{"id":"https://openalex.org/W6967115135","doi":"https://doi.org/10.48550/arxiv.2505.23678","title":"Grounded Reinforcement Learning for Visual Reasoning","display_name":"Grounded Reinforcement Learning for Visual Reasoning","publication_year":2025,"publication_date":"2025-05-29","ids":{"openalex":"https://openalex.org/W6967115135","doi":"https://doi.org/10.48550/arxiv.2505.23678"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2505.23678","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2505.23678","pdf_url":"https://arxiv.org/pdf/2505.23678","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"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2505.23678","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5035580849","display_name":"Gabriel Herbert Sarch","orcid":"https://orcid.org/0000-0002-4396-7612","observed_orcids":["https://orcid.org/0000-0002-4396-7612"]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sarch, Gabriel","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5145531690","display_name":"Snigdha Saha","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Saha, Snigdha","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081570831","display_name":"Naitik Khandelwal","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Khandelwal, Naitik","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jain, Ayush","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jain, Ayush","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008604805","display_name":"Michael J. Tarr","orcid":"https://orcid.org/0000-0003-4724-1744","observed_orcids":["https://orcid.org/0000-0003-4724-1744"]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tarr, Michael J.","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5144550139","display_name":"Aviral Kumar","orcid":"https://orcid.org/0009-0002-3457-4072","observed_orcids":["https://orcid.org/0009-0002-3457-4072"]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kumar, Aviral","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008661738","display_name":"Katerina Fragkiadaki","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fragkiadaki, Katerina","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":64,"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":true,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9824000000953674,"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":0.9824000000953674,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.004699999932199717,"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":0.003000000026077032,"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/visual-reasoning","display_name":"visual reasoning","score":0.9800000190734863},{"id":"https://openalex.org/keywords/vision-language-models","display_name":"vision-language models","score":0.7459999918937683},{"id":"https://openalex.org/keywords/spatial-grounding","display_name":"spatial grounding","score":0.7009999752044678},{"id":"https://openalex.org/keywords/visual-attention","display_name":"visual attention","score":0.8539999723434448},{"id":"https://openalex.org/keywords/multi-turn-reinforcement-learning","display_name":"multi-turn reinforcement learning","score":0.8830000162124634},{"id":"https://openalex.org/keywords/visual-search","display_name":"visual search","score":0.8349999785423279},{"id":"https://openalex.org/keywords/visual-verification","display_name":"visual verification","score":0.5929999947547913}],"concepts":[{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.745199978351593},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5830000042915344},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5728999972343445},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.5109000205993652},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5056999921798706},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5041000247001648},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.49160000681877136},{"id":"https://openalex.org/C2779321571","wikidata":"https://www.wikidata.org/wiki/Q7936605","display_name":"Visual learning","level":2,"score":0.4426000118255615},{"id":"https://openalex.org/C155911833","wikidata":"https://www.wikidata.org/wiki/Q3817354","display_name":"Spatial intelligence","level":2,"score":0.41040000319480896},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3878999948501587},{"id":"https://openalex.org/C111370547","wikidata":"https://www.wikidata.org/wiki/Q7451120","display_name":"Sensory cue","level":2,"score":0.3749000132083893},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.3483000099658966},{"id":"https://openalex.org/C2780103172","wikidata":"https://www.wikidata.org/wiki/Q1309721","display_name":"Visual Objects","level":3,"score":0.3370000123977661},{"id":"https://openalex.org/C124913957","wikidata":"https://www.wikidata.org/wiki/Q1232548","display_name":"Zoom","level":3,"score":0.3368000090122223},{"id":"https://openalex.org/C158495155","wikidata":"https://www.wikidata.org/wiki/Q2369151","display_name":"Visual search","level":2,"score":0.33559998869895935},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3303999900817871},{"id":"https://openalex.org/C115086926","wikidata":"https://www.wikidata.org/wiki/Q17004651","display_name":"Causal