{"id":"https://openalex.org/W7225273621","doi":"https://doi.org/10.48550/arxiv.2611.04142","title":"Interpretable Early Termination of Web Navigation Agents via Closed Sequential Pattern Mining","display_name":"Interpretable Early Termination of Web Navigation Agents via Closed Sequential Pattern Mining","publication_year":2026,"publication_date":"2026-11-03","ids":{"openalex":"https://openalex.org/W7225273621","doi":"https://doi.org/10.48550/arxiv.2611.04142"},"language":"en","primary_location":{"id":"doi:10.48550/arxiv.2611.04142","doi":"https://doi.org/10.48550/arxiv.2611.04142","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2611.04142","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-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"volume":null,"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2611.04142","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5119450558","display_name":"Sergio Talavera","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Talavera, Sergio","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5083435293","display_name":"Magdalini Eirinaki","orcid":"https://orcid.org/0000-0002-4711-3366","observed_orcids":["https://orcid.org/0000-0002-4711-3366"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Eirinaki, Magdalini","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/T12016","display_name":"Web Data Mining and Analysis","score":0.5414999723434448,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T12016","display_name":"Web Data Mining and Analysis","score":0.5414999723434448,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.2896000146865845,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.07930000126361847,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/early-termination","display_name":"early termination","score":0.9789999723434448},{"id":"https://openalex.org/keywords/fault-diagnosis","display_name":"fault diagnosis","score":0.7429999709129333},{"id":"https://openalex.org/keywords/failure-taxonomy","display_name":"failure taxonomy","score":0.7170000076293945},{"id":"https://openalex.org/keywords/repair-recommendations","display_name":"repair recommendations","score":0.8339999914169312},{"id":"https://openalex.org/keywords/explainable-ai","display_name":"explainable AI","score":0.6520000100135803},{"id":"https://openalex.org/keywords/token-cost-reduction","display_name":"token cost reduction","score":0.7170000076293945},{"id":"https://openalex.org/keywords/open-weight-language-models","display_name":"open-weight language models","score":0.746999979019165}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7354999780654907},{"id":"https://openalex.org/C141603448","wikidata":"https://www.wikidata.org/wiki/Q134830","display_name":"Prefix","level":2,"score":0.5558000206947327},{"id":"https://openalex.org/C149490388","wikidata":"https://www.wikidata.org/wiki/Q1718507","display_name":"Sequential Pattern Mining","level":2,"score":0.5152999758720398},{"id":"https://openalex.org/C2780385302","wikidata":"https://www.wikidata.org/wiki/Q367158","display_name":"Protocol (science)","level":3,"score":0.4498000144958496},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4097999930381775},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4088999927043915},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.3303000032901764},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.32440000772476196},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.30720001459121704},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2946000099182129},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2921000123023987},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.27410000562667847},{"id":"https://openalex.org/C58642233","wikidata":"https://www.wikidata.org/wiki/Q8269924","display_name":"Taxonomy (biology)","level":2,"score":0.2736999988555908},{"id":"https://openalex.org/C133112747","wikidata":"https://www.wikidata.org/wiki/Q7251931","display_name":"Protocol analysis","level":2,"score":0.2671000063419342},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.2623000144958496},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2583000063896179},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.2574999928474426},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.25130000710487366}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2611.04142","doi":"https://doi.org/10.48550/arxiv.2611.04142","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2611.04142","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-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2611.04142","doi":"https://doi.org/10.48550/arxiv.2611.04142","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2611.04142","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-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7171973064","https://openalex.org/W7207543213","https://openalex.org/W7165635847","https://openalex.org/W7215865273","https://openalex.org/W4417080754","https://openalex.org/W7160625789","https://openalex.org/W7223071094","https://openalex.org/W7171681756","https://openalex.org/W4414975410","https://openalex.org/W7160896442"],"abstract_inverted_index":{"Web":[0],"navigation":[1],"agents":[2],"built":[3],"on":[4,121,137],"open-weight":[5,128],"language":[6,129],"models":[7],"fail":[8,11],"often":[9],"and":[10,100,153],"late,":[12],"with":[13,83],"most":[14],"of":[15,65,147,161],"the":[16,20,132,138],"tokens":[17,162],"spent":[18],"after":[19],"trajectory":[21],"has":[22,27],"become":[23],"unrecoverable.":[24],"Recent":[25],"work":[26,54],"shown":[28],"that":[29,44,76,93,106,158],"early":[30],"termination":[31,42],"is":[32],"a":[33,71,79,89],"viable":[34],"cost-reduction":[35],"strategy,":[36],"but":[37],"existing":[38],"approaches":[39],"produce":[40,70],"opaque":[41],"decisions":[43],"do":[45],"not":[46],"support":[47],"diagnosis":[48],"or":[49],"human":[50],"oversight.":[51],"In":[52],"this":[53],"we":[55],"apply":[56],"closed":[57],"sequential":[58],"pattern":[59],"mining":[60],"(BIDE+)":[61],"to":[62,69],"K-step":[63],"prefixes":[64],"agent":[66],"execution":[67],"traces":[68,124],"small,":[72],"human-reviewable":[73],"failure-signature":[74],"library":[75],"organizes":[77],"into":[78],"four-category":[80],"failure":[81],"taxonomy":[82],"associated":[84],"repair":[85],"recommendations.":[86],"We":[87,117],"use":[88],"multi-variant":[90],"evaluation":[91],"protocol":[92],"explicitly":[94],"removes":[95],"contamination":[96],"artifacts":[97],"(zero-step":[98],"crashes":[99],"trivially":[101],"separable":[102],"single-step":[103],"successes)":[104],"so":[105],"reported":[107],"detection":[108],"accuracy":[109],"reflects":[110],"behavioral":[111],"discrimination":[112],"rather":[113],"than":[114],"trace-length":[115],"distributions.":[116],"evaluate":[118],"our":[119],"methodology":[120],"1,544":[122],"MiniWoB++":[123],"collected":[125],"from":[126],"three":[127,151],"models,":[130],"achieving":[131],"best":[133],"F1":[134],"at":[135,163],"K=3":[136],"Exclude-errors":[139],"configuration":[140],"across":[141],"eight":[142],"methods":[143],"(0.717),":[144],"recovering":[145],"88%":[146],"test-set":[148],"failures":[149],"within":[150],"steps,":[152],"supporting":[154],"an":[155],"early-termination":[156],"policy":[157],"saves":[159],"26.3%":[160],"92%":[164],"precision.":[165]},"counts_by_year":[],"updated_date":"2026-11-06T12:05:46.655746","created_date":"2026-11-05T00:00:00"}