{"id":"https://openalex.org/W7161727191","doi":"https://doi.org/10.48550/arxiv.2605.16416","title":"CAVE: A Structured Credit Assignment Approach for Fragmented Visual Evidence Reasoning","display_name":"CAVE: A Structured Credit Assignment Approach for Fragmented Visual Evidence Reasoning","publication_year":2026,"publication_date":"2026-05-13","ids":{"openalex":"https://openalex.org/W7161727191","doi":"https://doi.org/10.48550/arxiv.2605.16416"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.16416","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.16416","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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.2605.16416","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101089157","display_name":"Tengda Guo","orcid":"https://orcid.org/0009-0002-6040-0906"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guo, Tengda","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114022916","display_name":"Jie LENG","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Leng, Jie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136501393","display_name":"Hanlei Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Hanlei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136495136","display_name":"Yaoyuan Liang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liang, Yaoyuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136495598","display_name":"Qingyue Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Qingyue","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101219239","display_name":"Dian Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Dian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136469581","display_name":"Mingyu Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Mingyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136471555","display_name":"Yuhua Fu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fu, Yuhua","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5088293566","display_name":"Shao\u2010Lun Huang","orcid":"https://orcid.org/0000-0003-2827-4022"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Shao-Lun","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":0.9853000044822693,"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":0.9853000044822693,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.0019000000320374966,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.0017000000225380063,"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":0.7724999785423279},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5149000287055969},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4474000036716461},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.4235999882221222},{"id":"https://openalex.org/keywords/abductive-reasoning","display_name":"Abductive reasoning","score":0.4108000099658966},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.40049999952316284},{"id":"https://openalex.org/keywords/deductive-reasoning","display_name":"Deductive reasoning","score":0.38350000977516174},{"id":"https://openalex.org/keywords/empirical-evidence","display_name":"Empirical evidence","score":0.36970001459121704},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.34450000524520874},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.3424000144004822}],"concepts":[{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.7724999785423279},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6998999714851379},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6014000177383423},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5149000287055969},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4474000036716461},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4235999882221222},{"id":"https://openalex.org/C166088908","wikidata":"https://www.wikidata.org/wiki/Q308495","display_name":"Abductive reasoning","level":2,"score":0.4108000099658966},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.40049999952316284},{"id":"https://openalex.org/C97364631","wikidata":"https://www.wikidata.org/wiki/Q484284","display_name":"Deductive reasoning","level":2,"score":0.38350000977516174},{"id":"https://openalex.org/C166052673","wikidata":"https://www.wikidata.org/wiki/Q83021","display_name":"Empirical evidence","level":2,"score":0.36970001459121704},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3668000102043152},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.34450000524520874},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.3424000144004822},{"id":"https://openalex.org/C56461940","wikidata":"https://www.wikidata.org/wiki/Q970687","display_name":"Eye tracking","level":2,"score":0.33970001339912415},{"id":"https://openalex.org/C103057564","wikidata":"https://www.wikidata.org/wiki/Q4751139","display_name":"Analytic