{"id":"https://openalex.org/W7214944401","doi":"https://doi.org/10.48550/arxiv.2609.36684","title":"ProgressCompass: Embodied Progress Reward Models Are Lost Without the Right Context","display_name":"ProgressCompass: Embodied Progress Reward Models Are Lost Without the Right Context","publication_year":2026,"publication_date":"2026-09-29","ids":{"openalex":"https://openalex.org/W7214944401","doi":"https://doi.org/10.48550/arxiv.2609.36684"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.36684","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.36684","pdf_url":"https://arxiv.org/pdf/2609.36684","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","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/2609.36684","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5153612867","display_name":"Jianshu Zhang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Jianshu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103989597","display_name":"Keyi Wu","orcid":"https://orcid.org/0009-0005-4204-6407","observed_orcids":["https://orcid.org/0009-0005-4204-6407"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Keliang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113330364","display_name":"Chengxuan Qian","orcid":"https://orcid.org/0009-0007-3517-8043","observed_orcids":["https://orcid.org/0009-0007-3517-8043"]},"institutions":[{"id":"https://openalex.org/I154570441","display_name":"University of California, Santa Barbara","ror":"https://ror.org/02t274463","country_code":"US","type":"education","lineage":["https://openalex.org/I154570441"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qian, Chengxuan","raw_affiliation_strings":["UCSB"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UCSB","institution_ids":["https://openalex.org/I154570441"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153562635","display_name":"Xiyuan Yang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yang, Xiyuan","raw_affiliation_strings":["UIUC"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UIUC","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153636430","display_name":"Ce Zhang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Ce","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153683349","display_name":"Ariel Tian","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tian, Ariel","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5143709143","display_name":"Anbang Liu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Anbang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153636712","display_name":"Haoran Lu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lu, Haoran","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5153634973","display_name":"Han Liu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Han","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9101999998092651,"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":0.9101999998092651,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.08259999752044678,"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"}},{"id":"https://openalex.org/T10906","display_name":"AI-based Problem Solving and Planning","score":0.001500000013038516,"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/embodied-agents","display_name":"embodied agents","score":0.7559999823570251},{"id":"https://openalex.org/keywords/vision-language-models","display_name":"vision-language models","score":0.7379999756813049},{"id":"https://openalex.org/keywords/progress-monitoring","display_name":"progress monitoring","score":0.4339999854564667}],"concepts":[{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7397000193595886},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.7365000247955322},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.7293999791145325},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6187000274658203},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4875999987125397},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4390999972820282},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.42419999837875366},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40790000557899475},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.3813000023365021},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.3287000060081482},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.3257000148296356},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.3246999979019165},{"id":"https://openalex.org/C98184364","wikidata":"https://www.wikidata.org/wiki/Q1780131","display_name":"Argument (complex