{"id":"https://openalex.org/W7161158789","doi":"https://doi.org/10.48550/arxiv.2605.12620","title":"Think Twice, Act Once: Verifier-Guided Action Selection For Embodied Agents","display_name":"Think Twice, Act Once: Verifier-Guided Action Selection For Embodied Agents","publication_year":2026,"publication_date":"2026-05-12","ids":{"openalex":"https://openalex.org/W7161158789","doi":"https://doi.org/10.48550/arxiv.2605.12620"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.12620","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.12620","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.2605.12620","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5083337957","display_name":"Nishad Singhi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Singhi, Nishad","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019958728","display_name":"Christian Bialas","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bialas, Christian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129930396","display_name":"Snehal Jauhri","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jauhri, Snehal","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024771523","display_name":"Vignesh Prasad","orcid":"https://orcid.org/0000-0002-9729-2454"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Prasad, Vignesh","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026055366","display_name":"Georgia Chalvatzaki","orcid":"https://orcid.org/0000-0002-5055-199X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chalvatzaki, Georgia","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136119283","display_name":"Marcus Rohrbach","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rohrbach, Marcus","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5037747070","display_name":"Anna Rohrbach","orcid":"https://orcid.org/0000-0003-1161-6006"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rohrbach, Anna","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":0.6852999925613403,"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":0.6852999925613403,"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/T10028","display_name":"Topic Modeling","score":0.05429999902844429,"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/T12090","display_name":"Language and cultural evolution","score":0.02759999968111515,"subfield":{"id":"https://openalex.org/subfields/3316","display_name":"Cultural Studies"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/embodied-cognition","display_name":"Embodied cognition","score":0.7760000228881836},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5077999830245972},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.4925999939441681},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.48429998755455017},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.46720001101493835},{"id":"https://openalex.org/keywords/action-selection","display_name":"Action selection","score":0.4643999934196472},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.44929999113082886}],"concepts":[{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.7760000228881836},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6891999840736389},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5250999927520752},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5077999830245972},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.4925999939441681},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.48429998755455017},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.46720001101493835},{"id":"https://openalex.org/C166109690","wikidata":"https://www.wikidata.org/wiki/Q4677422","display_name":"Action selection","level":3,"score":0.4643999934196472},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.44929999113082886},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.43790000677108765},{"id":"https://openalex.org/C103683099","wikidata":"https://www.wikidata.org/wiki/Q5370102","display_name":"Embodied agent","level":3,"score":0.42829999327659607},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3702000081539154},{"id":"https://openalex.org/C187191949","wikidata":"https://www.wikidata.org/wiki/Q1138496","display_name":"Profiling (computer programming)","level":2,"score":0.33230000734329224},{"id":"https://openalex.org/C2777655017","wikidata":"https://www.wikidata.org/wiki/Q1501161","display_name":"Toolbox","level":2,"score":0.3314000070095062},{"id":"https://openalex.org/C192327766","wikidata":"https://www.wikidata.org/wiki/Q1038799","display_name":"Cognitive robotics","level":3,"score":0.3010999858379364},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.2863999903202057},{"id":"https://openalex.org/C2993101906","wikidata":"https://www.wikidata.org/wiki/Q23768","display_name":"Las vegas","level":3,"score":0.2741999924182892},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.2703999876976013},{"id":"https://openalex.org/C2779607372","wikidata":"https://www.wikidata.org/wiki/Q4789757","display_name":"Argumentation framework","level":3,"score":0.25060001015663147}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.12620","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.12620","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.2605.12620","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.12620","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":{"Building":[0],"generalist":[1],"embodied":[2,66,151],"agents":[3,29,67],"capable":[4],"of":[5,27,64,88,133,144],"solving":[6],"complex":[7],"real-world":[8],"tasks":[9],"remains":[10],"a":[11,56,80,93,116,130,141,167],"fundamental":[12],"challenge":[13],"in":[14],"AI.":[15],"Multimodal":[16],"Large":[17],"Language":[18],"Models":[19],"(MLLMs)":[20],"have":[21],"significantly":[22],"advanced":[23],"the":[24,62,98,104,138,155,177],"reasoning":[25,152],"capabilities":[26],"such":[28],"through":[30,68],"strong":[31,173],"vision-language":[32],"knowledge":[33],"and":[34,91,157],"chain-of-thought":[35],"(CoT)":[36],"reasoning,":[37],"yet":[38],"remain":[39],"brittle":[40],"when":[41],"faced":[42],"with":[43],"challenging":[44,179],"out-of-distribution":[45],"scenarios.":[46],"To":[47],"address":[48],"this,":[49],"we":[50,108],"propose":[51],"Verifier-Guided":[52],"Action":[53],"Selection":[54],"(VegAS),":[55],"test-time":[57],"framework":[58],"designed":[59],"to":[60,79,96,136,140,166],"improve":[61],"robustness":[63],"MLLM-based":[65],"an":[69,86,112],"explicit":[70],"verification":[71],"step.":[72],"At":[73],"inference":[74],"time,":[75],"rather":[76],"than":[77],"committing":[78],"single":[81],"decoded":[82],"action,":[83],"VeGAS":[84,160],"samples":[85],"ensemble":[87],"candidate":[89],"actions":[90],"uses":[92],"generative":[94],"verifier":[95,117,139],"identify":[97],"most":[99,178],"reliable":[100],"choice,":[101],"without":[102],"modifying":[103],"underlying":[105],"policy.":[106],"Crucially,":[107],"find":[109],"that":[110],"using":[111],"MLLM":[113],"off-the-shelf":[114],"as":[115],"yields":[118],"no":[119],"improvement,":[120],"motivating":[121],"our":[122],"LLM-driven":[123],"data":[124],"synthesis":[125],"strategy,":[126],"which":[127],"automatically":[128],"constructs":[129],"diverse":[131],"curriculum":[132],"failure":[134],"cases":[135],"expose":[137],"rich":[142],"distribution":[143],"potential":[145],"errors":[146],"at":[147],"training":[148],"time.":[149],"Across":[150],"benchmarks":[153],"spanning":[154],"Habitat":[156],"ALFRED":[158],"environments,":[159],"consistently":[161],"improves":[162],"generalization,":[163],"achieving":[164],"up":[165],"36%":[168],"relative":[169],"performance":[170],"gain":[171],"over":[172],"CoT":[174],"baselines":[175],"on":[176],"multi-object,":[180],"long-horizon":[181],"tasks.":[182]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-15T00:00:00"}