{"id":"https://openalex.org/W7204209332","doi":"https://doi.org/10.48550/arxiv.2608.23179","title":"NetConfArena: An Executable Benchmark for LLM Agents in Closed-Loop Network Configuration","display_name":"NetConfArena: An Executable Benchmark for LLM Agents in Closed-Loop Network Configuration","publication_year":2026,"publication_date":"2026-08-24","ids":{"openalex":"https://openalex.org/W7204209332","doi":"https://doi.org/10.48550/arxiv.2608.23179"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.23179","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.23179","pdf_url":"https://arxiv.org/pdf/2608.23179","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","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.23179","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5148099814","display_name":"Chang Liu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liu, Chang","raw_affiliation_strings":["Department of Computer Science and Technology , Tsinghua University , Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology , Tsinghua University , Beijing , China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148169076","display_name":"Xiaohui Xie","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xie, Xiaohui","raw_affiliation_strings":["Department of Computer Science and Technology , Tsinghua University , Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology , Tsinghua University , Beijing , China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115911624","display_name":"Xinyi Chen","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen, Xinyi","raw_affiliation_strings":["Department of Computer Science and Technology , Tsinghua University , Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology , Tsinghua University , Beijing , China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5126127823","display_name":"Yong Cui","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cui, Yong","raw_affiliation_strings":["Department of Computer Science and Technology , Tsinghua University , Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology , Tsinghua University , Beijing , China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I99065089"],"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/T10714","display_name":"Software-Defined Networks and 5G","score":0.8198000192642212,"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/T10714","display_name":"Software-Defined Networks and 5G","score":0.8198000192642212,"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":0.11320000141859055,"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/T12127","display_name":"Software System Performance and Reliability","score":0.005799999926239252,"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/llm-based-agents","display_name":"LLM agents","score":0.859000027179718},{"id":"https://openalex.org/keywords/network-configuration","display_name":"network configuration","score":0.8450000286102295},{"id":"https://openalex.org/keywords/netconf","display_name":"NETCONF","score":0.7160000205039978},{"id":"https://openalex.org/keywords/benchmarking","display_name":"benchmarking","score":0.7129999995231628},{"id":"https://openalex.org/keywords/network-emulation","display_name":"network emulation","score":0.6439999938011169},{"id":"https://openalex.org/keywords/task-templates","display_name":"task templates","score":0.6779999732971191},{"id":"https://openalex.org/keywords/network-topology","display_name":"network topology","score":0.4180000126361847},{"id":"https://openalex.org/keywords/agent-evaluation","display_name":"agent evaluation","score":0.3700000047683716}],"concepts":[{"id":"https://openalex.org/C160145156","wikidata":"https://www.wikidata.org/wiki/Q778586","display_name":"Executable","level":2,"score":0.9190000295639038},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.781499981880188},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7675999999046326},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.7032999992370605},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6115999817848206},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5763999819755554},{"id":"https://openalex.org/C2780385302","wikidata":"https://www.wikidata.org/wiki/Q367158","display_name":"Protocol (science)","level":3,"score":0.41909998655319214},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.4140999913215637},{"id":"https://openalex.org/C199845137","wikidata":"https://www.wikidata.org/wiki/Q145490","display_name":"Network topology","level":2,"score":0.4129999876022339},{"id":"https://openalex.org/C165464430","wikidata":"https://www.wikidata.org/wiki/Q1570441","display_name":"Parameterized complexity","level":2,"score":0.34689998626708984},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.3109000027179718},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.29789999127388},{"id":"https://openalex.org/C139940560","wikidata":"https://www.wikidata.org/wiki/Q290036","display_name":"Network simulation","level":2,"score":0.29409998655319214},{"id":"https://openalex.org/C2779173999","wikidata":"https://www.wikidata.org/wiki/Q680296","display_name":"Network