{"id":"https://openalex.org/W7215106350","doi":"https://doi.org/10.48550/arxiv.2609.40230","title":"EviRover: Reinforcing Agentic Perception Beyond a Glance","display_name":"EviRover: Reinforcing Agentic Perception Beyond a Glance","publication_year":2026,"publication_date":"2026-09-30","ids":{"openalex":"https://openalex.org/W7215106350","doi":"https://doi.org/10.48550/arxiv.2609.40230"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.40230","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.40230","pdf_url":"https://arxiv.org/pdf/2609.40230","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/2609.40230","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5041527073","display_name":"Kaixuan Fan","orcid":"https://orcid.org/0009-0003-0354-5057","observed_orcids":["https://orcid.org/0009-0003-0354-5057"]},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Fan, Kaixuan","raw_affiliation_strings":["MMLab , The Chinese University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MMLab , The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035737908","display_name":"Kaituo Feng","orcid":"https://orcid.org/0000-0001-8746-6900","observed_orcids":["https://orcid.org/0000-0001-8746-6900"]},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Feng, Kaituo","raw_affiliation_strings":["MMLab , The Chinese University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MMLab , The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114139333","display_name":"Tianshuo Peng","orcid":"https://orcid.org/0009-0009-7347-0648","observed_orcids":["https://orcid.org/0009-0009-7347-0648"]},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Peng, Tianshuo","raw_affiliation_strings":["MMLab , The Chinese University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MMLab , The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153903276","display_name":"Yilei Jiang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Jiang, Yilei","raw_affiliation_strings":["MMLab , The Chinese University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MMLab , The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153717266","display_name":"Manyuan Zhang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Zhang, Manyuan","raw_affiliation_strings":["MMLab , The Chinese University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MMLab , The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153949524","display_name":"Junke Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wang, Junke","raw_affiliation_strings":["Fudan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078165161","display_name":"Xiangyu Yue","orcid":"https://orcid.org/0000-0002-6887-2046","observed_orcids":["https://orcid.org/0000-0002-6887-2046"]},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yue, Xiangyu","raw_affiliation_strings":["MMLab , The Chinese University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MMLab , The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"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":0.9984999895095825,"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":0.9984999895095825,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.00039999998989515007,"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":0.0003000000142492354,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/insufficient-evidence","display_name":"insufficient evidence","score":0.6890000104904175},{"id":"https://openalex.org/keywords/data-generation-pipeline","display_name":"data generation pipeline","score":0.382999986410141},{"id":"https://openalex.org/keywords/agentic-reinforcement-learning","display_name":"agentic reinforcement learning","score":0.7919999957084656},{"id":"https://openalex.org/keywords/supervised-fine-tuning","display_name":"supervised fine-tuning","score":0.859000027179718},{"id":"https://openalex.org/keywords/multisensory-perception","display_name":"multisensory perception","score":0.6740000247955322}],"concepts":[{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.7675999999046326},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5605999827384949},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5450000166893005},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4839000105857849},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.45680001378059387},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.4242999851703644},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.4172999858856201},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4171000123023987},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3709000051021576},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.35510000586509705},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.31769999861717224},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.2971000075340271},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.2865999937057495},{"id":"https://openalex.org/C22033958","wikidata":"https://www.wikidata.org/wiki/Q7167036","display_name":"Perceptual