{"id":"https://openalex.org/W7224133015","doi":"https://doi.org/10.48550/arxiv.2610.36947","title":"Beyond QASecClaw: Agent Scaling, Verifier Feedback, and Evidence Reliability in Software Assurance","display_name":"Beyond QASecClaw: Agent Scaling, Verifier Feedback, and Evidence Reliability in Software Assurance","publication_year":2026,"publication_date":"2026-10-27","ids":{"openalex":"https://openalex.org/W7224133015","doi":"https://doi.org/10.48550/arxiv.2610.36947"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.36947","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.36947","pdf_url":"https://arxiv.org/pdf/2610.36947","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2610.36947","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5160050761","display_name":"S M Abdulla Al Mamun","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mamun, S M Abdulla Al","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063245603","display_name":"Akif Islam","orcid":"https://orcid.org/0009-0004-2755-7316","observed_orcids":["https://orcid.org/0009-0004-2755-7316"]},"institutions":[{"id":"https://openalex.org/I902853133","display_name":"University of Rajshahi","ror":"https://ror.org/05nnyr510","country_code":"BD","type":"education","lineage":["https://openalex.org/I902853133"]}],"countries":["BD"],"is_corresponding":false,"raw_author_name":"Islam, Akif","raw_affiliation_strings":["Department of Computer Science and Engineering , University of Rajshahi , Bangladesh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering , University of Rajshahi , Bangladesh","institution_ids":["https://openalex.org/I902853133"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072932207","display_name":"Mohd Ruhul Ameen","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ameen, Mohd. Ruhul","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.9535999894142151,"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"}},"topics":[{"id":"https://openalex.org/T10743","display_name":"Software Testing and Debugging Techniques","score":0.9535999894142151,"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/T10260","display_name":"Software Engineering Research","score":0.018400000408291817,"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/T10142","display_name":"Formal Methods in Verification","score":0.0071000000461936,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/software-assurance","display_name":"software assurance","score":0.8330000042915344},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.7059999704360962},{"id":"https://openalex.org/keywords/reliability-of-evidence","display_name":"reliability of evidence","score":0.628000020980835},{"id":"https://openalex.org/keywords/context-length","display_name":"context length","score":0.4309999942779541},{"id":"https://openalex.org/keywords/defects4j","display_name":"Defects4J","score":0.878000020980835},{"id":"https://openalex.org/keywords/sv-comp","display_name":"SV-COMP","score":0.828000009059906},{"id":"https://openalex.org/keywords/misleading-evidence","display_name":"misleading evidence","score":0.4309999942779541},{"id":"https://openalex.org/keywords/qwen2-5-coder","display_name":"Qwen2.5-Coder","score":0.7300000190734863}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6395000219345093},{"id":"https://openalex.org/C40422974","wikidata":"https://www.wikidata.org/wiki/Q741248","display_name":"Assertion","level":2,"score":0.5375000238418579},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5220999717712402},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.4546999931335449},{"id":"https://openalex.org/C1009929","wikidata":"https://www.wikidata.org/wiki/Q179550","display_name":"Software bug","level":3,"score":0.43050000071525574},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.41909998655319214},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4027999937534332},{"id":"https://openalex.org/C2778012447","wikidata":"https://www.wikidata.org/wiki/Q1034415","display_name":"Scope (computer science)","level":2,"score":0.3935999870300293},{"id":"https://openalex.org/C2776969324","wikidata":"https://www.wikidata.org/wiki/Q613918","display_name":"Software quality assurance","level":5,"score":0.3894999921321869},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.3725999891757965},{"id":"https://openalex.org/C135945739","wikidata":"https://www.wikidata.org/wiki/Q1211457","display_name":"Software release life cycle","level":5,"score":0.3617999851703644},{"id":"https://openalex.org/C117447612","wikidata":"https://www.wikidata.org/wiki/Q1412670","display_name":"Software