{"id":"https://openalex.org/W7133496313","doi":"https://doi.org/10.48550/arxiv.2603.02798","title":"Guideline-Grounded Evidence Accumulation for High-Stakes Agent Verification","display_name":"Guideline-Grounded Evidence Accumulation for High-Stakes Agent Verification","publication_year":2026,"publication_date":"2026-03-03","ids":{"openalex":"https://openalex.org/W7133496313","doi":"https://doi.org/10.48550/arxiv.2603.02798"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.02798","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.02798","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":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.02798","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5128111635","display_name":"Yichi Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Zhang, Yichi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067213867","display_name":"Nabeel Seedat","orcid":"https://orcid.org/0000-0002-2134-6639"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Seedat, Nabeel","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128056157","display_name":"Yinpeng Dong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dong, Yinpeng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128042312","display_name":"Peng Cui","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cui, Peng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128123658","display_name":"Jun Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhu, Jun","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5128098092","display_name":"Mihaela van de Schaar","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"van de Schaar, Mihaela","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5128111635"],"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/T13702","display_name":"Machine Learning in Healthcare","score":0.2718999981880188,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.2718999981880188,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.16009999811649323,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.11330000311136246,"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/correctness","display_name":"Correctness","score":0.8169999718666077},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.6022999882698059},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.5012999773025513},{"id":"https://openalex.org/keywords/trustworthiness","display_name":"Trustworthiness","score":0.5001999735832214},{"id":"https://openalex.org/keywords/guideline","display_name":"Guideline","score":0.47099998593330383},{"id":"https://openalex.org/keywords/domain-knowledge","display_name":"Domain knowledge","score":0.4361000061035156},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.4296000003814697}],"concepts":[{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.8169999718666077},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7247999906539917},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.6022999882698059},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.5012999773025513},{"id":"https://openalex.org/C153701036","wikidata":"https://www.wikidata.org/wiki/Q659974","display_name":"Trustworthiness","level":2,"score":0.5001999735832214},{"id":"https://openalex.org/C2780182762","wikidata":"https://www.wikidata.org/wiki/Q1630279","display_name":"Guideline","level":2,"score":0.47099998593330383},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.46619999408721924},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44839999079704285},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.44040000438690186},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.4361000061035156},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.4296000003814697},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.40799999237060547},{"id":"https://openalex.org/C93226319","wikidata":"https://www.wikidata.org/wiki/Q193137","display_name":"Differential (mechanical device)","level":2,"score":0.3711000084877014},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.33799999952316284},{"id":"https://openalex.org/C3018095205","wikidata":"https://www.wikidata.org/wiki/Q55641553","display_name":"Real world evidence","level":2,"score":0.3278999924659729},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.27730000019073486},{"id":"https://openalex.org/C105002631","wikidata":"https://www.wikidata.org/wiki/Q4833645","display_name":"Subject-matter expert","level":3,"score":0.25920000672340393},{"id":"https://openalex.org/C63002673","wikidata":"https://www.wikidata.org/wiki/Q2260590","display_name":"Scoring rule","level":2,"score":0.25679999589920044},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.2542000114917755},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.2535000145435333}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.02798","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.02798","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":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.02798","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.02798","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":"article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.5054866075515747},{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.4580865800380707}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"As":[0],"LLM-powered":[1],"agents":[2],"have":[3],"been":[4],"used":[5],"for":[6,107],"high-stakes":[7],"decision-making,":[8],"such":[9],"as":[10],"clinical":[11,124],"diagnosis,":[12],"it":[13],"becomes":[14],"critical":[15],"to":[16,23,33],"develop":[17],"reliable":[18],"verification":[19,50],"of":[20,36],"their":[21],"decisions":[22],"facilitate":[24],"trustworthy":[25],"deployment.":[26],"Yet,":[27],"existing":[28],"verifiers":[29],"usually":[30],"underperform":[31],"owing":[32],"a":[34],"lack":[35],"domain":[37,71],"knowledge":[38],"and":[39,73,86,114,141,154],"limited":[40],"calibration.":[41,155],"To":[42],"address":[43],"this,":[44],"we":[45],"establish":[46],"GLEAN,":[47],"an":[48],"agent":[49],"framework":[51],"with":[52,70,122,161],"Guideline-grounded":[53],"Evidence":[54],"Accumulation":[55],"that":[56],"compiles":[57],"expert-curated":[58],"protocols":[59],"into":[60,77,88],"trajectory-informed,":[61],"well-calibrated":[62],"correctness":[63,89],"signals.":[64],"GLEAN":[65,121],"evaluates":[66],"the":[67,84,96,130,134,149,158],"step-wise":[68],"alignment":[69],"guidelines":[72],"aggregates":[74],"multi-guideline":[75],"ratings":[76],"surrogate":[78],"features,":[79],"which":[80,102,147],"are":[81],"accumulated":[82],"along":[83],"trajectory":[85],"calibrated":[87],"probabilities":[90],"using":[91],"Bayesian":[92],"logistic":[93],"regression.":[94],"Moreover,":[95],"estimated":[97],"uncertainty":[98],"triggers":[99],"active":[100],"verification,":[101],"selectively":[103],"collects":[104],"additional":[105],"evidence":[106],"uncertain":[108],"cases":[109],"via":[110],"expanding":[111],"guideline":[112],"coverage":[113],"performing":[115],"differential":[116],"checks.":[117],"We":[118],"empirically":[119],"validate":[120],"agentic":[123],"diagnosis":[125],"across":[126],"three":[127],"diseases":[128],"from":[129],"MIMIC-IV":[131],"dataset,":[132],"surpassing":[133],"best":[135],"baseline":[136],"by":[137],"12%":[138],"in":[139,143,151,166],"AUROC":[140],"50%":[142],"Brier":[144],"score":[145],"reduction,":[146],"confirms":[148],"effectiveness":[150],"both":[152],"discrimination":[153],"In":[156],"addition,":[157],"expert":[159],"study":[160],"clinicians":[162],"recognizes":[163],"GLEAN's":[164],"utility":[165],"practice.":[167]},"counts_by_year":[],"updated_date":"2026-03-05T07:36:02.291473","created_date":"2026-03-05T00:00:00"}