{"id":"https://openalex.org/W4415537831","doi":"https://doi.org/10.1145/3746027.3762056","title":"Analyze-Prompt-Reason: A Collaborative Agent-Based Framework for Multi-Image Vision-Language Reasoning","display_name":"Analyze-Prompt-Reason: A Collaborative Agent-Based Framework for Multi-Image Vision-Language Reasoning","publication_year":2025,"publication_date":"2025-10-25","ids":{"openalex":"https://openalex.org/W4415537831","doi":"https://doi.org/10.1145/3746027.3762056"},"language":null,"primary_location":{"id":"doi:10.1145/3746027.3762056","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3762056","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","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":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3746027.3762056","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5060202205","display_name":"Angelos Vlachos","orcid":null},"institutions":[{"id":"https://openalex.org/I174458059","display_name":"National Technical University of Athens","ror":"https://ror.org/03cx6bg69","country_code":"GR","type":"education","lineage":["https://openalex.org/I174458059"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Angelos Vlachos","raw_affiliation_strings":["National Technical University of Athens, School of Electrical and Computer Engineering, Artificial Intelligence and Learning Systems Laboratory, National Technical University of Athens, Athens, Attiki, Greece"],"raw_orcid":"https://orcid.org/0009-0000-9467-6754","affiliations":[{"raw_affiliation_string":"National Technical University of Athens, School of Electrical and Computer Engineering, Artificial Intelligence and Learning Systems Laboratory, National Technical University of Athens, Athens, Attiki, Greece","institution_ids":["https://openalex.org/I174458059"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077371399","display_name":"Giorgos Filandrianos","orcid":null},"institutions":[{"id":"https://openalex.org/I174458059","display_name":"National Technical University of Athens","ror":"https://ror.org/03cx6bg69","country_code":"GR","type":"education","lineage":["https://openalex.org/I174458059"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Giorgos Filandrianos","raw_affiliation_strings":["National Technical University of Athens, School of Electrical and Computer Engineering, Artificial Intelligence and Learning Systems Laboratory, National Technical University of Athens, Athens, Attiki, Greece"],"raw_orcid":"https://orcid.org/0000-0002-7015-7746","affiliations":[{"raw_affiliation_string":"National Technical University of Athens, School of Electrical and Computer Engineering, Artificial Intelligence and Learning Systems Laboratory, National Technical University of Athens, Athens, Attiki, Greece","institution_ids":["https://openalex.org/I174458059"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020141370","display_name":"Maria Lymperaiou","orcid":"https://orcid.org/0000-0001-9442-4186"},"institutions":[{"id":"https://openalex.org/I174458059","display_name":"National Technical University of Athens","ror":"https://ror.org/03cx6bg69","country_code":"GR","type":"education","lineage":["https://openalex.org/I174458059"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Maria Lymperaiou","raw_affiliation_strings":["National Technical University of Athens, School of Electrical and Computer Engineering, Artificial Intelligence and Learning Systems Laboratory, National Technical University of Athens, Athens, Attiki, Greece"],"raw_orcid":"https://orcid.org/0000-0001-9442-4186","affiliations":[{"raw_affiliation_string":"National Technical University of Athens, School of Electrical and Computer Engineering, Artificial Intelligence and Learning Systems Laboratory, National Technical University of Athens, Athens, Attiki, Greece","institution_ids":["https://openalex.org/I174458059"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5099022384","display_name":"Nikolaos Spanos","orcid":"https://orcid.org/0009-0001-2691-0956"},"institutions":[{"id":"https://openalex.org/I174458059","display_name":"National Technical University of Athens","ror":"https://ror.org/03cx6bg69","country_code":"GR","type":"education","lineage":["https://openalex.org/I174458059"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Nikolaos Spanos","raw_affiliation_strings":["National Technical University of Athens, School of Electrical and Computer Engineering, Artificial Intelligence and Learning Systems Laboratory, National Technical University of Athens, Athens, Attiki, Greece"],"raw_orcid":"https://orcid.org/0009-0001-2691-0956","affiliations":[{"raw_affiliation_string":"National Technical University of Athens, School of Electrical and Computer Engineering, Artificial Intelligence