{"id":"https://openalex.org/W7165024570","doi":"https://doi.org/10.48550/arxiv.2606.17871","title":"StepGuard: Guarding Web Navigation via Single-Step Calibration","display_name":"StepGuard: Guarding Web Navigation via Single-Step Calibration","publication_year":2026,"publication_date":"2026-06-16","ids":{"openalex":"https://openalex.org/W7165024570","doi":"https://doi.org/10.48550/arxiv.2606.17871"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.17871","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.17871","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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.2606.17871","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5003750914","display_name":"Zhihao Cui","orcid":"https://orcid.org/0009-0006-6025-6640"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cui, Zhihao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138787959","display_name":"Yuchen Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Yuchen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108881008","display_name":"Xiyang Sun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sun, Xiyang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138776670","display_name":"Yaxiong Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Yaxiong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005096654","display_name":"Lei Zhu","orcid":"https://orcid.org/0009-0003-3762-8344"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhu, Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107311606","display_name":"J Hu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hu, Jinpeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138811200","display_name":"Liu Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138773918","display_name":"Mengjia Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Mengjia","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5138820415","display_name":"Yujiao Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Yujiao","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":0.7875000238418579,"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":0.7875000238418579,"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/T10028","display_name":"Topic Modeling","score":0.11400000005960464,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.017999999225139618,"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/leverage","display_name":"Leverage (statistics)","score":0.5938000082969666},{"id":"https://openalex.org/keywords/reflection","display_name":"Reflection (computer programming)","score":0.44909998774528503},{"id":"https://openalex.org/keywords/calibration","display_name":"Calibration","score":0.40610000491142273},{"id":"https://openalex.org/keywords/turn-by-turn-navigation","display_name":"Turn-by-turn navigation","score":0.39559999108314514},{"id":"https://openalex.org/keywords/navigation-system","display_name":"Navigation system","score":0.39160001277923584},{"id":"https://openalex.org/keywords/web-navigation","display_name":"Web navigation","score":0.38519999384880066},{"id":"https://openalex.org/keywords/web-application","display_name":"Web application","score":0.36899998784065247}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7075999975204468},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5938000082969666},{"id":"https://openalex.org/C65682993","wikidata":"https://www.wikidata.org/wiki/Q1056451","display_name":"Reflection (computer programming)","level":2,"score":0.44909998774528503},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.40610000491142273},{"id":"https://openalex.org/C43472768","wikidata":"https://www.wikidata.org/wiki/Q7855620","display_name":"Turn-by-turn navigation","level":5,"score":0.39559999108314514},{"id":"https://openalex.org/C2777891301","wikidata":"https://www.wikidata.org/wiki/Q3475123","display_name":"Navigation system","level":2,"score":0.39160001277923584},{"id":"https://openalex.org/C61096286","wikidata":"https://www.wikidata.org/wiki/Q7978592","display_name":"Web navigation","level":3,"score":0.38519999384880066},{"id":"https://openalex.org/C118643609","wikidata":"https://www.wikidata.org/wiki/Q189210","display_name":"Web application","level":2,"score":0.36899998784065247},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.36320000886917114},{"id":"https://openalex.org/C48677424","wikidata":"https://www.wikidata.org/wiki/Q6888088","display_name":"Mode (computer interface)","level":2,"score":0.3630000054836273},{"id":"https://openalex.org/C80191262","wikidata":"https://www.wikidata.org/wiki/Q5477668","display_name":"Fragility","level":2,"score":0.35749998688697815},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.3513999879360199},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.31349998712539673},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.3010999858379364},{"id":"https://openalex.org/C103088060","wikidata":"https://www.wikidata.org/wiki/Q1062839","display_name":"Error detection and correction","level":2,"score":0.3000999987125397},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2831000089645386},{"id":"https://openalex.org/C35578498","wikidata":"https://www.wikidata.org/wiki/Q193424","display_name":"Web service","level":2,"score":0.2533000111579895}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.17871","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.17871","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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.2606.17871","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.17871","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":{"Web":[0,122],"navigation":[1,134,145],"requires":[2],"agents":[3],"to":[4,34,66,97,100],"follow":[5],"natural":[6],"language":[7],"goals,":[8],"interact":[9],"with":[10],"web":[11,144],"pages,":[12],"and":[13,23,37,60,93,135],"produce":[14],"accurate":[15],"answers.":[16],"While":[17],"recent":[18],"advances":[19],"leverage":[20],"vision-language":[21],"models":[22],"reinforcement":[24],"learning,":[25],"existing":[26],"methods":[27],"still":[28],"suffer":[29],"from":[30],"single-step":[31,73,103],"fragility":[32],"due":[33],"reward":[35,43,68],"misalignment":[36],"error":[38],"propagation.":[39],"To":[40,70],"tackle":[41],"the":[42,72,102,106,109],"entanglement,":[44],"we":[45,75,112],"design":[46],"Dynamic":[47],"Dual-Policy":[48],"Optimization":[49],"(DDPO),":[50],"which":[51],"dynamically":[52],"switches":[53],"between":[54],"a":[55,82,117],"navigation-first":[56],"mode":[57,63],"for":[58,64],"exploration":[59],"an":[61],"answer-first":[62],"question-answering":[65],"mitigate":[67],"conflict.":[69],"calibrate":[71,101],"error,":[74],"propose":[76],"Confidence-Guided":[77],"Adaptive":[78],"Navigation":[79,123],"Reflection":[80],"(CANR),":[81],"mechanism":[83],"that":[84,129],"estimates":[85],"per-step":[86],"confidence,":[87],"triggers":[88],"reflection":[89],"only":[90],"when":[91],"necessary,":[92],"uses":[94],"contrastive":[95],"rewards":[96],"encourage":[98],"self-correction":[99],"inaccuracy.":[104],"With":[105],"above":[107],"as":[108],"main":[110],"components,":[111],"finally":[113],"develop":[114],"our":[115,130],"StepGuard,":[116],"new":[118,139],"framework":[119],"of":[120],"Guarding":[121],"via":[124],"Single-Step":[125],"Calibration.":[126],"Experiments":[127],"demonstrate":[128],"approach":[131],"significantly":[132],"improves":[133],"answer":[136],"accuracy,":[137],"setting":[138],"state-of-the-art":[140],"performance":[141],"on":[142],"standard":[143],"benchmarks.":[146]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-18T00:00:00"}
