{"id":"https://openalex.org/W7202221045","doi":"https://doi.org/10.48550/arxiv.2608.07959","title":"SCOUT: Self-Checking and Recovery-Aware Tool-Thought Agents for Ultra-Long Egocentric Video Reasoning","display_name":"SCOUT: Self-Checking and Recovery-Aware Tool-Thought Agents for Ultra-Long Egocentric Video Reasoning","publication_year":2026,"publication_date":"2026-08-08","ids":{"openalex":"https://openalex.org/W7202221045","doi":"https://doi.org/10.48550/arxiv.2608.07959"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.07959","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.07959","pdf_url":"https://arxiv.org/pdf/2608.07959","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","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.07959","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5063396689","display_name":"Keyang Zhong","orcid":"https://orcid.org/0009-0008-7420-3333","observed_orcids":["https://orcid.org/0009-0008-7420-3333"]},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhong, Keyang","raw_affiliation_strings":["Sun Yat-sen University Guangzhou , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University Guangzhou , China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5146568128","display_name":"Kuo Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wang, Kuo","raw_affiliation_strings":["Sun Yat-sen University Guangzhou , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University Guangzhou , China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5146571857","display_name":"Peng Liu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Peng","raw_affiliation_strings":["Guangdong","OPPO Mobile Telecommunications Corp., Ltd. OPPO AI Center Shenzhen , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangdong","institution_ids":[]},{"raw_affiliation_string":"OPPO Mobile Telecommunications Corp., Ltd. OPPO AI Center Shenzhen , China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038810646","display_name":"Quanlong Zheng","orcid":"https://orcid.org/0000-0001-5059-0078","observed_orcids":["https://orcid.org/0000-0001-5059-0078"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zheng, Quanlong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133602172","display_name":"Junlin Xie","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xie, Junlin","raw_affiliation_strings":["The Chinese University of Hong Kong , Shenzhen Shenzhen , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong , Shenzhen Shenzhen , China","institution_ids":["https://openalex.org/I4210116924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132693654","display_name":"Zhijia Liang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang, Zhijia","raw_affiliation_strings":["Sun Yat-sen University Guangzhou , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sun Yat-sen University Guangzhou , China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125732514","display_name":"Yanhao Zhang","orcid":"https://orcid.org/0009-0001-6300-8590","observed_orcids":["https://orcid.org/0009-0001-6300-8590"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Yanhao","raw_affiliation_strings":["Guangdong","OPPO Mobile Telecommunications Corp., Ltd. OPPO AI Center Shenzhen , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangdong","institution_ids":[]},{"raw_affiliation_string":"OPPO Mobile Telecommunications Corp., Ltd. OPPO AI Center Shenzhen , China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5132618374","display_name":"Guanbin Li","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li, Guanbin","raw_affiliation_strings":["Shenzhen Loop Area Institute Shenzhen , China","Sun Yat-sen University Guangzhou , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Loop Area Institute Shenzhen , China","institution_ids":[]},{"raw_affiliation_string":"Sun Yat-sen University Guangzhou , China","institution_ids":["https://openalex.org/I157773358"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"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":0.9907000064849854,"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":0.9907000064849854,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.0020000000949949026,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.0006000000284984708,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/multi-hop-reasoning","display_name":"multi-hop reasoning","score":0.7519999742507935},{"id":"https://openalex.org/keywords/error-propagation","display_name":"error propagation","score":0.628000020980835},{"id":"https://openalex.org/keywords/credit-assignment","display_name":"credit assignment","score":0.7730000019073486}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7773000001907349},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5881999731063843},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5741000175476074},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5680000185966492},{"id":"https://openalex.org/C148220186","wikidata":"https://www.wikidata.org/wiki/Q7111912","display_name":"Outcome (game theory)","level":2,"score":0.46880000829696655},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4440999925136566},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.36899998784065247},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.2906000018119812},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2761000096797943},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.26969999074935913},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.2678999900817871},{"id":"https://openalex.org/C2983174267","wikidata":"https://www.wikidata.org/wiki/Q3775098","display_name":"Video retrieval","level":2,"score":0.2639999985694885},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.2547999918460846}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.07959","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.07959","pdf_url":"https://arxiv.org/pdf/2608.07959","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.2608.07959","doi":"https://doi.org/10.48550/arxiv.2608.07959","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.07959","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:2608.07959","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.07959","pdf_url":"https://arxiv.org/pdf/2608.07959","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/G4751043524","display_name":null,"funder_award_id":"62322608","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320317140","display_name":"National Supercomputer Centre in Guangzhou","ror":"https://ror.org/042999n30"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7202221045.pdf","grobid_xml":"https://content.openalex.org/works/W7202221045.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4415109264","https://openalex.org/W7213341021","https://openalex.org/W7162553809","https://openalex.org/W7215057394","https://openalex.org/W7196937680","https://openalex.org/W4416117013","https://openalex.org/W7125555593","https://openalex.org/W4417464859","https://openalex.org/W7117248150","https://openalex.org/W4415932907"],"abstract_inverted_index":{"Ultra-long":[0],"egocentric":[1,178],"video":[2,27],"understanding":[3],"requires":[4],"reasoning":[5,90],"over":[6,91,115],"temporally":[7],"sparse":[8,109],"evidence":[9],"distributed":[10],"across":[11],"hours":[12],"or":[13],"days,":[14],"challenging":[15],"current":[16],"multimodal":[17],"models":[18],"with":[19,160],"limited":[20],"context":[21],"and":[22,37,77,83,112],"the":[23],"grounding":[24],"of":[25],"key":[26],"segments.":[28],"While":[29],"Chain-of-Tool-Thought":[30],"(CoTT)":[31],"agent":[32],"systems":[33],"enable":[34],"iterative":[35],"retrieval":[36],"inspection,":[38],"they":[39],"suffer":[40],"from":[41],"error":[42],"propagation":[43],"due":[44],"to":[45],"rigid":[46],"zoom-in":[47],"strategies":[48],"that":[49,72,138,156,171],"lack":[50,113],"recovery":[51],"mechanisms.":[52],"In":[53],"this":[54],"work,":[55],"we":[56,130],"address":[57,128],"these":[58],"challenges":[59],"through":[60],"SCOUT":[61,172],"(Self-Checking":[62],"Chain-Of-Tool-thought),":[63],"a":[64,152],"recovery-aware":[65],"agentic":[66],"framework":[67],"introducing":[68],"an":[69,133],"adaptive":[70],"policy":[71,135],"evaluates":[73],"intermediate":[74],"tool":[75],"observations":[76],"dynamically":[78],"trades":[79],"off":[80],"exploitation":[81],"(zoom-in)":[82],"exploration":[84,140],"(region":[85],"switching),":[86],"enabling":[87],"robust":[88],"multi-hop":[89],"extremely":[92],"long":[93],"horizons.":[94],"However,":[95],"training":[96],"such":[97],"multi-turn":[98],"tool-using":[99],"agents":[100],"remains":[101],"challenging,":[102],"as":[103],"existing":[104],"RL":[105],"methods":[106],"rely":[107],"on":[108,141,176,183],"outcome-level":[110],"rewards":[111,159,164],"supervision":[114],"extended":[116],"decision":[117],"trajectories,":[118],"resulting":[119],"in":[120],"suboptimal":[121],"credit":[122,167],"assignment":[123],"for":[124,165],"long-horizon":[125],"reasoning.":[126],"To":[127],"this,":[129],"develop":[131],"UPS-GRPO,":[132],"uncertainty-prioritized":[134],"optimization":[136],"method":[137],"concentrates":[139],"high-uncertainty":[142],"post-tool":[143],"states":[144],"while":[145,180],"preserving":[146],"sample":[147],"efficiency.":[148],"We":[149],"further":[150],"introduce":[151],"turn-level":[153],"advantage":[154],"decomposition":[155],"integrates":[157],"outcome":[158],"tool-grounded":[161],"temporal":[162],"alignment":[163],"improved":[166],"assignment.":[168],"Experiments":[169],"show":[170],"achieves":[173],"state-of-the-art":[174],"results":[175],"ultra-long":[177],"benchmarks,":[179],"remaining":[181],"competitive":[182],"shorter-horizon":[184],"long-video":[185],"settings.":[186]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-08-12T00:00:00"}