{"id":"https://openalex.org/W7131064009","doi":"https://doi.org/10.1109/iccvw69036.2025.00124","title":"A Dynamic Agent Framework for Large Language Model Reasoning for Medical and Visual Question Answering","display_name":"A Dynamic Agent Framework for Large Language Model Reasoning for Medical and Visual Question Answering","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W7131064009","doi":"https://doi.org/10.1109/iccvw69036.2025.00124"},"language":null,"primary_location":{"id":"doi:10.1109/iccvw69036.2025.00124","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccvw69036.2025.00124","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)","raw_type":"proceedings-article"},"type":"article","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/A5066852636","display_name":"Ziyan Xiao","orcid":"https://orcid.org/0000-0002-6893-7751"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"Ziyan Xiao","raw_affiliation_strings":["School of Computing and Data Science, University of Hong Kong,Hong Kong"],"affiliations":[{"raw_affiliation_string":"School of Computing and Data Science, University of Hong Kong,Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ruiyang Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Ruiyang Zhang","raw_affiliation_strings":["School of Computing and Data Science, University of Hong Kong,Hong Kong"],"affiliations":[{"raw_affiliation_string":"School of Computing and Data Science, University of Hong Kong,Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010089987","display_name":"Yuan Feng","orcid":"https://orcid.org/0000-0002-6369-0737"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yushi Feng","raw_affiliation_strings":["School of Computing and Data Science, University of Hong Kong,Hong Kong"],"affiliations":[{"raw_affiliation_string":"School of Computing and Data Science, University of Hong Kong,Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126598586","display_name":"Lingting Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Lingting Zhu","raw_affiliation_strings":["School of Computing and Data Science, University of Hong Kong,Hong Kong"],"affiliations":[{"raw_affiliation_string":"School of Computing and Data Science, University of Hong Kong,Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126603302","display_name":"Liang Peng","orcid":null},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Liang Peng","raw_affiliation_strings":["School of Computing and Data Science, University of Hong Kong,Hong Kong"],"affiliations":[{"raw_affiliation_string":"School of Computing and Data Science, University of Hong Kong,Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086786598","display_name":"Long Yu","orcid":"https://orcid.org/0000-0002-5796-6426"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Lequan Yu","raw_affiliation_strings":["School of Computing and Data Science, University of Hong Kong,Hong Kong"],"affiliations":[{"raw_affiliation_string":"School of Computing and Data Science, University of Hong Kong,Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5066852636"],"corresponding_institution_ids":["https://openalex.org/I889458895"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.73296013,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1154","last_page":"1163"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8848999738693237,"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":0.8848999738693237,"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/T12031","display_name":"Speech and dialogue systems","score":0.026399999856948853,"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/T10028","display_name":"Topic Modeling","score":0.024700000882148743,"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/inference","display_name":"Inference","score":0.6934000253677368},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5605999827384949},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.5602999925613403},{"id":"https://openalex.org/keywords/model-based-reasoning","display_name":"Model-based reasoning","score":0.5310999751091003},{"id":"https://openalex.org/keywords/reasoning-system","display_name":"Reasoning system","score":0.42170000076293945},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.35589998960494995},{"id":"https://openalex.org/keywords/opportunistic-reasoning","display_name":"Opportunistic reasoning","score":0.352400004863739},{"id":"https://openalex.org/keywords/abductive-reasoning","display_name":"Abductive reasoning","score":0.3522000014781952},{"id":"https://openalex.org/keywords/qualitative-reasoning","display_name":"Qualitative reasoning","score":0.3440000116825104}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7698000073432922},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6934000253677368},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5605999827384949},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.5602999925613403},{"id":"https://openalex.org/C37335422","wikidata":"https://www.wikidata.org/wiki/Q6888134","display_name":"Model-based reasoning","level":3,"score":0.5310999751091003},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.524399995803833},{"id":"https://openalex.org/C89288958","wikidata":"https://www.wikidata.org/wiki/Q7301504","display_name":"Reasoning system","level":2,"score":0.42170000076293945},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36890000104904175},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.35589998960494995},{"id":"https://openalex.org/C86827895","wikidata":"https://www.wikidata.org/wiki/Q7098582","display_name":"Opportunistic