{"id":"https://openalex.org/W7208748611","doi":"https://doi.org/10.48550/arxiv.2609.04021","title":"FLY-EVAL++: An Evidence-Driven Evaluation Protocol for Safety-Constrained Flight Prediction with Large Language Models","display_name":"FLY-EVAL++: An Evidence-Driven Evaluation Protocol for Safety-Constrained Flight Prediction with Large Language Models","publication_year":2026,"publication_date":"2026-09-03","ids":{"openalex":"https://openalex.org/W7208748611","doi":"https://doi.org/10.48550/arxiv.2609.04021"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.04021","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.04021","pdf_url":"https://arxiv.org/pdf/2609.04021","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","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2609.04021","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5133524793","display_name":"Yalun Wu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Wu, Yalun","raw_affiliation_strings":["NExT++ Lab , School of Computing , National University of Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NExT++ Lab , School of Computing , National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5150034767","display_name":"Junfeng Fang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Fang, Junfeng","raw_affiliation_strings":["NExT++ Lab , School of Computing , National University of Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NExT++ Lab , School of Computing , National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5150001948","display_name":"Jiawei Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Wang, Jiawei","raw_affiliation_strings":["NExT++ Lab , School of Computing , National University of Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NExT++ Lab , School of Computing , National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133529763","display_name":"Haotian Liu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liu, Haotian","raw_affiliation_strings":["Xiamen University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiamen University","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5150010599","display_name":"Qijun Yang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yang, Qijun","raw_affiliation_strings":["University of Manchester"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Manchester","institution_ids":["https://openalex.org/I28407311"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101802213","display_name":"Minghan Yang","orcid":"https://orcid.org/0000-0002-6501-7132","observed_orcids":["https://orcid.org/0000-0002-6501-7132","https://orcid.org/0000-0002-5277-7191"]},"institutions":[{"id":"https://openalex.org/I189210763","display_name":"Yunnan University","ror":"https://ror.org/0040axw97","country_code":"CN","type":"education","lineage":["https://openalex.org/I189210763"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang, Minghan","raw_affiliation_strings":["Yunnan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yunnan University","institution_ids":["https://openalex.org/I189210763"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5150037623","display_name":"Hongcheng Guo","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guo, Hongcheng","raw_affiliation_strings":["Fudan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5150012411","display_name":"Zhoujun Li","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li, Zhoujun","raw_affiliation_strings":["CCSE , Beihang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CCSE , Beihang University","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5133508932","display_name":"Boyang Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210136246","display_name":"China Telecom (China)","ror":"https://ror.org/03jgnzt20","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210136246"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wang, Boyang","raw_affiliation_strings":["Xingchen AGI Lab , China Telecom Artificial Intelligence Technology (Beijing) Co., Ltd. , Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xingchen AGI Lab , China Telecom Artificial Intelligence Technology (Beijing) Co., Ltd. , Beijing , China","institution_ids":["https://openalex.org/I4210136246"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":7,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.42500001192092896,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.42500001192092896,"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/T13295","display_name":"Safety Systems Engineering in Autonomy","score":0.34689998626708984,"subfield":{"id":"https://openalex.org/subfields/2213","display_name":"Safety, Risk, Reliability and Quality"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11489","display_name":"Air Traffic Management and Optimization","score":0.03779999911785126,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.8610000014305115},{"id":"https://openalex.org/keywords/aircraft-trajectory-prediction","display_name":"aircraft trajectory prediction","score":0.8939999938011169},{"id":"https://openalex.org/keywords/safety-compliance","display_name":"safety compliance","score":0.5350000262260437},{"id":"https://openalex.org/keywords/multi-step-forecasting","display_name":"multi-step