{"id":"https://openalex.org/W7214948575","doi":"https://doi.org/10.48550/arxiv.2609.38086","title":"VISTA: Internalizing Collective Visual Experience via On-Policy Distillation for Active Multimodal Agents","display_name":"VISTA: Internalizing Collective Visual Experience via On-Policy Distillation for Active Multimodal Agents","publication_year":2026,"publication_date":"2026-09-29","ids":{"openalex":"https://openalex.org/W7214948575","doi":"https://doi.org/10.48550/arxiv.2609.38086"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.38086","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.38086","pdf_url":"https://arxiv.org/pdf/2609.38086","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":null,"license_id":null,"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/2609.38086","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5153558713","display_name":"Zheng Jiang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiang, Zheng","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052881929","display_name":"Houde Qian","orcid":"https://orcid.org/0009-0003-6604-7485","observed_orcids":["https://orcid.org/0009-0003-6604-7485"]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qian, Houde","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153672225","display_name":"Yiming Chen","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen, Yiming","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153622514","display_name":"Ling Li","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li, Ling","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153654901","display_name":"Chaoyang Li","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li, Chaoyang","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Li, Yueqi","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li, Yueqi","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153638732","display_name":"Yuxuan Liu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liu, Yuxuan","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5122099578","display_name":"Lifeng Sun","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sun, Lifeng","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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":0.7172999978065491,"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":0.7172999978065491,"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":0.26249998807907104,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.006099999882280827,"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/on-policy-distillation","display_name":"on-policy distillation","score":0.878000020980835},{"id":"https://openalex.org/keywords/visual-tools","display_name":"visual tools","score":0.6039999723434448},{"id":"https://openalex.org/keywords/reasoning","display_name":"reasoning","score":0.3720000088214874}],"concepts":[{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.619700014591217},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5824999809265137},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5529999732971191},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.527400016784668},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5231999754905701},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.4758000075817108},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4189000129699707},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.38510000705718994},{"id":"https://openalex.org/C2779321571","wikidata":"https://www.wikidata.org/wiki/Q7936605","display_name":"Visual learning","level":2,"score":0.373199999332428},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.33820000290870667},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.32739999890327454},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3156999945640564},{"id":"https://openalex.org/C193611912","wikidata":"https://www.wikidata.org/wiki/Q4677596","display_name":"Active vision","level":2,"score":0.27309998869895935},{"id":"https://openalex.org/C56461940","wikidata":"https://www.wikidata.org/wiki/Q970687","display_name":"Eye tracking","level":2,"score":0.2727000117301941},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.2694000005722046},{"id":"https://openalex.org/C2986089797","wikidata":"https://www.wikidata.org/wiki/Q6501338","display_name":"Visual attention","level":3,"score":0.2694000005722046},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.2669000029563904},{"id":"https://openalex.org/C111370547","wikidata":"https://www.wikidata.org/wiki/Q7451120","display_name":"Sensory cue","level":2,"score":0.2655999958515167}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.38086","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.38086","pdf_url":"https://arxiv.org/pdf/2609.38086","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2609.38086","doi":"https://doi.org/10.48550/arxiv.2609.38086","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.38086","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-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2609.38086","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.38086","pdf_url":"https://arxiv.org/pdf/2609.38086","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7214948575.pdf","grobid_xml":"https://content.openalex.org/works/W7214948575.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W2146950091","https://openalex.org/W4382173266","https://openalex.org/W4391631327","https://openalex.org/W4402727815","https://openalex.org/W4409366465","https://openalex.org/W4414580753","https://openalex.org/W4414585765","https://openalex.org/W4415023020","https://openalex.org/W4415798312","https://openalex.org/W4415800507","https://openalex.org/W4416036724","https://openalex.org/W4416068843","https://openalex.org/W4416073099","https://openalex.org/W4416257511","https://openalex.org/W4416271960","https://openalex.org/W4416780398","https://openalex.org/W4417298859","https://openalex.org/W6948369276","https://openalex.org/W7075994152","https://openalex.org/W7125861034","https://openalex.org/W7128026050","https://openalex.org/W7128783650","https://openalex.org/W7128814765","https://openalex.org/W7152742853","https://openalex.org/W7161676639","https://openalex.org/W7162070791","https://openalex.org/W7164002273","https://openalex.org/W7165121545","https://openalex.org/W7165932739","https://openalex.org/W7166046835","https://openalex.org/W7170492302"],"related_works":["https://openalex.org/W7216548374","https://openalex.org/W7131431193","https://openalex.org/W7135214336","https://openalex.org/W7147154999","https://openalex.org/W7214957760","https://openalex.org/W7171411428","https://openalex.org/W6941409059","https://openalex.org/W7168963557","https://openalex.org/W2968968020","https://openalex.org/W3202064807"],"abstract_inverted_index":{"Active":[0],"multimodal":[1,143,169],"agents":[2,144],"use":[3,24],"visual":[4,33,42,57,124],"tools":[5,125],"to":[6,27,103],"acquire":[7],"task-relevant":[8],"evidence":[9],"while":[10,74],"reasoning.":[11],"Although":[12],"reinforcement":[13],"learning":[14,105],"samples":[15],"multiple":[16],"interaction":[17,66,131],"trajectories":[18,81],"per":[19],"input,":[20],"outcome-based":[21],"objectives":[22],"primarily":[23],"the":[25,93,110,135,140,162],"group":[26],"estimate":[28],"scalar":[29],"advantages,":[30],"leaving":[31],"complementary":[32],"discoveries":[34,99],"underused.":[35],"We":[36],"introduce":[37],"VISTA,":[38],"which":[39],"internalizes":[40],"collective":[41,165],"experience":[43,58,166],"through":[44],"on-policy":[45],"distillation":[46,59,85],"by":[47],"turning":[48],"observations":[49,63],"from":[50,100],"same-input":[51],"rollouts":[52],"into":[53],"shared":[54],"supervision.":[55],"Collective":[56],"(CVED)":[60],"organizes":[61],"these":[62],"with":[64,71],"their":[65],"context":[67],"and":[68,82,126,148,157],"aligns":[69],"them":[70],"individual":[72],"decisions,":[73],"heterogeneity-aware":[75],"policy":[76],"improvement":[77],"(HAPI)":[78],"reinforces":[79],"successful":[80],"provides":[83],"experience-guided":[84],"for":[86,167],"unsuccessful":[87],"attempts.":[88],"An":[89],"experience-conditioned":[90],"teacher":[91],"evaluates":[92],"student's":[94,111],"sampled":[95],"response":[96],"prefixes,":[97],"allowing":[98],"one":[101],"trajectory":[102],"guide":[104],"in":[106],"another":[107],"without":[108],"replacing":[109],"original":[112],"history":[113],"or":[114],"generating":[115],"new":[116],"target":[117],"trajectories.":[118],"The":[119],"trained":[120],"agent":[121],"retains":[122],"its":[123,129],"acts":[127],"using":[128],"own":[130],"history.":[132],"VISTA":[133],"achieves":[134],"strongest":[136],"average":[137],"performance":[138],"among":[139],"evaluated":[141],"active":[142,168],"of":[145,164],"comparable":[146],"size":[147],"consistently":[149],"outperforms":[150],"same-backbone":[151],"training":[152],"baselines":[153],"across":[154],"fine-grained":[155],"perception":[156],"general":[158],"reasoning":[159],"tasks,":[160],"demonstrating":[161],"value":[163],"learning.":[170]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-10-01T00:00:00"}