quality","level":4,"score":0.3614000082015991},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.34439998865127563},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.32580000162124634},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.31380000710487366},{"id":"https://openalex.org/C128942645","wikidata":"https://www.wikidata.org/wiki/Q1568346","display_name":"Test case","level":3,"score":0.3068000078201294},{"id":"https://openalex.org/C168065819","wikidata":"https://www.wikidata.org/wiki/Q845566","display_name":"Debugging","level":2,"score":0.30309998989105225},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.2791000008583069},{"id":"https://openalex.org/C42475967","wikidata":"https://www.wikidata.org/wiki/Q194292","display_name":"Operations research","level":1,"score":0.27230000495910645},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.27070000767707825},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.2703000009059906},{"id":"https://openalex.org/C166052673","wikidata":"https://www.wikidata.org/wiki/Q83021","display_name":"Empirical evidence","level":2,"score":0.2651999890804291},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.26260000467300415}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.36947","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.36947","pdf_url":"https://arxiv.org/pdf/2610.36947","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2610.36947","doi":"https://doi.org/10.48550/arxiv.2610.36947","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.36947","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:2610.36947","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.36947","pdf_url":"https://arxiv.org/pdf/2610.36947","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":"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/W7224133015.pdf","grobid_xml":"https://content.openalex.org/works/W7224133015.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7203446082","https://openalex.org/W133688045","https://openalex.org/W7161819278","https://openalex.org/W7214624296","https://openalex.org/W7169838041","https://openalex.org/W7204023260","https://openalex.org/W7140216759","https://openalex.org/W7117506882","https://openalex.org/W7167411612","https://openalex.org/W7172134659"],"abstract_inverted_index":{"Can":[0],"additional":[1],"specialist":[2],"language-model":[3],"contexts":[4],"improve":[5],"software":[6],"assurance":[7],"when":[8],"deterministic":[9,172],"tool":[10],"evidence":[11,39,137,173],"is":[12,156],"already":[13],"available?":[14],"We":[15],"study":[16],"this":[17],"question":[18],"through":[19],"five":[20],"experiments":[21],"spanning":[22],"authored":[23],"Java":[24],"warning":[25],"controls,":[26],"OWASP":[27,79],"Benchmark":[28],"assessment,":[29],"Defects4J":[30,160],"test":[31,166],"generation,":[32],"SV-COMP":[33,97],"assertion":[34],"verdicts,":[35],"and":[36,51,128,187],"deliberately":[37],"misleading":[38],"packages.":[40],"The":[41],"evaluated":[42],"systems":[43],"use":[44,71],"Qwen2.5-Coder-7B-Instruct,":[45],"with":[46],"a":[47,120],"1.5B":[48],"sensitivity":[49],"analysis,":[50],"complete":[52],"13,638":[53],"model":[54,81,105],"requests.":[55],"On":[56,77,95,132],"eight":[57],"related":[58],"development":[59],"warnings,":[60],"increasing":[61],"the":[62,88,165,176,188],"context":[63],"count":[64],"from":[65,107,116],"1":[66],"to":[67,109,118],"50":[68],"increases":[69],"token":[70],"49-fold":[72],"without":[73],"improving":[74],"unsafe":[75],"clearance.":[76],"160":[78],"cases,":[80],"configurations":[82],"trade":[83],"clearance":[84],"against":[85],"unresolved":[86,130],"outcomes;":[87],"ten-context":[89],"arm":[90],"assesses":[91],"only":[92],"96":[93],"cases.":[94],"32":[96],"tasks,":[98],"raw":[99],"verifier":[100],"feedback":[101,185],"raises":[102,113],"mean":[103],"correct":[104,126],"verdicts":[106,115,127],"12.7":[108],"22.0,":[110],"but":[111],"also":[112],"incorrect":[114],"one":[117,162],"seven;":[119],"JBMC-plus-JVM":[121],"validation":[122],"baseline":[123],"returns":[124],"26":[125],"six":[129],"outcomes.":[131],"two":[133],"sets":[134],"of":[135,142,182],"120":[136],"packages,":[138],"models":[139],"reject":[140],"70-100%":[141],"applicable":[143],"counterexamples,":[144],"while":[145,179],"construction-specific":[146],"scope":[147],"checks":[148],"classify":[149],"every":[150],"package":[151],"correctly.":[152],"No":[153],"target":[154],"defect":[155],"discovered":[157],"in":[158],"three":[159],"bugs,":[161],"unsupported":[163],"by":[164],"adapter.":[167],"These":[168],"descriptive":[169],"results":[170],"support":[171],"admission":[174],"for":[175],"tested":[177],"settings,":[178],"exposing":[180],"limits":[181],"verdict":[183],"aggregation,":[184],"interpretation,":[186],"available":[189],"evaluation":[190],"coverage.":[191]},"counts_by_year":[],"updated_date":"2026-10-31T12:09:11.096373","created_date":"2026-10-29T00:00:00"}