reasoning","level":4,"score":0.352400004863739},{"id":"https://openalex.org/C166088908","wikidata":"https://www.wikidata.org/wiki/Q308495","display_name":"Abductive reasoning","level":2,"score":0.3522000014781952},{"id":"https://openalex.org/C83725634","wikidata":"https://www.wikidata.org/wiki/Q7268699","display_name":"Qualitative reasoning","level":2,"score":0.3440000116825104},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.32829999923706055},{"id":"https://openalex.org/C159032336","wikidata":"https://www.wikidata.org/wiki/Q2488768","display_name":"Non-monotonic logic","level":2,"score":0.32269999384880066},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3221000134944916},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.30059999227523804},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.29409998655319214},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.29100000858306885},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2825999855995178},{"id":"https://openalex.org/C97364631","wikidata":"https://www.wikidata.org/wiki/Q484284","display_name":"Deductive reasoning","level":2,"score":0.27709999680519104},{"id":"https://openalex.org/C46743427","wikidata":"https://www.wikidata.org/wiki/Q1341685","display_name":"Inference engine","level":3,"score":0.2721000015735626},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.26809999346733093},{"id":"https://openalex.org/C195344581","wikidata":"https://www.wikidata.org/wiki/Q2555318","display_name":"Automated reasoning","level":2,"score":0.2630999982357025},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2630000114440918},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2603999972343445},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.25450000166893005},{"id":"https://openalex.org/C534262118","wikidata":"https://www.wikidata.org/wiki/Q177719","display_name":"Medical diagnosis","level":2,"score":0.25040000677108765}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iccvw69036.2025.00124","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccvw69036.2025.00124","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5280306935310364,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W2901466771","https://openalex.org/W2970482702","https://openalex.org/W2970641574","https://openalex.org/W3162922479","https://openalex.org/W3165058054","https://openalex.org/W4361001766","https://openalex.org/W4403726885","https://openalex.org/W4408291427","https://openalex.org/W4409657176","https://openalex.org/W4412551677","https://openalex.org/W4412944561","https://openalex.org/W4412944572","https://openalex.org/W4412944790","https://openalex.org/W4415797946","https://openalex.org/W4416036229"],"related_works":[],"abstract_inverted_index":{"Eliciting":[0],"the":[1,20,50,61,106,115,186],"reasoning":[2,38,47,84,107,116],"capability":[3],"of":[4,22,60,190],"Large":[5],"Language":[6],"Models":[7],"(LLMs)":[8],"for":[9,127,134,169],"medical":[10,43,74,109,170,194],"Visual":[11],"Question":[12],"Answering":[13],"(VQA)":[14],"remains":[15],"essential":[16],"yet":[17],"challenging.":[18],"First,":[19],"entanglement":[21],"question":[23],"comprehension,":[24],"knowledge":[25],"retrieval,":[26],"and":[27,35,138,142,148,167,175,188],"inference":[28,143],"processes":[29],"makes":[30],"it":[31],"difficult":[32],"to":[33,81,104,164],"isolate":[34],"analyze":[36],"individual":[37],"components.":[39],"Second,":[40],"addressing":[41],"different":[42],"questions":[44],"requires":[45],"various":[46],"paradigms,":[48],"while":[49],"traditional":[51],"static":[52],"prompt":[53],"paradigm":[54],"does":[55],"not":[56],"take":[57],"full":[58],"advantage":[59],"diverse":[62],"instructions":[63],"that":[64,179],"LLMs":[65],"can":[66],"provide.":[67],"These":[68],"limitations":[69],"are":[70],"compounded":[71],"by":[72],"current":[73],"VQA":[75,195],"benchmarks,":[76],"which":[77],"lack":[78],"granular":[79],"metrics":[80],"evaluate":[82],"context-specific":[83],"patterns":[85],"beyond":[86],"overall":[87],"accuracy.":[88],"To":[89],"address":[90],"those":[91],"challenges,":[92],"in":[93,108,184,193],"this":[94,153],"paper,":[95],"we":[96],"propose":[97],"a":[98,122,131,140,159],"reward-based":[99],"Dynamic":[100],"Agent":[101],"Framework":[102],"(MedDAF)":[103],"improve":[105],"VQA.":[110,171],"Our":[111],"framework":[112,157,163],"explicitly":[113],"disentangles":[114],"pipeline":[117],"into":[118],"three":[119],"components:":[120],"(1)":[121],"question-agent":[123],"latent":[124],"space":[125],"module":[126,133,144],"experience":[128],"accumulation,":[129],"(2)":[130],"planning":[132],"optimal":[135],"agent":[136,162],"selection,":[137],"(3)":[139],"judgment":[141],"with":[145],"reward":[146],"scoring":[147],"final":[149],"answer":[150],"generation.":[151],"Through":[152],"iterative":[154],"process,":[155],"our":[156,180],"forms":[158],"temporal":[160],"dynamic":[161],"enhance":[165],"accuracy":[166,187],"efficiency":[168,189],"Experiments":[172],"on":[173,203],"VQA-RAD":[174],"SLAKE":[176],"have":[177],"shown":[178],"approach":[181],"is":[182,200],"effective":[183],"improving":[185],"zero-shot":[191],"performance":[192],"tasks.":[196],"The":[197],"implementation":[198],"code":[199],"publicly":[201],"available":[202],"https://github.com/Ziyan-Xiao/MedDAF/.":[204]},"counts_by_year":[],"updated_date":"2026-03-25T23:56:10.502304","created_date":"2026-02-24T00:00:00"}