{"id":"https://openalex.org/W7137818832","doi":"https://doi.org/10.48550/arxiv.2603.14117","title":"Improving Visual Reasoning with Iterative Evidence Refinement","display_name":"Improving Visual Reasoning with Iterative Evidence Refinement","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7137818832","doi":"https://doi.org/10.48550/arxiv.2603.14117"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.14117","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.14117","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.14117","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5111036231","display_name":"Zeru Shi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shi, Zeru","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100929110","display_name":"Kai Mei","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mei, Kai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114202283","display_name":"Yihao Quan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Quan, Yihao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129698569","display_name":"Dimitris N. Metaxas","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Metaxas, Dimitris N.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5129687573","display_name":"Ruixiang Tang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tang, Ruixiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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":0.9722999930381775,"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":0.9722999930381775,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.005400000140070915,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.0038999998942017555,"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":0.7361999750137329},{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.48420000076293945},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.45730000734329224},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.3686000108718872},{"id":"https://openalex.org/keywords/visual-objects","display_name":"Visual Objects","score":0.34450000524520874},{"id":"https://openalex.org/keywords/visual-perception","display_name":"Visual perception","score":0.33329999446868896},{"id":"https://openalex.org/keywords/eye-tracking","display_name":"Eye tracking","score":0.31520000100135803},{"id":"https://openalex.org/keywords/opportunistic-reasoning","display_name":"Opportunistic reasoning","score":0.304500013589859}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7451000213623047},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.7361999750137329},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6905999779701233},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.48420000076293945},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.45730000734329224},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.40209999680519104},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.3686000108718872},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3506999909877777},{"id":"https://openalex.org/C2780103172","wikidata":"https://www.wikidata.org/wiki/Q1309721","display_name":"Visual Objects","level":3,"score":0.34450000524520874},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.33329999446868896},{"id":"https://openalex.org/C56461940","wikidata":"https://www.wikidata.org/wiki/Q970687","display_name":"Eye tracking","level":2,"score":0.31520000100135803},{"id":"https://openalex.org/C86827895","wikidata":"https://www.wikidata.org/wiki/Q7098582","display_name":"Opportunistic reasoning","level":4,"score":0.304500013589859},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2879999876022339},{"id":"https://openalex.org/C83725634","wikidata":"https://www.wikidata.org/wiki/Q7268699","display_name":"Qualitative reasoning","level":2,"score":0.2851000130176544},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2696000039577484},{"id":"https://openalex.org/C124913957","wikidata":"https://www.wikidata.org/wiki/Q1232548","display_name":"Zoom","level":3,"score":0.2685000002384186},{"id":"https://openalex.org/C193611912","wikidata":"https://www.wikidata.org/wiki/Q4677596","display_name":"Active vision","level":2,"score":0.26820001006126404},{"id":"https://openalex.org/C5339829","wikidata":"https://www.wikidata.org/wiki/Q1425977","display_name":"Machine vision","level":2,"score":0.2678999900817871},{"id":"https://openalex.org/C103057564","wikidata":"https://www.wikidata.org/wiki/Q4751139","display_name":"Analytic reasoning","level":3,"score":0.26249998807907104},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.26030001044273376},{"id":"https://openalex.org/C37335422","wikidata":"https://www.wikidata.org/wiki/Q6888134","display_name":"Model-based reasoning","level":3,"score":0.2597000002861023},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.257999986410141},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.25029999017715454}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.14117","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.14117","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.14117","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.14117","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Vision":[0],"language":[1],"models":[2,95],"(VLMs)":[3],"are":[4],"increasingly":[5],"capable":[6],"of":[7,107],"reasoning":[8,14,53,116,161,167],"over":[9],"images,":[10],"but":[11],"robust":[12],"visual":[13,23,68,130,149,166],"often":[15],"requires":[16,45],"re-grounding":[17],"intermediate":[18],"steps":[19,125],"in":[20],"the":[21,52,115,144,160],"underlying":[22],"evidence.":[24],"Recent":[25],"approaches":[26],"typically":[27],"rely":[28],"on":[29,128,164,187],"external":[30,133],"image":[31,47,98,109],"operations":[32],"such":[33],"as":[34],"zooming":[35],"or":[36,136],"cropping":[37],"to":[38,78,96,126,142,147,155],"re-access":[39],"fine-grained":[40],"details":[41],"during":[42,159],"inference,":[43],"which":[44,152],"additional":[46,119],"re-encoding":[48],"and":[49,66,70,111,151,157,173],"can":[50,74],"disrupt":[51],"trajectory.":[54],"We":[55,138],"argue":[56],"that":[57,71,93,177],"VLMs":[58],"already":[59],"provide":[60],"strong":[61],"internal":[62,101],"signals":[63,73],"for":[64],"identifying":[65],"reusing":[67],"evidence,":[69],"these":[72],"be":[75],"directly":[76],"leveraged":[77],"support":[79],"image-grounded":[80],"reasoning.":[81],"Motivated":[82],"by":[83,184],"this":[84],"insight,":[85],"we":[86],"propose":[87],"an":[88],"end-to-end":[89],"self-revisit":[90],"framework,":[91],"SIEVE,":[92],"trains":[94],"re-engage":[97],"evidence":[99],"through":[100],"representations.":[102],"SIEVE":[103,178],"automatically":[104],"extracts":[105],"embeddings":[106,154],"salient":[108],"regions":[110],"injects":[112],"them":[113],"into":[114],"chain":[117],"when":[118,146],"grounding":[120],"is":[121],"needed,":[122],"enabling":[123],"later":[124],"condition":[127],"relevant":[129],"cues":[131],"without":[132],"tool":[134],"calls":[135],"re-encoding.":[137],"use":[139],"reinforcement":[140],"learning":[141],"teach":[143],"model":[145],"trigger":[148],"revisiting":[150],"region":[153],"retrieve":[156],"insert":[158],"process.":[162],"Experiments":[163],"multiple":[165],"benchmarks,":[168],"together":[169],"with":[170],"perception,":[171],"reasoning,":[172],"hallucination":[174],"evaluations,":[175],"show":[176],"yields":[179],"consistent":[180],"gains,":[181],"improving":[182],"performance":[183],"8":[185],"percent":[186],"average":[188],"across":[189],"several":[190],"benchmarks.":[191]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-03-18T00:00:00"}