and Learning Systems Laboratory, National Technical University of Athens, Athens, Attiki, Greece","institution_ids":["https://openalex.org/I174458059"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5094275025","display_name":"Ilias Mitsouras","orcid":null},"institutions":[{"id":"https://openalex.org/I174458059","display_name":"National Technical University of Athens","ror":"https://ror.org/03cx6bg69","country_code":"GR","type":"education","lineage":["https://openalex.org/I174458059"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Ilias Mitsouras","raw_affiliation_strings":["National Technical University of Athens, School of Electrical and Computer Engineering, Artificial Intelligence and Learning Systems Laboratory, National Technical University of Athens, Athens, Attiki, Greece"],"raw_orcid":"https://orcid.org/0009-0006-3918-2616","affiliations":[{"raw_affiliation_string":"National Technical University of Athens, School of Electrical and Computer Engineering, Artificial Intelligence and Learning Systems Laboratory, National Technical University of Athens, Athens, Attiki, Greece","institution_ids":["https://openalex.org/I174458059"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5098535047","display_name":"Vasileios Karampinis","orcid":null},"institutions":[{"id":"https://openalex.org/I174458059","display_name":"National Technical University of Athens","ror":"https://ror.org/03cx6bg69","country_code":"GR","type":"education","lineage":["https://openalex.org/I174458059"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Vasileios Karampinis","raw_affiliation_strings":["National Technical University of Athens, School of Electrical and Computer Engineering, Artificial Intelligence and Learning Systems Laboratory, National Technical University of Athens, Athens, Attiki, Greece"],"raw_orcid":"https://orcid.org/0009-0005-4839-6192","affiliations":[{"raw_affiliation_string":"National Technical University of Athens, School of Electrical and Computer Engineering, Artificial Intelligence and Learning Systems Laboratory, National Technical University of Athens, Athens, Attiki, Greece","institution_ids":["https://openalex.org/I174458059"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062640206","display_name":"Athanasios Voulodimos","orcid":"https://orcid.org/0000-0002-0632-9769"},"institutions":[{"id":"https://openalex.org/I174458059","display_name":"National Technical University of Athens","ror":"https://ror.org/03cx6bg69","country_code":"GR","type":"education","lineage":["https://openalex.org/I174458059"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Athanasios Voulodimos","raw_affiliation_strings":["National Technical University of Athens, School of Electrical and Computer Engineering, Artificial Intelligence and Learning Systems Laboratory, National Technical University of Athens, Athens, Attiki, Greece"],"raw_orcid":"https://orcid.org/0000-0002-0632-9769","affiliations":[{"raw_affiliation_string":"National Technical University of Athens, School of Electrical and Computer Engineering, Artificial Intelligence and Learning Systems Laboratory, National Technical University of Athens, Athens, Attiki, Greece","institution_ids":["https://openalex.org/I174458059"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I174458059"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.25315195,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"13799","last_page":"13805"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9639999866485596,"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":0.9490000009536743,"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/visual-reasoning","display_name":"Visual reasoning","score":0.6729999780654907},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6363999843597412},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5989000201225281},{"id":"https://openalex.org/keywords/automated-reasoning","display_name":"Automated reasoning","score":0.39570000767707825},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.3702999949455261},{"id":"https://openalex.org/keywords/model-based-reasoning","display_name":"Model-based reasoning","score":0.32269999384880066},{"id":"https://openalex.org/keywords/spatial-intelligence","display_name":"Spatial intelligence","score":0.3212999999523163}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7896999716758728},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.6729999780654907},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6363999843597412},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5989000201225281},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5575000047683716},{"id":"https://openalex.org/C195344581","wikidata":"https://www.wikidata.org/wiki/Q2555318","display_name":"Automated