administrator","level":2,"score":0.28519999980926514},{"id":"https://openalex.org/C168065819","wikidata":"https://www.wikidata.org/wiki/Q845566","display_name":"Debugging","level":2,"score":0.2851000130176544},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.2775999903678894},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2750999927520752},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.2680000066757202},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2590000033378601},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2565999925136566},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.2556000053882599},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2538999915122986},{"id":"https://openalex.org/C193415008","wikidata":"https://www.wikidata.org/wiki/Q639681","display_name":"Network architecture","level":2,"score":0.2526000142097473}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.23179","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.23179","pdf_url":"https://arxiv.org/pdf/2608.23179","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.2608.23179","doi":"https://doi.org/10.48550/arxiv.2608.23179","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.23179","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:2608.23179","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.23179","pdf_url":"https://arxiv.org/pdf/2608.23179","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":[{"id":"https://openalex.org/G7033924410","display_name":null,"funder_award_id":"62132009","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7488493096","display_name":null,"funder_award_id":"62221003","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204209332.pdf","grobid_xml":"https://content.openalex.org/works/W7204209332.grobid-xml"},"referenced_works_count":4,"referenced_works":["https://openalex.org/W4385963839","https://openalex.org/W4404652946","https://openalex.org/W4407806682","https://openalex.org/W4416873402"],"related_works":["https://openalex.org/W7154540637","https://openalex.org/W4417530091","https://openalex.org/W7166144042","https://openalex.org/W4410461489","https://openalex.org/W4399629579","https://openalex.org/W4413358480","https://openalex.org/W7140201360","https://openalex.org/W7171531882","https://openalex.org/W4416927413","https://openalex.org/W7169863657"],"abstract_inverted_index":{"Large":[0],"language":[1],"model":[2],"(LLM)":[3],"agents":[4,28,82,89,138],"are":[5,18,157],"increasingly":[6],"attractive":[7],"for":[8,79,101],"automating":[9],"network":[10,61,85,108,127],"configuration,":[11,62],"yet":[12],"their":[13],"reliability":[14],"and":[15,70,97,104,153,171,174,192,202],"failure":[16],"patterns":[17],"poorly":[19],"understood.":[20],"An":[21],"essential":[22],"prerequisite":[23],"is":[24],"to":[25,160,188],"assess":[26],"such":[27],"in":[29,83,90,168],"a":[30,95],"realistic":[31],"but":[32],"risk-free":[33],"environment.":[34],"Existing":[35],"benchmarks,":[36],"however,":[37],"fall":[38],"short:":[39],"they":[40],"often":[41],"treat":[42],"configuration":[43],"as":[44,185],"static":[45],"command":[46,161],"generation":[47],"or":[48],"rely":[49],"on":[50,119,139],"overly":[51],"simplified":[52],"settings.":[53],"Such":[54],"evaluations":[55],"understate":[56],"the":[57,106],"core":[58],"challenges":[59],"of":[60],"where":[63],"correctness":[64],"requires":[65],"reasoning":[66],"about":[67],"protocol":[68],"complexity":[69],"topology":[71],"dependence.":[72],"We":[73,134],"present":[74],"NetConfArena,":[75],"an":[76,120],"executable":[77,113],"benchmark":[78,117],"evaluating":[80],"LLM":[81,137],"closed-loop":[84],"configuration.":[86],"NetConfArena":[87],"places":[88],"emulated":[91],"multi-device":[92],"networks,":[93],"provides":[94],"standardized":[96],"compact":[98],"action":[99],"interface":[100],"task":[102,132,141,147],"execution,":[103],"evaluates":[105],"resulting":[107],"behavior":[109],"with":[110],"hidden":[111],"task-specific":[112],"test":[114],"cases.":[115],"The":[116,163],"relies":[118],"LLM-assisted,":[121],"emulation-grounded":[122],"pipeline,":[123],"which":[124],"converts":[125],"human-oriented":[126],"materials":[128],"into":[129],"reusable":[130],"parameterized":[131],"templates.":[133],"evaluate":[135],"representative":[136],"480":[140],"instances":[142],"instantiated":[143],"from":[144],"96":[145],"protocol-focused":[146],"templates,":[148],"yielding":[149],"3840":[150],"execution":[151,199],"trajectories,":[152],"show":[154],"that":[155,196],"failures":[156,164],"not":[158],"limited":[159],"errors.":[162],"also":[165],"reveal":[166],"gaps":[167],"task-specification":[169],"adherence":[170],"robust":[172],"planning":[173],"execution.":[175],"These":[176],"findings":[177],"suggest":[178],"two":[179],"future":[180],"directions:":[181],"using":[182],"validated":[183],"trajectories":[184],"supervision":[186],"signals":[187],"improve":[189],"foundation":[190],"models,":[191],"designing":[193],"harness":[194],"mechanisms":[195],"make":[197],"agent":[198],"more":[200],"reliable":[201],"accountable.":[203]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-08-26T00:00:00"}
