{"id":"https://openalex.org/W7151431891","doi":"https://doi.org/10.48550/arxiv.2604.04108","title":"Hypothesis Graph Refinement: Hypothesis-Driven Exploration with Cascade Error Correction for Embodied Navigation","display_name":"Hypothesis Graph Refinement: Hypothesis-Driven Exploration with Cascade Error Correction for Embodied Navigation","publication_year":2026,"publication_date":"2026-04-05","ids":{"openalex":"https://openalex.org/W7151431891","doi":"https://doi.org/10.48550/arxiv.2604.04108"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.04108","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.04108","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,"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"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2604.04108","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5133110055","display_name":"Peixin Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Peixin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133085553","display_name":"Guoxi Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Guoxi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133135720","display_name":"Jianwei Ma","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ma, Jianwei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5133076842","display_name":"Qing Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Qing","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":0.9501000046730042,"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":0.9501000046730042,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.00559999980032444,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.0052999998442828655,"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/leverage","display_name":"Leverage (statistics)","score":0.6844000220298767},{"id":"https://openalex.org/keywords/knowledge-graph","display_name":"Knowledge graph","score":0.5550000071525574},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.550599992275238},{"id":"https://openalex.org/keywords/embodied-cognition","display_name":"Embodied cognition","score":0.5375000238418579},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5005999803543091},{"id":"https://openalex.org/keywords/cascade","display_name":"Cascade","score":0.4641000032424927},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.3790000081062317},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.3653999865055084}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7651000022888184},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6844000220298767},{"id":"https://openalex.org/C2987255567","wikidata":"https://www.wikidata.org/wiki/Q33002955","display_name":"Knowledge graph","level":2,"score":0.5550000071525574},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.550599992275238},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.5375000238418579},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5277000069618225},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5005999803543091},{"id":"https://openalex.org/C34146451","wikidata":"https://www.wikidata.org/wiki/Q5048094","display_name":"Cascade","level":2,"score":0.4641000032424927},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4097000062465668},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.3790000081062317},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37389999628067017},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.3653999865055084},{"id":"https://openalex.org/C197914299","wikidata":"https://www.wikidata.org/wiki/Q18650","display_name":"Semantic memory","level":3,"score":0.3407000005245209},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3327000141143799},{"id":"https://openalex.org/C2779458634","wikidata":"https://www.wikidata.org/wiki/Q24963715","display_name":"Debiasing","level":2,"score":0.3327000141143799},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.29760000109672546},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.28940001130104065},{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.28790000081062317},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.2870999872684479},{"id":"https://openalex.org/C27286358","wikidata":"https://www.wikidata.org/wiki/Q6031027","display_name":"Information cascade","level":2,"score":0.28679999709129333},{"id":"https://openalex.org/C87007009","wikidata":"https://www.wikidata.org/wiki/Q210832","display_name":"Statistical hypothesis testing","level":2,"score":0.2867000102996826},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.28610000014305115},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.28290000557899475},{"id":"https://openalex.org/C2776207758","wikidata":"https://www.wikidata.org/wiki/Q5303302","display_name":"Downstream (manufacturing)","level":2,"score":0.2734000086784363},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2596000134944916},{"id":"https://openalex.org/C2776650193","wikidata":"https://www.wikidata.org/wiki/Q264661","display_name":"Obstacle","level":2,"score":0.25780001282691956},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.2551000118255615}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.04108","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.04108","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,"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":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2604.04108","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.04108","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,"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"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Embodied":[0],"agents":[1],"must":[2],"explore":[3],"partially":[4],"observed":[5],"environments":[6],"while":[7,76],"maintaining":[8],"reliable":[9,170],"long-horizon":[10],"memory.":[11,105],"Existing":[12],"graph-based":[13],"navigation":[14,180],"systems":[15],"improve":[16],"scalability,":[17],"but":[18],"they":[19],"often":[20],"treat":[21],"unexplored":[22],"regions":[23,225],"as":[24,97],"semantically":[25],"unknown,":[26],"leading":[27],"to":[28,162,223],"inefficient":[29],"frontier":[30,38,95],"search.":[31],"Although":[32],"vision-language":[33],"models":[34],"(VLMs)":[35],"can":[36,69],"predict":[37],"semantics,":[39],"erroneous":[40,166,224],"predictions":[41,72,96],"may":[42],"be":[43],"embedded":[44],"into":[45],"memory":[46,169],"and":[47,119,128,130,182,193,198,220,230],"propagate":[48],"through":[49],"downstream":[50,153],"inferences,":[51],"causing":[52],"structural":[53],"error":[54],"accumulation":[55],"that":[56,68,93,209],"confidence":[57],"attenuation":[58],"alone":[59],"cannot":[60],"resolve.":[61],"These":[62],"observations":[63,138],"call":[64],"for":[65,73,234],"a":[66,91,102],"framework":[67,92],"leverage":[70],"semantic":[71,109,115],"directed":[74],"exploration":[75,121],"systematically":[77],"retracting":[78],"errors":[79],"once":[80],"new":[81],"evidence":[82],"contradicts":[83],"them.":[84],"We":[85,174],"propose":[86],"Hypothesis":[87],"Graph":[88],"Refinement":[89],"(HGR),":[90],"represents":[94],"revisable":[98],"hypothesis":[99,110,218],"nodes":[100,219],"in":[101],"dependency-aware":[103],"graph":[104,161],"HGR":[106,176,188],"introduces":[107],"(1)":[108],"module,":[111],"which":[112,135],"estimates":[113],"context-conditioned":[114],"distributions":[116],"over":[117],"frontiers":[118],"ranks":[120],"targets":[122],"by":[123,164,226],"goal":[124],"relevance,":[125],"travel":[126],"cost,":[127],"uncertainty,":[129],"(2)":[131],"verification-driven":[132],"cascade":[133,210],"correction,":[134],"compares":[136],"on-site":[137],"against":[139],"predicted":[140],"semantics":[141],"and,":[142],"upon":[143],"mismatch,":[144],"retracts":[145],"the":[146,160],"refuted":[147],"node":[148],"together":[149],"with":[150,228],"all":[151],"its":[152],"dependents.":[154],"Unlike":[155],"additive":[156],"map-building,":[157],"this":[158],"allows":[159],"contract":[163],"pruning":[165],"subgraphs,":[167],"keeping":[168],"throughout":[171],"long":[172],"episodes.":[173],"evaluate":[175],"on":[177,196,202],"multimodal":[178],"lifelong":[179],"(GOAT-Bench)":[181],"embodied":[183],"question":[184],"answering":[185],"(A-EQA,":[186],"EM-EQA).":[187],"achieves":[189],"72.41%":[190],"success":[191],"rate":[192],"56.22%":[194],"SPL":[195],"GOAT-Bench,":[197],"shows":[199],"consistent":[200],"improvements":[201],"both":[203],"QA":[204],"benchmarks.":[205],"Diagnostic":[206],"analysis":[207],"reveals":[208],"correction":[211],"eliminates":[212],"approximately":[213],"20%":[214],"of":[215,236],"structurally":[216],"redundant":[217],"reduces":[221],"revisits":[222],"4.5x,":[227],"specular":[229],"transparent":[231],"surfaces":[232],"accounting":[233],"67%":[235],"corrected":[237],"prediction":[238],"errors.":[239]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-04-08T00:00:00"}