reasoning","level":3,"score":0.3228999972343445},{"id":"https://openalex.org/C2777055276","wikidata":"https://www.wikidata.org/wiki/Q7936580","display_name":"Visual approach","level":2,"score":0.3156999945640564},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.31299999356269836},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.29919999837875366},{"id":"https://openalex.org/C83725634","wikidata":"https://www.wikidata.org/wiki/Q7268699","display_name":"Qualitative reasoning","level":2,"score":0.26840001344680786},{"id":"https://openalex.org/C159032336","wikidata":"https://www.wikidata.org/wiki/Q2488768","display_name":"Non-monotonic logic","level":2,"score":0.2624000012874603},{"id":"https://openalex.org/C2780330621","wikidata":"https://www.wikidata.org/wiki/Q7936609","display_name":"Visual modeling","level":4,"score":0.25119999051094055},{"id":"https://openalex.org/C166088908","wikidata":"https://www.wikidata.org/wiki/Q308495","display_name":"Abductive reasoning","level":2,"score":0.25049999356269836},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.24940000474452972},{"id":"https://openalex.org/C86827895","wikidata":"https://www.wikidata.org/wiki/Q7098582","display_name":"Opportunistic reasoning","level":4,"score":0.24860000610351562},{"id":"https://openalex.org/C160086991","wikidata":"https://www.wikidata.org/wiki/Q5939193","display_name":"Human visual system model","level":3,"score":0.24699999392032623},{"id":"https://openalex.org/C56461940","wikidata":"https://www.wikidata.org/wiki/Q970687","display_name":"Eye tracking","level":2,"score":0.24639999866485596},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.24619999527931213},{"id":"https://openalex.org/C2986089797","wikidata":"https://www.wikidata.org/wiki/Q6501338","display_name":"Visual attention","level":3,"score":0.23989999294281006},{"id":"https://openalex.org/C193221554","wikidata":"https://www.wikidata.org/wiki/Q5153664","display_name":"Commonsense reasoning","level":2,"score":0.23029999434947968},{"id":"https://openalex.org/C103057564","wikidata":"https://www.wikidata.org/wiki/Q4751139","display_name":"Analytic reasoning","level":3,"score":0.2296999990940094},{"id":"https://openalex.org/C97364631","wikidata":"https://www.wikidata.org/wiki/Q484284","display_name":"Deductive reasoning","level":2,"score":0.22869999706745148},{"id":"https://openalex.org/C89288958","wikidata":"https://www.wikidata.org/wiki/Q7301504","display_name":"Reasoning system","level":2,"score":0.22619999945163727},{"id":"https://openalex.org/C36964233","wikidata":"https://www.wikidata.org/wiki/Q7920942","display_name":"Verbal reasoning","level":3,"score":0.2257000058889389},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.2249000072479248},{"id":"https://openalex.org/C2778251979","wikidata":"https://www.wikidata.org/wiki/Q7936617","display_name":"Visual processing","level":3,"score":0.21649999916553497},{"id":"https://openalex.org/C178278151","wikidata":"https://www.wikidata.org/wiki/Q7936607","display_name":"Visual memory","level":3,"score":0.2143000066280365},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.21379999816417694},{"id":"https://openalex.org/C43971567","wikidata":"https://www.wikidata.org/wiki/Q3142865","display_name":"Logical reasoning","level":2,"score":0.21160000562667847}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2505.23678","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2505.23678","pdf_url":"https://arxiv.org/pdf/2505.23678","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.2505.23678","doi":"https://doi.org/10.48550/arxiv.2505.23678","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2505.23678","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":"pmh:oai:arXiv.org:2505.23678","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2505.23678","pdf_url":"https://arxiv.org/pdf/2505.23678","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"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G1523888516","display_name":null,"funder_award_id":"FA9550-","funder_id":"https://openalex.org/F4320338279","funder_display_name":"Air Force Office of Scientific Research"},{"id":"https://openalex.org/G2584449986","display_name":"Graduate Research Fellowship Program (GRFP)","funder_award_id":"1745016","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6098521345","display_name":null,"funder_award_id":"FA9550","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G8051438088","display_name":"Graduate Research Fellowship Program (GRFP)","funder_award_id":"2140739","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8876996369","display_name":null,"funder_award_id":"N00014","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320332447","display_name":"U.S. Army","ror":"https://ror.org/00afsp483"},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"},{"id":"https://openalex.org/F4320338279","display_name":"Air Force Office of Scientific