reasoning","level":3,"score":0.329800009727478},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.32409998774528503},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.32249999046325684},{"id":"https://openalex.org/C89288958","wikidata":"https://www.wikidata.org/wiki/Q7301504","display_name":"Reasoning system","level":2,"score":0.3089999854564667},{"id":"https://openalex.org/C158495155","wikidata":"https://www.wikidata.org/wiki/Q2369151","display_name":"Visual search","level":2,"score":0.299699991941452},{"id":"https://openalex.org/C115086926","wikidata":"https://www.wikidata.org/wiki/Q17004651","display_name":"Causal reasoning","level":3,"score":0.2930999994277954},{"id":"https://openalex.org/C193221554","wikidata":"https://www.wikidata.org/wiki/Q5153664","display_name":"Commonsense reasoning","level":2,"score":0.28999999165534973},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.2849999964237213},{"id":"https://openalex.org/C2987834672","wikidata":"https://www.wikidata.org/wiki/Q4677630","display_name":"Action recognition","level":3,"score":0.28029999136924744},{"id":"https://openalex.org/C107848011","wikidata":"https://www.wikidata.org/wiki/Q4680756","display_name":"Adaptive reasoning","level":4,"score":0.26739999651908875},{"id":"https://openalex.org/C155911833","wikidata":"https://www.wikidata.org/wiki/Q3817354","display_name":"Spatial intelligence","level":2,"score":0.26600000262260437},{"id":"https://openalex.org/C2780103172","wikidata":"https://www.wikidata.org/wiki/Q1309721","display_name":"Visual Objects","level":3,"score":0.262800008058548},{"id":"https://openalex.org/C43971567","wikidata":"https://www.wikidata.org/wiki/Q3142865","display_name":"Logical reasoning","level":2,"score":0.26109999418258667},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.26030001044273376},{"id":"https://openalex.org/C86827895","wikidata":"https://www.wikidata.org/wiki/Q7098582","display_name":"Opportunistic reasoning","level":4,"score":0.25699999928474426},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2533999979496002},{"id":"https://openalex.org/C37335422","wikidata":"https://www.wikidata.org/wiki/Q6888134","display_name":"Model-based reasoning","level":3,"score":0.25}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.16416","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.16416","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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.2605.16416","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.16416","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Vision-Language":[0],"Models":[1],"(VLMs)":[2],"have":[3],"achieved":[4],"strong":[5],"performance":[6,125,145],"on":[7,49,126,146],"general":[8,147],"multimodal":[9,148],"reasoning,":[10],"yet":[11],"remain":[12],"challenged":[13],"in":[14],"integrating":[15],"nonlocal":[16,104],"visual":[17,23,53,94,130,158],"information":[18],"to":[19,85,115],"support":[20],"semantically":[21,106],"underdetermined":[22],"reasoning.":[24,54],"We":[25],"describe":[26],"this":[27,34],"challenge":[28],"as":[29],"Fragmented":[30],"Visual":[31,41],"Reasoning.":[32],"To":[33],"end,":[35],"we":[36,98],"propose":[37],"Credit":[38],"Assignment":[39],"for":[40,51],"Evidence":[42],"(CAVE),":[43],"a":[44],"structured":[45],"process-reward":[46],"method":[47],"based":[48],"GRPO":[50],"interleaved":[52],"Specifically,":[55],"CAVE":[56,122,154],"evaluates":[57],"the":[58,64,83,157],"contribution":[59],"of":[60],"intermediate":[61,113],"steps":[62],"at":[63],"action":[65,89],"level":[66],"via":[67],"three":[68],"complementary":[69],"reasoning":[70,88,95,108,117,159],"process":[71],"signals:":[72],"belief":[73],"update,":[74],"evidence":[75,114,131],"acquisition,":[76],"and":[77,90,105,110,137,161,167],"adaptive":[78],"focus":[79],"control,":[80],"thereby":[81],"guiding":[82],"model":[84],"optimize":[86],"each":[87],"learn":[91],"more":[92],"reliable":[93],"strategies.":[96],"Meanwhile,":[97],"construct":[99],"TRACER-Bench,":[100,141],"which":[101],"covers":[102],"four":[103],"confusable":[107],"dimensions":[109],"provides":[111],"key":[112],"supervise":[116],"paths.":[118],"Experiments":[119],"demonstrate":[120],"that":[121,153],"substantially":[123],"improves":[124,156],"tasks":[127],"requiring":[128],"fragmented":[129],"integration,":[132],"covering":[133],"both":[134],"public":[135],"benchmarks":[136],"our":[138],"newly":[139],"introduced":[140],"while":[142],"retaining":[143],"competitive":[144],"evaluations.":[149],"Further":[150],"analyses":[151],"reveal":[152],"effectively":[155],"capacity":[160],"exhibits":[162],"stronger":[163],"robustness":[164],"under":[165],"longer-range":[166],"deeper":[168],"cross-region":[169],"dependencies.":[170]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-20T00:00:00"}