{"id":"https://openalex.org/W7225150288","doi":"https://doi.org/10.48550/arxiv.2611.02676","title":"Does the Judge See What the Evaluation Requires? Input Assurance for LLM Agent Evaluation","display_name":"Does the Judge See What the Evaluation Requires? Input Assurance for LLM Agent Evaluation","publication_year":2026,"publication_date":"2026-11-02","ids":{"openalex":"https://openalex.org/W7225150288","doi":"https://doi.org/10.48550/arxiv.2611.02676"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2611.02676","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2611.02676","pdf_url":"https://arxiv.org/pdf/2611.02676","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/2611.02676","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5018192313","display_name":"Boming Xia","orcid":"https://orcid.org/0009-0003-7385-4023","observed_orcids":["https://orcid.org/0009-0003-7385-4023"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xia, Boming","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160408581","display_name":"Qinghua Lu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lu, Qinghua","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160461268","display_name":"Runze Li","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Runze","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040046354","display_name":"Dino Sejdinovi\u0107","orcid":"https://orcid.org/0000-0001-5547-9213","observed_orcids":["https://orcid.org/0000-0001-5547-9213","https://orcid.org/0000-0001-5831-633X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sejdinovic, Dino","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5160496141","display_name":"Liming Zhu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhu, Liming","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":false,"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":0.8179000020027161,"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":0.8179000020027161,"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/T10430","display_name":"Software Engineering Techniques and Practices","score":0.03480000048875809,"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/T11986","display_name":"Scientific Computing and Data Management","score":0.028300000354647636,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/llm-agent-evaluation","display_name":"LLM agent evaluation","score":0.8769999742507935},{"id":"https://openalex.org/keywords/llm-as-a-judge","display_name":"LLM-as-a-judge","score":0.6539999842643738},{"id":"https://openalex.org/keywords/integration-testing","display_name":"integration testing","score":0.5070000290870667}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7099999785423279},{"id":"https://openalex.org/C2778089247","wikidata":"https://www.wikidata.org/wiki/Q368951","display_name":"Blank","level":2,"score":0.6399000287055969},{"id":"https://openalex.org/C158379750","wikidata":"https://www.wikidata.org/wiki/Q214111","display_name":"Network packet","level":2,"score":0.6151999831199646},{"id":"https://openalex.org/C43364308","wikidata":"https://www.wikidata.org/wiki/Q8799","display_name":"Byte","level":2,"score":0.5782999992370605},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.41920000314712524},{"id":"https://openalex.org/C103088060","wikidata":"https://www.wikidata.org/wiki/Q1062839","display_name":"Error detection and correction","level":2,"score":0.4043999910354614},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.3959999978542328},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.38420000672340393},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3343000113964081},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.3334999978542328},{"id":"https://openalex.org/C2778527123","wikidata":"https://www.wikidata.org/wiki/Q11750728","display_name":"Punching","level":2,"score":0.3287000060081482},{"id":"https://openalex.org/C168065819","wikidata":"https://www.wikidata.org/wiki/Q845566","display_name":"Debugging","level":2,"score":0.32179999351501465},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.30230000615119934},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.29420000314712524},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.2838999927043915},{"id":"https://openalex.org/C2776175482","wikidata":"https://www.wikidata.org/wiki/Q1195816","display_name":"Transfer (computing)","level":2,"score":0.2732999920845032},{"id":"https://openalex.org/C2776505523","wikidata":"https://www.wikidata.org/wiki/Q4785468","display_name":"Plan (archaeology)","level":2,"score":0.27230000495910645},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.27059999108314514},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.2671999931335449},{"id":"https://openalex.org/C131377759","wikidata":"https://www.wikidata.org/wiki/Q322514","display_name":"Acceptance testing","level":2,"score":0.2623000144958496},{"id":"https://openalex.org/C11742125","wikidata":"https://www.wikidata.org/wiki/Q1195374","display_name":"Syntax error","level":4,"score":0.25540000200271606},{"id":"https://openalex.org/C147494362","wikidata":"https://www.wikidata.org/wiki/Q2078905","display_name":"Troubleshooting","level":2,"score":0.25540000200271606},{"id":"https://openalex.org/C63676506","wikidata":"https://www.wikidata.org/wiki/Q3976238","display_name":"Stub (electronics)","level":2,"score":0.2542000114917755},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2502000033855438}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2611.02676","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2611.02676","pdf_url":"https://arxiv.org/pdf/2611.02676","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.2611.02676","doi":"https://doi.org/10.48550/arxiv.2611.02676","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2611.02676","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:2611.02676","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2611.02676","pdf_url":"https://arxiv.org/pdf/2611.02676","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7165644528","https://openalex.org/W7169763549","https://openalex.org/W7207693075","https://openalex.org/W7204561462","https://openalex.org/W7155074625","https://openalex.org/W7223575517","https://openalex.org/W7206190889","https://openalex.org/W7223125175","https://openalex.org/W7125389743","https://openalex.org/W7206182487"],"abstract_inverted_index":{"An":[0],"LLM":[1],"judge":[2,59,115,199],"assesses":[3],"agent":[4],"steps":[5,108],"from":[6],"text":[7],"packets.":[8],"A":[9],"renderer":[10,97],"converts":[11],"recorded":[12],"runs":[13],"into":[14,237],"these":[15],"packets,":[16],"while":[17,169],"software":[18],"checkers":[19,47,74,186],"test":[20],"records":[21],"and":[22,38,57,75,180,205,240],"packets":[23,79,153],"against":[24],"requirements.":[25],"We":[26,233],"ask":[27],"what":[28,34],"evidence":[29],"shows":[30],"a":[31,51,139,195,201,206],"packet":[32,204],"is":[33],"the":[35,58,61,81,90,156,170,198,222,235],"evaluation":[36],"requires":[37],"propose":[39],"four":[40,88,172,238],"input-assurance":[41],"obligations:":[42],"required":[43],"content":[44],"survives":[45],"rendering,":[46],"cover":[48],"their":[49,244],"requirements,":[50],"failed":[52,202],"check":[53],"stops":[54],"later":[55,117],"use":[56],"reads":[60],"bytes":[62],"last":[63,91],"checked.":[64],"In":[65,152,192],"one":[66,114],"pipeline":[67],"with":[68,84],"30":[69],"trajectories,":[70],"matching":[71,111],"hashes,":[72],"passing":[73],"successful":[76],"staging":[77],"(copying":[78],"for":[80],"judge)":[82],"coexisted":[83],"violations":[85],"of":[86,105,141,216],"all":[87],"obligations,":[89],"two":[92],"in":[93],"integration":[94,193],"tests.":[95],"The":[96,227],"omitted":[98],"every":[99,132,166],"structured":[100],"tool":[101,190],"call,":[102],"leaving":[103],"53":[104],"60":[106],"judged":[107,157],"blank":[109,167,178],"despite":[110],"hashes.":[112],"For":[113],"configuration,":[116],"context":[118],"raised":[119],"error":[120,126,179],"flags":[121],"by":[122],"13":[123],"more":[124],"on":[125,128,165],"than":[127],"correct":[129,181],"steps.":[130,182],"Restoring":[131],"call":[133],"reduced":[134],"this":[135],"contrast":[136],"to":[137,150,242,246],"2,":[138],"reduction":[140],"11":[142],"(0.37":[143],"per":[144],"trajectory,":[145],"95%":[146],"cluster-bootstrap":[147],"interval":[148],"0.17":[149],"0.53).":[151],"ending":[154],"at":[155,162],"step,":[158,168],"that":[159],"configuration":[160],"abstained":[161,174],"least":[163],"once":[164],"other":[171],"sometimes":[173],"but":[175],"also":[176],"flagged":[177],"Both":[183],"separately":[184],"written":[185],"accepted":[187],"an":[188],"unmatched":[189],"result.":[191],"tests,":[194],"stub":[196,223],"replacing":[197],"read":[200,224],"build's":[203],"copy":[207],"changed":[208],"after":[209],"staging.":[210],"Three":[211],"added":[212],"controls":[213],"stopped":[214],"18":[215],"19":[217],"constructed":[218],"fault":[219],"cases":[220],"before":[221],"any":[225],"packet.":[226],"remaining":[228],"stale":[229],"script":[230],"never":[231],"ran.":[232],"turn":[234],"obligations":[236],"tests":[239],"plan":[241],"evaluate":[243],"transfer":[245],"independent":[247],"pipelines.":[248]},"counts_by_year":[],"updated_date":"2026-11-05T12:25:35.769452","created_date":"2026-11-04T00:00:00"}
