{"id":"https://openalex.org/W7214219958","doi":"https://doi.org/10.48550/arxiv.2609.27571","title":"FDE-Bench: Evaluating LLM Agents for Deployment Environment Configuration","display_name":"FDE-Bench: Evaluating LLM Agents for Deployment Environment Configuration","publication_year":2026,"publication_date":"2026-09-23","ids":{"openalex":"https://openalex.org/W7214219958","doi":"https://doi.org/10.48550/arxiv.2609.27571"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.27571","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.27571","pdf_url":"https://arxiv.org/pdf/2609.27571","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/2609.27571","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5152512157","display_name":"Weihang Ding","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ding, Weihang","raw_affiliation_strings":["University of California , Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California , Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5152726635","display_name":"Junfei Zhan","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Zhan, Junfei","raw_affiliation_strings":["Imperial College London"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Imperial College London","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5152749323","display_name":"Yueting Li","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Li, Yueting","raw_affiliation_strings":["University of California , Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California , Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5152729229","display_name":"Qirong Guo","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]},{"id":"https://openalex.org/I4405261251","display_name":"The Hong Kong University of Science and Technology (Guangzhou)","ror":"https://ror.org/050h0vm43","country_code":"CN","type":"education","lineage":["https://openalex.org/I4405261251"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Guo, Qirong","raw_affiliation_strings":["The Hong Kong University of Science and Technology (Guangzhou"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology (Guangzhou","institution_ids":["https://openalex.org/I200769079","https://openalex.org/I4405261251"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":4,"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/T10260","display_name":"Software Engineering Research","score":0.5268999934196472,"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"}},"topics":[{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.5268999934196472,"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/T12127","display_name":"Software System Performance and Reliability","score":0.34769999980926514,"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/T10430","display_name":"Software Engineering Techniques and Practices","score":0.0494999997317791,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/llm-based-agents","display_name":"LLM agents","score":0.9210000038146973},{"id":"https://openalex.org/keywords/benchmarking","display_name":"benchmarking","score":0.421999990940094},{"id":"https://openalex.org/keywords/docker-image","display_name":"Docker image","score":0.6399999856948853},{"id":"https://openalex.org/keywords/kubernetes","display_name":"Kubernetes","score":0.6840000152587891},{"id":"https://openalex.org/keywords/service-readiness","display_name":"service readiness","score":0.5870000123977661},{"id":"https://openalex.org/keywords/adversarial-evaluation","display_name":"adversarial evaluation","score":0.5040000081062317}],"concepts":[{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.8824999928474426},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6657000184059143},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.515500009059906},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.44110000133514404},{"id":"https://openalex.org/C45340560","wikidata":"https://www.wikidata.org/wiki/Q215382","display_name":"Disjoint sets","level":2,"score":0.397599995136261},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.3935000002384186},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.3409000039100647},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.3352999985218048},{"id":"https://openalex.org/C81293917","wikidata":"https://www.wikidata.org/wiki/Q4189534","display_name":"System deployment","level":3,"score":0.3271999955177307},{"id":"https://openalex.org/C2777286243","wikidata":"https://www.wikidata.org/wiki/Q5591926","display_name":"Grading (engineering)","level":2,"score":0.31610000133514404},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.29899999499320984},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.2962999939918518},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.2856000065803528},{"id":"https://openalex.org/C2985126265","wikidata":"https://www.wikidata.org/wiki/Q1637368","display_name":"Task