.592199981212616},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.5092999935150146},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4959000051021576},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.4819999933242798},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.4546000063419342},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4487000107765198},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.44429999589920044},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.43650001287460327},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3815000057220459},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.3700999915599823},{"id":"https://openalex.org/C2780660688","wikidata":"https://www.wikidata.org/wiki/Q25052564","display_name":"Multimodal learning","level":2,"score":0.33239999413490295},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3294999897480011},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2944999933242798},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.2874000072479248},{"id":"https://openalex.org/C2778023277","wikidata":"https://www.wikidata.org/wiki/Q321703","display_name":"Premise","level":2,"score":0.27559998631477356},{"id":"https://openalex.org/C135641252","wikidata":"https://www.wikidata.org/wiki/Q738567","display_name":"Multimodal interaction","level":2,"score":0.2685000002384186},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.2662999927997589},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.25699999928474426}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48448/2psx-5r82","doi":"https://doi.org/10.48448/2psx-5r82","is_oa":true,"landing_page_url":"https://doi.org/10.48448/2psx-5r82","pdf_url":null,"source":{"id":"https://openalex.org/S7407053148","display_name":"Underline Science Inc.","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Audiovisual"}],"best_oa_location":{"id":"doi:10.48448/2psx-5r82","doi":"https://doi.org/10.48448/2psx-5r82","is_oa":true,"landing_page_url":"https://doi.org/10.48448/2psx-5r82","pdf_url":null,"source":{"id":"https://openalex.org/S7407053148","display_name":"Underline Science Inc.","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Audiovisual"},"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/W4389520499","https://openalex.org/W7117783641","https://openalex.org/W7211989624","https://openalex.org/W7124205336","https://openalex.org/W7203711546","https://openalex.org/W6948057294","https://openalex.org/W4417072983","https://openalex.org/W6947652877","https://openalex.org/W4398150830","https://openalex.org/W4415539809"],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,160],"multimodal":[3,15,60,147],"question":[4],"answering":[5],"have":[6,22],"primarily":[7],"focused":[8],"on":[9,29,145],"combining":[10],"heterogeneous":[11],"modalities":[12],"or":[13],"fine-tuning":[14],"large":[16],"language":[17],"models.":[18],"While":[19],"these":[20,50,107],"approaches":[21],"shown":[23],"strong":[24],"performance,":[25],"they":[26],"often":[27],"rely":[28],"a":[30,55,119],"single,":[31],"generalized":[32],"reasoning":[33,130],"strategy,":[34],"overlooking":[35],"the":[36,88,113,116,129],"unique":[37],"characteristics":[38],"of":[39,142],"each":[40,99,135],"modality":[41],"ultimately":[42],"limiting":[43],"both":[44,161],"accuracy":[45,162],"and":[46,65,76,93,105,133,163],"interpretability.":[47],"To":[48],"address":[49],"limitations,":[51],"we":[52],"propose":[53],"MAMMQA,":[54],"multi-agent":[56,154],"QA":[57,148],"framework":[58,155],"for":[59],"inputs":[61],"spanning":[62],"text,":[63],"tables,":[64],"images.":[66],"Our":[67],"system":[68],"includes":[69],"two":[70],"Visual":[71],"Language":[72,80],"Model":[73,81],"(VLM)":[74],"agents":[75],"one":[77],"text-based":[78],"Large":[79],"(LLM)":[82],"agent.":[83],"The":[84,101],"first":[85],"VLM":[86,103],"decomposes":[87],"user":[89],"query":[90],"into":[91,118],"sub-questions":[92],"sequentially":[94],"retrieves":[95],"partial":[96],"answers":[97],"from":[98],"modality.":[100],"second":[102],"synthesizes":[104],"refines":[106],"results":[108],"through":[109],"cross-modal":[110],"reasoning.":[111],"Finally,":[112],"LLM":[114],"integrates":[115],"insights":[117],"cohesive":[120],"answer.":[121],"This":[122],"modular":[123],"design":[124],"enhances":[125],"interpretability":[126],"by":[127],"making":[128],"process":[131],"transparent":[132],"allows":[134],"agent":[136],"to":[137],"operate":[138],"within":[139],"its":[140],"domain":[141],"expertise.":[143],"Experiments":[144],"diverse":[146],"benchmarks":[149],"demonstrate":[150],"that":[151],"our":[152],"cooperative,":[153],"consistently":[156],"outperforms":[157],"existing":[158],"baselines":[159],"robustness.":[164]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-02-19T00:00:00"}