analysis)","level":2,"score":0.2800000011920929},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.2612000107765198},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.25440001487731934},{"id":"https://openalex.org/C147297375","wikidata":"https://www.wikidata.org/wiki/Q6674930","display_name":"Look-ahead","level":2,"score":0.2531999945640564}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.36684","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.36684","pdf_url":"https://arxiv.org/pdf/2609.36684","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2609.36684","doi":"https://doi.org/10.48550/arxiv.2609.36684","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.36684","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2609.36684","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.36684","pdf_url":"https://arxiv.org/pdf/2609.36684","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","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/W7214944401.pdf","grobid_xml":"https://content.openalex.org/works/W7214944401.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7160901029","https://openalex.org/W7214719620","https://openalex.org/W7165643088","https://openalex.org/W7222962226","https://openalex.org/W7139101525","https://openalex.org/W7171376342","https://openalex.org/W6891891220","https://openalex.org/W7150898713","https://openalex.org/W7164801679","https://openalex.org/W7221311832"],"abstract_inverted_index":{"Embodied":[0,231],"agents":[1],"now":[2],"take":[3],"on":[4,70,83,88,301],"ever":[5],"longer":[6],"tasks.":[7,305],"For":[8],"long":[9,52],"tasks,":[10],"knowing":[11,157],"only":[12],"whether":[13,101],"a":[14,35,151,181,294],"task":[15,36,64],"finally":[16],"succeeds":[17],"or":[18],"fails":[19],"says":[20],"little;":[21],"the":[22,25,54,63,97,142,187,201,208,218,221,243,266,268,273,275],"steps":[23,149,159],"along":[24],"way":[26],"matter.":[27],"Progress":[28],"Reward":[29],"Models":[30],"(PRMs)":[31],"score":[32],"how":[33,61],"far":[34,62,299],"has":[37,65],"come":[38],"at":[39,174],"every":[40],"step,":[41],"and":[42,48,100,162,166,194,259,285],"serve":[43],"as":[44],"dense":[45],"rewards,":[46],"verifiers":[47],"monitors.":[49],"Yet":[50],"in":[51,141,191,195,213,272],"tasks":[53,90,119],"current":[55,98,143,261],"frame":[56],"alone":[57],"often":[58],"cannot":[59],"tell":[60],"come,":[66],"because":[67],"progress":[68,79,84,92,105,135,155,227,238,281,298],"depends":[69],"what":[71],"happened":[72],"before.":[73],"We":[74,112,178,246],"call":[75],"this":[76],"problem":[77],"context-dependent":[78],"estimation.":[80],"Existing":[81],"benchmarks":[82],"estimation":[85],"mostly":[86],"focus":[87],"short":[89],"whose":[91],"can":[93,103],"be":[94],"read":[95,207],"from":[96],"observation,":[99],"PRMs":[102,205,232,296],"estimate":[104,297],"when":[106],"context":[107,220,267],"is":[108,139],"needed":[109,133],"remains":[110],"underexplored.":[111],"therefore":[113,247],"build":[114],"ContextProgress-Bench,":[115],"with":[116,217],"24":[117],"manipulation":[118],"for":[120,134],"120":[121],"episodes.":[122],"The":[123],"benchmark":[124],"covers":[125],"three":[126],"settings:":[127],"(i)":[128],"State":[129],"Recall,":[130],"where":[131,148,170],"information":[132],"appeared":[136],"earlier":[137],"but":[138,240],"not":[140,235],"frame;":[144],"(ii)":[145],"Sequence":[146],"Tracking,":[147],"follow":[150],"fixed":[152],"order,":[153],"so":[154],"requires":[156],"which":[158,163],"are":[160,233],"done":[161],"comes":[164],"next;":[165],"(iii)":[167],"Recurrence":[168],"Disambiguation,":[169],"look-alike":[171],"frames":[172],"sit":[173],"very":[175],"different":[176],"progress.":[177],"then":[179],"run":[180,197],"paired":[182],"diagnosis:":[183],"each":[184],"PRM":[185,258,269,278],"keeps":[186],"same":[188,222,276],"input":[189],"format":[190],"both":[192],"runs,":[193],"one":[196],"its":[198,280,287],"instruction":[199],"integrates":[200],"right":[202,219,244],"context.":[203,245],"Even":[204],"that":[206,254],"entire":[209],"history":[210],"get":[211],"lost":[212,241],"estimating":[214],"progress,":[215],"yet":[216],"five":[223],"models":[224],"cut":[225],"their":[226],"error":[228,282],"by":[229,283,290],"77-82%.":[230],"thus":[234],"incapable":[236],"of":[237],"estimation,":[239],"without":[242],"propose":[248],"ProgressCompass,":[249],"an":[250,256],"autonomous":[251],"agentic":[252],"loop":[253],"reorients":[255],"existing":[257],"uses":[260],"general-purpose":[262],"VLMs":[263],"to":[264],"supply":[265],"needs.":[270],"Wrapped":[271],"loop,":[274],"frozen":[277],"cuts":[279],"63%":[284],"raises":[286],"rank":[288],"agreement":[289],"76%.":[291],"With":[292],"such":[293],"compass,":[295],"better":[300],"longer,":[302],"more":[303],"complex":[304]},"counts_by_year":[],"updated_date":"2026-11-06T12:05:46.655746","created_date":"2026-10-01T00:00:00"}