{"id":"https://openalex.org/W7137919423","doi":"https://doi.org/10.48550/arxiv.2603.15418","title":"MA-VLCM: A Vision Language Critic Model for Value Estimation of Policies in Multi-Agent Team Settings","display_name":"MA-VLCM: A Vision Language Critic Model for Value Estimation of Policies in Multi-Agent Team Settings","publication_year":2026,"publication_date":"2026-03-16","ids":{"openalex":"https://openalex.org/W7137919423","doi":"https://doi.org/10.48550/arxiv.2603.15418"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.15418","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.15418","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.2603.15418","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5123940343","display_name":"Shahil Shaik","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shaik, Shahil","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088416841","display_name":"Aditya Parameshwaran","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Parameshwaran, Aditya","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086880007","display_name":"Anshul Nayak","orcid":"https://orcid.org/0000-0003-0094-1639"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nayak, Anshul","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036239586","display_name":"Jonathon M. Smereka","orcid":"https://orcid.org/0000-0001-9262-1143"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Smereka, Jonathon M.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5129727058","display_name":"Yue Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Yue","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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.6578999757766724,"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"}},"topics":[{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.6578999757766724,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.19099999964237213,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.03700000047683716,"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/generalization","display_name":"Generalization","score":0.7300000190734863},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6590999960899353},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5591999888420105},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.5260000228881836},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.43970000743865967},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.4124999940395355},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.4090000092983246},{"id":"https://openalex.org/keywords/value","display_name":"Value (mathematics)","score":0.4025999903678894},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.387800008058548}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7301999926567078},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.7300000190734863},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6590999960899353},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.651199996471405},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5591999888420105},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.5260000228881836},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4968999922275543},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.43970000743865967},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.4124999940395355},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.4090000092983246},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.4025999903678894},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.387800008058548},{"id":"https://openalex.org/C2781235140","wikidata":"https://www.wikidata.org/wiki/Q275131","display_name":"Scratch","level":2,"score":0.3871000111103058},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.3865000009536743},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.3750999867916107},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.33070001006126404},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2980000078678131},{"id":"https://openalex.org/C2780878386","wikidata":"https://www.wikidata.org/wiki/Q1659648","display_name":"Visual language","level":2,"score":0.2872999906539917},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.28040000796318054},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.2782000005245209},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.2734000086784363},{"id":"https://openalex.org/C29202148","wikidata":"https://www.wikidata.org/wiki/Q287260","display_name":"Resource allocation","level":2,"score":0.2648000121116638},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.2587999999523163},{"id":"https://openalex.org/C2777055276","wikidata":"https://www.wikidata.org/wiki/Q7936580","display_name":"Visual approach","level":2,"score":0.25040000677108765}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.15418","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.15418","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.2603.15418","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.15418","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":{"Multi-agent":[0],"reinforcement":[1],"learning":[2,16,125],"(MARL)":[3],"commonly":[4],"relies":[5],"on":[6,40,109,143,152,158],"a":[7,18,82,93,105],"centralized":[8,88,106],"critic":[9,19,89,107,124],"to":[10,98],"estimate":[11],"the":[12,32,86],"value":[13],"function.":[14],"However,":[15],"such":[17],"from":[20],"scratch":[21],"is":[22],"highly":[23],"sample-inefficient":[24],"and":[25,47,69,117,160],"often":[26],"lacks":[27],"generalization":[28,49],"across":[29],"environments.":[30],"At":[31],"same":[33],"time,":[34],"large":[35],"vision-language-action":[36],"models":[37,153],"(VLAs)":[38],"trained":[39],"internet-scale":[41],"data":[42],"exhibit":[43],"strong":[44],"multimodal":[45],"reasoning":[46],"zero-shot":[48,149],"capabilities,":[50],"yet":[51],"directly":[52],"deploying":[53],"them":[54],"for":[55,141],"robotic":[56],"execution":[57,138],"remains":[58],"computationally":[59],"prohibitive,":[60],"particularly":[61],"in":[62,90,163],"heterogeneous":[63],"multi-robot":[64],"systems":[65],"with":[66,92,154],"diverse":[67],"embodiments":[68],"resource":[70],"constraints.":[71],"To":[72],"address":[73],"these":[74],"challenges,":[75],"we":[76],"propose":[77],"Multi-Agent":[78],"Vision-Language-Critic":[79],"Models":[80],"(MA-VLCM),":[81],"framework":[83],"that":[84],"replaces":[85],"learned":[87],"MARL":[91],"pretrained":[94],"vision-language":[95],"model":[96],"fine-tuned":[97],"evaluate":[99],"multi-agent":[100,119,164],"behavior.":[101],"MA-VLCM":[102],"acts":[103],"as":[104],"conditioned":[108],"natural":[110],"language":[111],"task":[112],"descriptions,":[113],"visual":[114],"trajectory":[115],"observations,":[116],"structured":[118],"state":[120],"information.":[121],"By":[122],"eliminating":[123],"during":[126],"policy":[127],"optimization,":[128],"our":[129],"approach":[130],"significantly":[131],"improves":[132],"sample":[133],"efficiency":[134],"while":[135],"producing":[136],"compact":[137],"policies":[139],"suitable":[140],"deployment":[142],"resource-constrained":[144],"robots.":[145],"Results":[146],"show":[147],"good":[148],"return":[150],"estimation":[151],"differing":[155],"VLM":[156],"backbones":[157],"in-distribution":[159],"out-of-distribution":[161],"scenarios":[162],"team":[165],"settings":[166]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-03-18T00:00:00"}