group","level":2,"score":0.27559998631477356},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.26589998602867126},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.2628999948501587},{"id":"https://openalex.org/C2776004034","wikidata":"https://www.wikidata.org/wiki/Q1068755","display_name":"Check-in","level":2,"score":0.2508000135421753}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.27571","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.27571","pdf_url":"https://arxiv.org/pdf/2609.27571","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.2609.27571","doi":"https://doi.org/10.48550/arxiv.2609.27571","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.27571","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:2609.27571","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.27571","pdf_url":"https://arxiv.org/pdf/2609.27571","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/W7214219958.pdf","grobid_xml":"https://content.openalex.org/works/W7214219958.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7163670536","https://openalex.org/W7214092080","https://openalex.org/W7168263593","https://openalex.org/W7214727914","https://openalex.org/W7221459426","https://openalex.org/W4414689552","https://openalex.org/W7218888370","https://openalex.org/W7164648835","https://openalex.org/W7102932810","https://openalex.org/W7203715738"],"abstract_inverted_index":{"Deployment":[0,178],"requires":[1,81],"an":[2,74],"agent":[3],"to":[4,66,254],"turn":[5],"application":[6],"code":[7],"into":[8],"a":[9,52,82,133,176,217,229],"running":[10],"system":[11],"whose":[12],"services":[13],"connect,":[14],"become":[15],"ready,":[16],"and":[17,34,38,49,64,86,106,139,162,174,252,260],"remain":[18],"observable.":[19],"FDE-Bench":[20,248],"evaluates":[21],"this":[22],"capability":[23],"with":[24,216],"136":[25],"deployment-configuration":[26],"tasks":[27,88,129,224],"spanning":[28],"Docker":[29],"images,":[30],"multi-service":[31],"Compose":[32],"stacks,":[33],"Kubernetes,":[35],"in":[36,51,119],"greenfield":[37,214],"diagnose-and-repair":[39],"modes.":[40],"Agents":[41],"submit":[42],"declarative":[43],"artifacts":[44,255],"that":[45,256],"are":[46],"collected,":[47],"rebuilt,":[48],"redeployed":[50],"pristine":[53],"environment.":[54],"Four":[55],"gated":[56],"binary":[57],"check":[58,98],"layers":[59],"measure":[60],"build,":[61],"readiness,":[62],"behavior,":[63],"conformance":[65],"the":[67,101,120,127,141,147,158,186,206,212,245],"deployment":[68,250],"specification,":[69],"using":[70],"programmatic":[71],"checks":[72,105],"without":[73],"LLM":[75],"judge.":[76],"A":[77],"four-arm":[78],"release":[79],"gate":[80],"resolving":[83],"reference":[84],"solution":[85],"rejects":[87],"solved":[89],"by":[90],"do-nothing,":[91],"specification-transcription,":[92],"or":[93],"generic-stub":[94],"submissions.":[95],"The":[96,168],"released":[97],"annotations":[99],"expose":[100],"link":[102],"between":[103],"2,145":[104],"their":[107],"specifications,":[108],"including":[109],"seven":[110,151],"documented":[111],"gaps.":[112],"Three":[113],"additional":[114],"adversarial":[115],"strategies":[116],"test":[117],"shortcuts":[118],"grading":[121],"signals;":[122],"none":[123,173],"resolves":[124,238],"any":[125],"of":[126,166,180,193],"135":[128],"they":[130],"cover,":[131],"while":[132],"vacuous":[134],"health":[135],"probe":[136],"passes":[137],"readiness":[138],"exposes":[140],"need":[142],"for":[143,191,220,244],"downstream":[144],"checks.":[145],"On":[146],"136-task":[148],"evaluation":[149],"grid,":[150],"language":[152],"models":[153],"from":[154],"four":[155],"providers":[156],"use":[157],"same":[159],"four-tool":[160],"scaffold":[161],"resolve":[163,172],"52.9-75.0":[164],"percent":[165,240,243],"tasks.":[167],"three":[169],"zero-intelligence":[170],"floors":[171],"reach":[175],"mean":[177],"Score":[179],"at":[181],"most":[182],"0.44.":[183],"Readiness":[184],"is":[185,200],"largest":[187],"failure":[188,253],"stage,":[189],"accounting":[190],"110":[192],"313":[194],"unresolved":[195],"episodes.":[196],"Mean":[197],"resolution":[198],"rate":[199],"30.7":[201],"percentage":[202],"points":[203],"higher":[204],"on":[205,211],"repair":[207],"task":[208],"group":[209],"than":[210],"disjoint":[213],"group,":[215],"positive":[218],"gap":[219],"every":[221],"model;":[222],"ten":[223],"resist":[225],"all":[226],"seven.":[227],"In":[228],"25-task":[230],"case":[231],"study,":[232],"one":[233],"practicing":[234],"engineer":[235],"directing":[236],"Claude-Sonnet-5":[237],"92":[239],"against":[241],"72":[242],"autonomous":[246],"baseline.":[247],"links":[249],"success":[251],"can":[257],"be":[258],"inspected":[259],"replayed.":[261]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-09-25T00:00:00"}