Research","ror":"https://ror.org/011e9bt93"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W6967115135.pdf","grobid_xml":"https://content.openalex.org/works/W6967115135.grobid-xml"},"referenced_works_count":51,"referenced_works":["https://openalex.org/W4296406182","https://openalex.org/W4312261477","https://openalex.org/W4323717348","https://openalex.org/W4327810158","https://openalex.org/W4386065691","https://openalex.org/W4390872747","https://openalex.org/W4390874575","https://openalex.org/W4392679398","https://openalex.org/W4399026215","https://openalex.org/W4401306886","https://openalex.org/W4402427562","https://openalex.org/W4402667024","https://openalex.org/W4402667093","https://openalex.org/W4402671607","https://openalex.org/W4402716477","https://openalex.org/W4402727815","https://openalex.org/W4403571128","https://openalex.org/W4403853618","https://openalex.org/W4403883066","https://openalex.org/W4403923795","https://openalex.org/W4404343203","https://openalex.org/W4405140008","https://openalex.org/W4405279515","https://openalex.org/W4405766390","https://openalex.org/W4405783982","https://openalex.org/W4406273429","https://openalex.org/W4406755521","https://openalex.org/W4407231747","https://openalex.org/W4407794264","https://openalex.org/W4409049124","https://openalex.org/W4411119463","https://openalex.org/W4413144646","https://openalex.org/W4413147124","https://openalex.org/W4413147844","https://openalex.org/W4413147863","https://openalex.org/W4414281281","https://openalex.org/W4414957333","https://openalex.org/W4415538382","https://openalex.org/W4415795300","https://openalex.org/W4415796467","https://openalex.org/W4415800507","https://openalex.org/W4416036482","https://openalex.org/W4416184586","https://openalex.org/W4417250113","https://openalex.org/W6929276109","https://openalex.org/W6966680242","https://openalex.org/W7133192525","https://openalex.org/W7133224126","https://openalex.org/W7138024215","https://openalex.org/W7160207210","https://openalex.org/W7196963086"],"related_works":["https://openalex.org/W7164878055","https://openalex.org/W7108230385","https://openalex.org/W7129121622","https://openalex.org/W4416238817","https://openalex.org/W7166661772","https://openalex.org/W7137815919","https://openalex.org/W4417066038","https://openalex.org/W7213505171","https://openalex.org/W4415938663","https://openalex.org/W7218844118"],"abstract_inverted_index":{"While":[0],"reinforcement":[1],"learning":[2],"(RL)":[3],"over":[4],"chains":[5],"of":[6,113],"thought":[7],"has":[8],"significantly":[9,155],"advanced":[10],"language":[11],"models":[12,27,225],"in":[13,39],"tasks":[14],"such":[15,180],"as":[16,106,181],"mathematics":[17],"and":[18,35,118,127,129,139,164,187],"coding,":[19],"visual":[20,30,63,68,79,114,125,153,165,178,188,197,228],"reasoning":[21,38,59,76,107,115,210],"introduces":[22],"added":[23],"complexity":[24],"by":[25,66],"requiring":[26],"to":[28,55,61,72,81,100],"direct":[29],"attention,":[31],"interpret":[32],"perceptual":[33],"inputs,":[34],"ground":[36],"abstract":[37],"spatial":[40,121],"evidence.":[41],"We":[42],"introduce":[43],"ViGoRL":[44,70],"(Visually":[45],"Grounded":[46],"Reinforcement":[47],"Learning),":[48],"a":[49,110,220],"vision-language":[50],"model":[51,99,209],"trained":[52],"with":[53,151,226],"RL":[54,95,141,150,218],"explicitly":[56],"anchor":[57],"each":[58,85],"step":[60],"specific":[62],"coordinates.":[64],"Inspired":[65],"human":[67,191],"decision-making,":[69],"learns":[71],"produce":[73],"spatially":[74,202],"grounded":[75,184,217],"traces,":[77],"guiding":[78],"attention":[80],"task-relevant":[82],"regions":[83],"at":[84],"step.":[86],"When":[87],"fine-grained":[88],"exploration":[89],"is":[90,219],"required,":[91],"our":[92],"novel":[93],"multi-turn":[94,149],"framework":[96],"enables":[97],"the":[98,195],"dynamically":[101],"zoom":[102],"into":[103],"predicted":[104],"coordinates":[105],"unfolds.":[108],"Across":[109],"diverse":[111],"set":[112],"benchmarks--including":[116],"SAT-2":[117],"BLINK":[119],"for":[120,124,131,207,223],"reasoning,":[122],"V*bench":[123],"search,":[126,166],"ScreenSpot":[128],"VisualWebArena":[130],"web-based":[132],"grounding--ViGoRL":[133],"consistently":[134],"outperforms":[135],"both":[136],"supervised":[137],"fine-tuning":[138],"conventional":[140],"baselines":[142],"that":[143,174,194,215],"lack":[144],"explicit":[145],"grounding":[146,175],"mechanisms.":[147],"Incorporating":[148],"zoomed-in":[152],"feedback":[154],"improves":[156],"ViGoRL's":[157],"performance":[158],"on":[159,169],"localizing":[160],"small":[161],"GUI":[162],"elements":[163],"achieving":[167],"86.4%":[168],"V*Bench.":[170],"Additionally,":[171],"we":[172],"find":[173],"amplifies":[176],"other":[177],"behaviors":[179],"region":[182],"exploration,":[183],"subgoal":[185],"setting,":[186],"verification.":[189],"Finally,":[190],"evaluations":[192],"show":[193,214],"model's":[196],"references":[198],"are":[199],"not":[200],"only":[201],"accurate":[203],"but":[204],"also":[205],"helpful":[206],"understanding":[208],"steps.":[211],"Our":[212],"results":[213],"visually":[216],"strong":[221],"paradigm":[222],"imbuing":[224],"general-purpose":[227],"reasoning.":[229]},"counts_by_year":[{"year":2026,"cited_by_count":49},{"year":2025,"cited_by_count":15}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2025-10-10T00:00:00"}