{"id":"https://openalex.org/W7204566174","doi":"https://doi.org/10.48550/arxiv.2608.27021","title":"FaulT-Bench: Towards Benchmarking Network Troubleshooting LLM Agents under Unreliable User Tickets","display_name":"FaulT-Bench: Towards Benchmarking Network Troubleshooting LLM Agents under Unreliable User Tickets","publication_year":2026,"publication_date":"2026-08-27","ids":{"openalex":"https://openalex.org/W7204566174","doi":"https://doi.org/10.48550/arxiv.2608.27021"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.27021","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.27021","pdf_url":"https://arxiv.org/pdf/2608.27021","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","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.27021","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5053434559","display_name":"Kuan-Hao Tseng","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Tseng, Kuan-Hao","raw_affiliation_strings":["The University of Sydney Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Sydney Australia","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106326450","display_name":"Niruth Bogahawatta","orcid":"https://orcid.org/0009-0008-4859-7017","observed_orcids":["https://orcid.org/0009-0008-4859-7017"]},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Bogahawatta, Niruth","raw_affiliation_strings":["The University of Sydney Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Sydney Australia","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092681387","display_name":"Yasod Ginige","orcid":"https://orcid.org/0009-0004-0479-1767","observed_orcids":["https://orcid.org/0009-0004-0479-1767"]},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Ginige, Yasod","raw_affiliation_strings":["The University of Sydney Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Sydney Australia","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074668519","display_name":"Kunjan Patel","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Patel, Kunjan","raw_affiliation_strings":["The University of Sydney Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Sydney Australia","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057353421","display_name":"Kosta Dakic","orcid":"https://orcid.org/0000-0002-3078-7698","observed_orcids":["https://orcid.org/0000-0002-3078-7698"]},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Dakic, Kosta","raw_affiliation_strings":["The University of Sydney Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Sydney Australia","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038376039","display_name":"Suranga Seneviratne","orcid":"https://orcid.org/0000-0002-5485-5595","observed_orcids":["https://orcid.org/0000-0002-5485-5595"]},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Seneviratne, Suranga","raw_affiliation_strings":["The University of Sydney Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Sydney Australia","institution_ids":["https://openalex.org/I129604602"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I129604602"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"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/T12127","display_name":"Software System Performance and Reliability","score":0.6894999742507935,"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"}},"topics":[{"id":"https://openalex.org/T12127","display_name":"Software System Performance and Reliability","score":0.6894999742507935,"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"}},{"id":"https://openalex.org/T12203","display_name":"Mobile Agent-Based Network Management","score":0.11289999634027481,"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"}},{"id":"https://openalex.org/T10714","display_name":"Software-Defined Networks and 5G","score":0.05649999901652336,"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/network-troubleshooting","display_name":"network troubleshooting","score":0.8799999952316284},{"id":"https://openalex.org/keywords/llm-based-agents","display_name":"LLM agents","score":0.8679999709129333},{"id":"https://openalex.org/keywords/benchmarking","display_name":"benchmarking","score":0.8190000057220459},{"id":"https://openalex.org/keywords/root-cause-diagnosis","display_name":"root cause diagnosis","score":0.6570000052452087},{"id":"https://openalex.org/keywords/marquis-de-sade","display_name":"Marquis de Sade","score":0.6850000023841858},{"id":"https://openalex.org/keywords/react","display_name":"React","score":0.9509999752044678},{"id":"https://openalex.org/keywords/claude-code","display_name":"Claude Code","score":0.8799999952316284},{"id":"https://openalex.org/keywords/overdiagnosis","display_name":"overdiagnosis","score":0.6990000009536743},{"id":"https://openalex.org/keywords/network-fault-diagnosis","display_name":"network fault diagnosis","score":0.593999981880188}],"concepts":[{"id":"https://openalex.org/C147494362","wikidata":"https://www.wikidata.org/wiki/Q2078905","display_name":"Troubleshooting","level":2,"score":0.8389999866485596},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6985999941825867},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.6970999836921692},{"id":"https://openalex.org/C2776540713","wikidata":"https://www.wikidata.org/wiki/Q7800647","display_name":"Ticket","level":2,"score":0.6894000172615051},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5745000243186951},{"id":"https://openalex.org/C85847156","wikidata":"https://www.wikidata.org/wiki/Q59015987","display_name":"Verifiable secret sharing","level":3,"score":0.5145999789237976},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.39800000190734863},{"id":"https://openalex.org/C84945661","wikidata":"https://www.wikidata.org/wiki/Q7366567","display_name":"Root cause","level":2,"score":0.38100001215934753},{"id":"https://openalex.org/C175551986","wikidata":"https://www.wikidata.org/wiki/Q47089","display_name":"Fault (geology)","level":2,"score":0.3434000015258789},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.3418000042438507},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.3122999966144562},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.27790001034736633},{"id":"https://openalex.org/C171078966","wikidata":"https://www.wikidata.org/wiki/Q111029","display_name":"Root (linguistics)","level":2,"score":0.2662000060081482},{"id":"https://openalex.org/C66989864","wikidata":"https://www.wikidata.org/wiki/Q594646","display_name":"Paillier cryptosystem","level":5,"score":0.2644999921321869},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.26159998774528503},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.2547999918460846}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.27021","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.27021","pdf_url":"https://arxiv.org/pdf/2608.27021","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","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2608.27021","doi":"https://doi.org/10.48550/arxiv.2608.27021","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.27021","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","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2608.27021","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.27021","pdf_url":"https://arxiv.org/pdf/2608.27021","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","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204566174.pdf","grobid_xml":"https://content.openalex.org/works/W7204566174.grobid-xml"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W2824525340","https://openalex.org/W2997290241","https://openalex.org/W3034676189","https://openalex.org/W4233496684","https://openalex.org/W4384345635","https://openalex.org/W4388629193","https://openalex.org/W4388644518","https://openalex.org/W4389519254","https://openalex.org/W4390660070","https://openalex.org/W4399455192","https://openalex.org/W4399629579","https://openalex.org/W4402571865","https://openalex.org/W4413757586","https://openalex.org/W4416071408","https://openalex.org/W4417530091","https://openalex.org/W7152580979","https://openalex.org/W7160533132","https://openalex.org/W7202172648","https://openalex.org/W7202200222"],"related_works":["https://openalex.org/W4417530091","https://openalex.org/W7160533132","https://openalex.org/W7211994942","https://openalex.org/W7220994845","https://openalex.org/W7204209332","https://openalex.org/W7202392698","https://openalex.org/W7203713097","https://openalex.org/W7166700222","https://openalex.org/W4413358480","https://openalex.org/W7156796491"],"abstract_inverted_index":{"LLM-based":[0],"agents":[1,105,214],"are":[2,136],"increasingly":[3],"proposed":[4],"for":[5,235],"network":[6,41,93,150,250],"fault":[7,22,53],"diagnosis,":[8,68],"but":[9],"existing":[10],"benchmarks":[11],"evaluate":[12],"them":[13],"only":[14],"on":[15,138],"accurate":[16,139,202],"tickets":[17,74,140,247],"and":[18,58,83,112,123,129,141,153],"always":[19],"assume":[20],"a":[21,33,89,160,167,181,191,205,233],"is":[23,151,156,174,183,195],"present,":[24],"conditions":[25],"rarely":[26],"met":[27],"in":[28,102],"practice.":[29],"We":[30],"present":[31],"FaulT-Bench,":[32],"benchmark":[34,234],"of":[35,248],"200":[36],"troubleshooting":[37],"scenarios":[38],"across":[39,120],"eight":[40],"topologies,":[42],"five":[43,76],"reimplemented":[44],"from":[45,218],"public":[46],"practitioner":[47],"labs,":[48],"spanning":[49],"genuine":[50],"faults,":[51],"false":[52],"reports,":[54],"incorrect":[55,59],"device":[56],"attribution,":[57],"root-cause":[60],"claims.":[61],"To":[62],"isolate":[63],"how":[64,180],"ticket":[65,155,182],"wording":[66],"affects":[67],"we":[69,132],"further":[70],"rewrite":[71],"72":[72],"false-premise":[73],"into":[75],"reporter":[77,81],"personas":[78],"that":[79,179,239],"vary":[80],"confidence":[82],"verifiable":[84],"detail":[85],"one":[86],"factor":[87],"at":[88,224],"time,":[90],"holding":[91],"the":[92,108,149,154,244],"state":[94],"fixed.":[95],"Our":[96],"automated":[97],"harness":[98],"deploys":[99],"each":[100],"scenario":[101],"Kathar\u00e1,":[103],"lets":[104],"interact":[106],"through":[107],"NIKA":[109],"tool":[110],"interface,":[111],"scores":[113],"free-text":[114],"diagnoses":[115],"with":[116],"an":[117,201],"LLM":[118],"judge":[119],"outcome,":[121],"fix,":[122],"reasoning":[124],"quality.":[125],"Evaluating":[126],"SADE,":[127],"ReAct,":[128],"Claude":[130],"Code,":[131],"find":[133],"all":[134],"three":[135,213],"near-saturated":[137],"robust":[142],"to":[143,166,221],"misdirection,":[144],"yet":[145],"degrade":[146],"sharply":[147],"when":[148],"healthy":[152],"wrong,":[157],"probing":[158],"until":[159],"benign":[161],"condition":[162],"can":[163,240],"be":[164],"promoted":[165],"root":[168],"cause":[169],"rather":[170],"than":[171,187],"concluding":[172],"nothing":[173],"wrong.":[175],"Persona":[176],"rewrites":[177],"show":[178],"written":[184],"matters":[185],"more":[186],"what":[188],"it":[189],"claims:":[190],"confidently":[192],"wrong":[193],"report":[194,208],"handled":[196],"about":[197],"as":[198,200,232],"well":[199],"one,":[203],"while":[204],"vague,":[206],"underspecified":[207],"degrades":[209],"performance":[210],"sharply.":[211],"The":[212],"also":[215],"fail":[216],"differently,":[217],"constant":[219],"over-diagnosis":[220],"unanswered":[222],"runs,":[223],"very":[225],"different":[226],"cost.":[227],"These":[228],"results":[229],"position":[230],"FaulT-Bench":[231],"developing":[236],"agentic":[237],"systems":[238],"reason":[241],"reliably":[242],"over":[243],"noisy,":[245],"unreliable":[246],"real-world":[249],"troubleshooting.":[251]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-08-29T00:00:00"}