learning","level":3,"score":0.27869999408721924},{"id":"https://openalex.org/C28063669","wikidata":"https://www.wikidata.org/wiki/Q7167042","display_name":"Perceptual system","level":3,"score":0.2694999873638153},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2685999870300293},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.267300009727478},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2644999921321869}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.40230","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.40230","pdf_url":"https://arxiv.org/pdf/2609.40230","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.2609.40230","doi":"https://doi.org/10.48550/arxiv.2609.40230","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.40230","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:2609.40230","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.40230","pdf_url":"https://arxiv.org/pdf/2609.40230","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":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7215106350.pdf","grobid_xml":"https://content.openalex.org/works/W7215106350.grobid-xml"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W2520200494","https://openalex.org/W4379659789","https://openalex.org/W4389523839","https://openalex.org/W4399251890","https://openalex.org/W4414990013","https://openalex.org/W4415022887","https://openalex.org/W4415337283","https://openalex.org/W4416780398","https://openalex.org/W4417095222","https://openalex.org/W6948315201","https://openalex.org/W6966957745","https://openalex.org/W6966994511","https://openalex.org/W6967068517","https://openalex.org/W7075994152","https://openalex.org/W7077911270","https://openalex.org/W7126150514","https://openalex.org/W7127415714","https://openalex.org/W7127952675","https://openalex.org/W7129373530","https://openalex.org/W7133190261","https://openalex.org/W7133354148","https://openalex.org/W7140170375","https://openalex.org/W7154482883","https://openalex.org/W7154600813","https://openalex.org/W7155358945","https://openalex.org/W7161031081","https://openalex.org/W7164548514","https://openalex.org/W7167100696","https://openalex.org/W7167739371"],"related_works":["https://openalex.org/W7138915851","https://openalex.org/W6948105168","https://openalex.org/W4417298859","https://openalex.org/W7106340406","https://openalex.org/W4414815271","https://openalex.org/W7164505148","https://openalex.org/W4415330115","https://openalex.org/W4414859144","https://openalex.org/W4415250692","https://openalex.org/W4416696005"],"abstract_inverted_index":{"Visual":[0],"perception":[1,62,109,123,172],"is":[2],"conventionally":[3],"formulated":[4],"as":[5,63],"a":[6,10,72,101,179],"one-shot":[7],"prediction":[8],"from":[9],"single":[11,73],"glance":[12],"at":[13],"the":[14,17,20,24,31,77,121,144],"image,":[15],"under":[16,57],"assumption":[18,34],"that":[19,40,67,143],"image":[21],"content":[22],"and":[23,49,60,93,174,187],"model's":[25],"parametric":[26],"knowledge":[27,120],"suffice":[28],"to":[29,118,127,160,169],"resolve":[30,128],"query.":[32],"This":[33],"often":[35],"fails":[36],"in":[37],"real-world":[38],"scenarios":[39],"hinge":[41],"on":[42,112,153,155,182],"fine-grained":[43],"visual":[44],"details":[45],"or":[46],"require":[47],"knowledge-intensive":[48],"up-to-date":[50],"information.":[51],"We":[52,97],"term":[53],"such":[54],"cases":[55],"\\textit{perception":[56],"insufficient":[58],"evidence}":[59],"formulate":[61],"an":[64],"agentic":[65,138],"process":[66],"can":[68],"obtain":[69],"information":[70],"beyond":[71,167],"glance.":[74],"To":[75],"address":[76],"absence":[78],"of":[79],"data":[80,88,188],"for":[81,95],"this":[82],"setting,":[83],"we":[84,115],"design":[85],"two":[86],"dedicated":[87],"generation":[89],"pipelines,":[90],"yielding":[91],"EviRover-SFT-5K":[92],"EviRover-RL-12K":[94],"training.":[96],"further":[98],"construct":[99],"EviLens,":[100,156],"human-verified":[102],"benchmark":[103],"comprising":[104],"688":[105],"instances":[106],"across":[107],"five":[108],"categories.":[110],"Building":[111],"these":[113],"data,":[114],"present":[116],"EviRover,":[117],"our":[119],"first":[122],"agent":[124],"explicitly":[125],"trained":[126],"perceptual":[129],"queries":[130],"through":[131],"interaction,":[132],"using":[133],"supervised":[134],"fine-tuning":[135],"followed":[136],"by":[137,150],"reinforcement":[139],"learning.":[140],"Experiments":[141],"show":[142],"4B":[145],"EviRover":[146],"outperforms":[147],"its":[148],"backbone":[149],"30":[151],"points":[152],"average":[154],"reaching":[157],"performance":[158],"comparable":[159],"advanced":[161],"proprietary":[162],"models.":[163],"The":[164],"gains":[165],"transfer":[166],"EviLens":[168],"WebEyes,":[170],"conventional":[171],"benchmarks,":[173,177],"general":[175],"multimodal":[176],"including":[178],"15-point":[180],"improvement":[181],"BrowseComp-VL.":[183],"All":[184],"code,":[185],"models,":[186],"are":[189],"released.":[190]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-10-02T00:00:00"}