reasoning","level":2,"score":0.39570000767707825},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.37209999561309814},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3702999949455261},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3540000021457672},{"id":"https://openalex.org/C37335422","wikidata":"https://www.wikidata.org/wiki/Q6888134","display_name":"Model-based reasoning","level":3,"score":0.32269999384880066},{"id":"https://openalex.org/C155911833","wikidata":"https://www.wikidata.org/wiki/Q3817354","display_name":"Spatial intelligence","level":2,"score":0.3212999999523163},{"id":"https://openalex.org/C86827895","wikidata":"https://www.wikidata.org/wiki/Q7098582","display_name":"Opportunistic reasoning","level":4,"score":0.310699999332428},{"id":"https://openalex.org/C83725634","wikidata":"https://www.wikidata.org/wiki/Q7268699","display_name":"Qualitative reasoning","level":2,"score":0.2996000051498413},{"id":"https://openalex.org/C20162079","wikidata":"https://www.wikidata.org/wiki/Q1151406","display_name":"Case-based reasoning","level":2,"score":0.29580000042915344},{"id":"https://openalex.org/C89288958","wikidata":"https://www.wikidata.org/wiki/Q7301504","display_name":"Reasoning system","level":2,"score":0.29420000314712524},{"id":"https://openalex.org/C2781020372","wikidata":"https://www.wikidata.org/wiki/Q533093","display_name":"On the fly","level":2,"score":0.27889999747276306},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2786000072956085},{"id":"https://openalex.org/C2992734406","wikidata":"https://www.wikidata.org/wiki/Q413267","display_name":"One shot","level":2,"score":0.25679999589920044},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.25130000710487366}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3746027.3762056","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3762056","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","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":{"id":"doi:10.1145/3746027.3762056","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3746027.3762056","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 33rd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W2890399523","https://openalex.org/W3004268082","https://openalex.org/W3120043490","https://openalex.org/W4285249364","https://openalex.org/W4312605624","https://openalex.org/W4312643954","https://openalex.org/W4382202558","https://openalex.org/W4402917193","https://openalex.org/W4404782713"],"related_works":[],"abstract_inverted_index":{"We":[0,73,142],"present":[1],"a":[2,26,29,38,40,89],"Collaborative":[3],"Agent-Based":[4],"Framework":[5],"for":[6,46],"Multi-Image":[7],"Reasoning.":[8],"Our":[9,106],"approach":[10],"tackles":[11],"the":[12,82,156],"challenge":[13],"of":[14,92,159],"interleaved":[15],"multimodal":[16],"reasoning":[17,94,157],"across":[18,59],"diverse":[19,79],"datasets":[20,80],"and":[21,37,55,63,103,138,153],"task":[22],"formats":[23],"by":[24,119],"employing":[25],"dual-agent":[27],"system:":[28],"language-based":[30],"PromptEngineer,":[31],"which":[32],"generates":[33],"context-aware,":[34],"task-specific":[35],"prompts,":[36],"VisionReasoner,":[39],"large":[41],"vision-language":[42],"model":[43,149],"(LVLM)":[44],"responsible":[45],"final":[47],"inference.":[48,105],"The":[49],"framework":[50],"is":[51],"fully":[52],"automated,":[53],"modular,":[54],"training-free,":[56],"enabling":[57],"generalization":[58],"classification,":[60],"question":[61],"answering,":[62],"free-form":[64],"generation":[65],"tasks":[66,95,130],"involving":[67],"one":[68],"or":[69],"multiple":[70,115],"input":[71,154],"images.":[72],"evaluate":[74],"our":[75],"method":[76],"on":[77,128],"18":[78],"from":[81],"2025":[83],"MIRAGE":[84],"Challenge":[85],"(Track":[86],"A),":[87],"covering":[88],"broad":[90],"spectrum":[91],"visual":[93,99],"including":[96],"document":[97],"QA,":[98],"comparison,":[100],"dialogue-based":[101],"understanding,":[102],"scene-level":[104],"results":[107],"demonstrate":[108],"that":[109],"LVLMs":[110],"can":[111],"effectively":[112],"reason":[113],"over":[114],"images":[116],"when":[117],"guided":[118],"informative":[120],"prompts.":[121],"Notably,":[122],"Claude":[123],"3.7":[124],"achieves":[125],"near-ceiling":[126],"performance":[127,158],"challenging":[129],"such":[131],"as":[132,148],"TQA":[133],"(99.13%":[134],"accuracy),":[135],"DocVQA":[136],"(96.87%),":[137],"MMCoQA":[139],"(75.28":[140],"ROUGE-L).":[141],"also":[143],"explore":[144],"how":[145],"design":[146],"choices-such":[147],"selection,":[150],"shot":[151],"count,":[152],"length-influence":[155],"different":[160],"LVLMs.":[161]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-25T00:00:00"}
