{"id":"https://openalex.org/W4415938663","doi":"https://doi.org/10.18653/v1/2026.acl-long.2102","title":"Does RLVR Extend Reasoning Boundaries? Investigating Capability Expansion in Vision-Language Models","display_name":"Does RLVR Extend Reasoning Boundaries? Investigating Capability Expansion in Vision-Language Models","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W4415938663","doi":"https://doi.org/10.18653/v1/2026.acl-long.2102"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2026.acl-long.2102","doi":"https://doi.org/10.18653/v1/2026.acl-long.2102","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.2102","pdf_url":null,"source":{"id":"https://openalex.org/S4393915740","display_name":"Proceedings of the conference - Association for Computational Linguistics. Meeting","issn_l":"0736-587X","issn":["0736-587X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.18653/v1/2026.acl-long.2102","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Minghe Shen","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Minghe Shen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120271568","display_name":"Zhuo Zhi","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhuo Zhi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Chonghan Liu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chonghan Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Shuo Xing","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shuo Xing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Zhengzhong Tu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhengzhong Tu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5014579261","display_name":"Che Liu","orcid":"https://orcid.org/0000-0002-9917-8487","observed_orcids":["https://orcid.org/0000-0002-9917-8487","https://orcid.org/0009-0004-3738-7998"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Che Liu","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":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00911838,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"45317","last_page":"45331"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9301999807357788,"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":0.9301999807357788,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.05649999901652336,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.00139999995008111,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning-with-verifiable-rewards","display_name":"reinforcement learning with verifiable rewards","score":0.9459999799728394},{"id":"https://openalex.org/keywords/vision-language-models","display_name":"vision-language models","score":0.9599999785423279},{"id":"https://openalex.org/keywords/spatial-reasoning","display_name":"spatial reasoning","score":0.9710000157356262},{"id":"https://openalex.org/keywords/zero-shot-navigation","display_name":"zero-shot navigation","score":0.6169999837875366},{"id":"https://openalex.org/keywords/out-of-domain-generalization","display_name":"out-of-domain generalization","score":0.7260000109672546}],"concepts":[{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7817999720573425},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6955000162124634},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6947000026702881},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6761000156402588},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6600000262260437},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5612999796867371},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5038999915122986},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.4832000136375427},{"id":"https://openalex.org/C155911833","wikidata":"https://www.wikidata.org/wiki/Q3817354","display_name":"Spatial intelligence","level":2,"score":0.46630001068115234},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4616999924182892},{"id":"https://openalex.org/C42058472","wikidata":"https://www.wikidata.org/wiki/Q810214","display_name":"Base (topology)","level":2,"score":0.44749999046325684},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.4131999909877777},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.3806000053882599},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3357999920845032},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3240000009536743},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.27730000019073486},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.25679999589920044},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.25189998745918274}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.2102","doi":"https://doi.org/10.18653/v1/2026.acl-long.2102","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.2102","pdf_url":null,"source":{"id":"https://openalex.org/S4393915740","display_name":"Proceedings of the conference - Association for Computational Linguistics. Meeting","issn_l":"0736-587X","issn":["0736-587X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2511.00710","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2511.00710","pdf_url":"https://arxiv.org/pdf/2511.00710","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2511.00710","doi":"https://doi.org/10.48550/arxiv.2511.00710","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2511.00710","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,"listed_in":[],"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"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.acl-long.2102","doi":"https://doi.org/10.18653/v1/2026.acl-long.2102","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.2102","pdf_url":null,"source":{"id":"https://openalex.org/S4393915740","display_name":"Proceedings of the conference - Association for Computational Linguistics. Meeting","issn_l":"0736-587X","issn":["0736-587X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W6979283479","https://openalex.org/W4417495068","https://openalex.org/W4416034987","https://openalex.org/W4416280569","https://openalex.org/W7160284950","https://openalex.org/W7137815919","https://openalex.org/W7163143254","https://openalex.org/W7213505171","https://openalex.org/W4415927687","https://openalex.org/W7170173184"],"abstract_inverted_index":{"Recent":[0],"studies":[1],"posit":[2],"that":[3,82,109,117],"Reinforcement":[4],"Learning":[5],"with":[6],"Verifiable":[7],"Rewards":[8],"(RLVR)":[9],"primarily":[10],"amplifies":[11],"behaviors":[12],"inherent":[13],"to":[14,29],"the":[15,33,42,47,66,76,86,95,110,122,135],"pre-training":[16],"distribution":[17],"rather":[18,162],"than":[19,163],"inducing":[20],"new":[21],"capabilities,":[22],"but":[23],"these":[24,153],"insights":[25],"are":[26],"predominantly":[27],"limited":[28],"language-only":[30],"domains,":[31],"leaving":[32],"dynamics":[34],"of":[35,44,50,78],"visual-centric":[36],"spatial":[37,87,158],"reasoning":[38,67,88,159],"under-explored.":[39],"To":[40],"examine":[41],"impact":[43],"RLVR":[45,84],"on":[46,61,92,130,137],"capability":[48,160],"boundaries":[49],"Vision-Language":[51],"Models":[52],"(VLMs),":[53],"we":[54,133],"introduce":[55],"\\textbf{Ariadne},":[56],"a":[57,146],"controlled":[58],"framework":[59],"based":[60],"synthetic":[62,131],"maze":[63],"navigation":[64,140],"where":[65,94],"difficulty":[68],"is":[69],"precisely":[70],"regulated":[71],"by":[72,121],"path":[73],"length":[74],"and":[75,143],"number":[77],"turns.":[79],"We":[80],"demonstrate":[81],"applying":[83],"extends":[85],"boundary,":[89],"achieving":[90],"success":[91],"problems":[93],"base":[96,123],"policy":[97,112],"VLM":[98],"consistently":[99],"attains":[100],"$0\\%$":[101],"accuracy":[102],"despite":[103,126],"increasing":[104],"pass@k":[105],"sampling":[106,165],"budgets,":[107],"indicating":[108],"optimized":[111],"successfully":[113],"navigates":[114],"search":[115],"spaces":[116],"were":[118],"effectively":[119],"unreachable":[120],"distribution.":[124],"Furthermore,":[125],"being":[127],"trained":[128],"exclusively":[129],"mazes,":[132],"evaluate":[134],"model":[136],"two":[138],"real-world":[139],"benchmarks":[141],"(MapBench":[142],"ReasonMap)":[144],"in":[145,152],"zero-shot":[147],"setting.":[148],"The":[149],"observed":[150],"improvements":[151],"out-of-domain":[154],"tasks":[155],"suggest":[156],"genuine":[157],"expansion":[161],"mere":[164],"efficiency.":[166]},"counts_by_year":[],"updated_date":"2026-10-29T09:56:32.521200","created_date":"2025-11-05T00:00:00"}