{"id":"https://openalex.org/W7204165768","doi":"https://doi.org/10.48550/arxiv.2608.22331","title":"Noise Floor Audit for Agent Benchmarks","display_name":"Noise Floor Audit for Agent Benchmarks","publication_year":2026,"publication_date":"2026-08-23","ids":{"openalex":"https://openalex.org/W7204165768","doi":"https://doi.org/10.48550/arxiv.2608.22331"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.22331","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.22331","pdf_url":"https://arxiv.org/pdf/2608.22331","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/2608.22331","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139237114","display_name":"Yihang Chen","orcid":"https://orcid.org/0009-0000-3322-4471","observed_orcids":["https://orcid.org/0009-0000-3322-4471"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Yihang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136194164","display_name":"Pin Qian","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qian, Pin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5141090255","display_name":"Su Wang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Su","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5143865114","display_name":"Chong Peng","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peng, Chong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5147617834","display_name":"Huan Xu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Huan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148165514","display_name":"Xiyang Wu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Xiyang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5147563718","display_name":"Yiqi Sun","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sun, Yiqi","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":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/T10181","display_name":"Natural Language Processing Techniques","score":0.2667999863624573,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.2667999863624573,"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/T10028","display_name":"Topic Modeling","score":0.1234000027179718,"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/T12127","display_name":"Software System Performance and Reliability","score":0.11400000005960464,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/tool-calling","display_name":"tool calling","score":0.4490000009536743},{"id":"https://openalex.org/keywords/measurement-variability","display_name":"measurement variability","score":0.5870000123977661},{"id":"https://openalex.org/keywords/noise-floor","display_name":"noise floor","score":0.8500000238418579},{"id":"https://openalex.org/keywords/prompt-perturbation","display_name":"prompt perturbation","score":0.7239999771118164},{"id":"https://openalex.org/keywords/failure-modes","display_name":"failure modes","score":0.5809999704360962},{"id":"https://openalex.org/keywords/groq","display_name":"Groq","score":0.5400000214576721},{"id":"https://openalex.org/keywords/gemini","display_name":"Gemini","score":0.9440000057220459},{"id":"https://openalex.org/keywords/llm-based-agents","display_name":"LLM agents","score":0.3580000102519989}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5720999836921692},{"id":"https://openalex.org/C199521495","wikidata":"https://www.wikidata.org/wiki/Q181487","display_name":"Audit","level":2,"score":0.5559999942779541},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5358999967575073},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.43149998784065247},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.42750000953674316},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.37790000438690186},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.3774000108242035},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.3305000066757202},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.29980000853538513},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.298799991607666},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2904999852180481},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2856999933719635},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2678000032901764},{"id":"https://openalex.org/C163164238","wikidata":"https://www.wikidata.org/wiki/Q2737027","display_name":"Failure rate","level":2,"score":0.2612999975681305},{"id":"https://openalex.org/C187612029","wikidata":"https://www.wikidata.org/wiki/Q17083130","display_name":"Noise floor","level":4,"score":0.25839999318122864}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.22331","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.22331","pdf_url":"https://arxiv.org/pdf/2608.22331","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.2608.22331","doi":"https://doi.org/10.48550/arxiv.2608.22331","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.22331","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:2608.22331","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.22331","pdf_url":"https://arxiv.org/pdf/2608.22331","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/W7204165768.pdf","grobid_xml":"https://content.openalex.org/works/W7204165768.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7167621924","https://openalex.org/W7221584959","https://openalex.org/W7208745310","https://openalex.org/W7161723152","https://openalex.org/W7222906163","https://openalex.org/W7214756950","https://openalex.org/W7123695262","https://openalex.org/W7123843187","https://openalex.org/W7170897004","https://openalex.org/W7204251673"],"abstract_inverted_index":{"We":[0],"audit":[1],"measurement":[2],"variability":[3],"for":[4,86],"3":[5],"native":[6],"tool-calling":[7],"endpoints":[8,33],"across":[9,31],"2":[10],"providers":[11],"on":[12,62],"the":[13,59],"official":[14],"BFCL":[15],"multiple":[16],"and":[17,34,44,53,89],"parallel":[18],"categories,":[19],"using":[20],"matched":[21],"AST":[22],"grading.":[23],"At":[24],"temperature":[25],"0,":[26],"reruns":[27],"are":[28,41],"nearly":[29],"deterministic":[30],"Groq":[32],"a":[35],"thinking-enabled":[36],"Gemini":[37],"setting:":[38],"ever-flip":[39],"fractions":[40],"0.7%,":[42],"2.0%,":[43],"2.7%,":[45],"with":[46,65],"mean":[47],"run":[48],"correlations":[49],"of":[50,91],"0.997,":[51],"0.966,":[52],"0.961.":[54],"Semantics-preserving":[55],"prompt":[56],"perturbations":[57],"create":[58],"larger":[60,73],"floor":[61],"all":[63],"endpoints,":[64],"median":[66],"perturbation":[67],"paired":[68,76],"SDs":[69],"11x":[70],"to":[71],"58x":[72],"than":[74],"rerun":[75],"SDs.":[77],"The":[78],"failure":[79,103],"character":[80],"also":[81,102],"shifts:":[82],"malformed-output":[83],"failures":[84],"account":[85],"30%,":[87],"7%,":[88],"<1%":[90],"task":[92],"failures,":[93],"so":[94],"marginal":[95],"accuracy":[96],"hides":[97],"not":[98],"only":[99],"stability":[100],"but":[101],"mode.":[104]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-08-26T00:00:00"}