forecasting","score":0.8700000047683716},{"id":"https://openalex.org/keywords/assessment-rubrics","display_name":"assessment rubrics","score":0.5329999923706055},{"id":"https://openalex.org/keywords/safety-critical-systems","display_name":"safety-critical systems","score":0.6179999709129333}],"concepts":[{"id":"https://openalex.org/C2780385302","wikidata":"https://www.wikidata.org/wiki/Q367158","display_name":"Protocol (science)","level":3,"score":0.6776999831199646},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6758999824523926},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6492999792098999},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.6262999773025513},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.5522000193595886},{"id":"https://openalex.org/C2780615836","wikidata":"https://www.wikidata.org/wiki/Q2471869","display_name":"USable","level":2,"score":0.5242999792098999},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.5016000270843506},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.47780001163482666},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.4169999957084656},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38499999046325684},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3716000020503998},{"id":"https://openalex.org/C199622910","wikidata":"https://www.wikidata.org/wiki/Q1128326","display_name":"Constraint satisfaction problem","level":3,"score":0.35370001196861267},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.337799996137619},{"id":"https://openalex.org/C126433048","wikidata":"https://www.wikidata.org/wiki/Q7921324","display_name":"Verification and validation of computer simulation models","level":2,"score":0.3359000086784363},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.3181999921798706},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.310699999332428},{"id":"https://openalex.org/C92446256","wikidata":"https://www.wikidata.org/wiki/Q3306762","display_name":"Data validation","level":2,"score":0.3086000084877014},{"id":"https://openalex.org/C44154836","wikidata":"https://www.wikidata.org/wiki/Q45045","display_name":"Simulation","level":1,"score":0.2587999999523163},{"id":"https://openalex.org/C2775907273","wikidata":"https://www.wikidata.org/wiki/Q7805281","display_name":"Time constraint","level":2,"score":0.2565999925136566},{"id":"https://openalex.org/C110251889","wikidata":"https://www.wikidata.org/wiki/Q1569697","display_name":"Model checking","level":2,"score":0.25440001487731934}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.04021","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.04021","pdf_url":"https://arxiv.org/pdf/2609.04021","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.2609.04021","doi":"https://doi.org/10.48550/arxiv.2609.04021","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.04021","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:2609.04021","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.04021","pdf_url":"https://arxiv.org/pdf/2609.04021","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/W7208748611.pdf","grobid_xml":"https://content.openalex.org/works/W7208748611.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7153993035","https://openalex.org/W7160988150","https://openalex.org/W7204500136","https://openalex.org/W7203717758","https://openalex.org/W7167246297","https://openalex.org/W7084084590","https://openalex.org/W4404355197","https://openalex.org/W4411119648","https://openalex.org/W4414875577","https://openalex.org/W7160416789"],"abstract_inverted_index":{"Evaluating":[0],"large":[1],"language":[2],"models":[3,113],"(LLMs)":[4],"in":[5,31,124,141,149],"safety-critical,":[6],"physics-governed":[7],"environments":[8],"requires":[9],"more":[10,120],"than":[11,121,161],"accuracy-based":[12],"metrics,":[13],"because":[14],"predictions":[15,138],"that":[16,59,147],"are":[17],"numerically":[18],"close":[19],"to":[20,37],"the":[21,91,106],"ground":[22],"truth":[23],"can":[24],"still":[25],"violate":[26],"operational":[27],"constraints,":[28],"combine":[29],"fields":[30],"physically":[32,136],"inconsistent":[33],"ways,":[34],"or":[35],"fail":[36],"produce":[38],"usable":[39],"structured":[40,157],"outputs.":[41],"Existing":[42],"evaluation":[43,57,148],"protocols":[44],"do":[45],"not":[46],"measure":[47,153],"these":[48],"failure":[49],"modes":[50],"reliably.":[51],"We":[52,79],"propose":[53],"FLY-EVAL++,":[54],"an":[55],"evidence-driven":[56],"protocol":[58,64],"combines":[60],"deterministic":[61],"verification":[62],"of":[63,110],"compliance,":[65],"physical":[66],"feasibility,":[67],"and":[68,85,96,127,139,156],"safety":[69,103,125,133],"constraints":[70],"with":[71,94,114],"fixed":[72],"rubric-guided":[73],"aggregation":[74],"into":[75],"interpretable":[76],"multi-dimensional":[77],"scores.":[78],"instantiate":[80],"FLY-EVAL++":[81],"for":[82],"Flight":[83],"Trajectory":[84],"Attitude":[86],"Prediction":[87],"(FTAP)":[88],"by":[89,119],"extending":[90],"PilotBench":[92],"setting":[93],"history-conditioned":[95],"multi-step":[97,142],"prediction":[98],"tasks.":[99],"Across":[100],"66":[101],"LLMs,":[102],"compliance":[104],"is":[105],"most":[107],"discriminative":[108],"dimension":[109],"model":[111],"behavior:":[112],"comparable":[115],"predictive":[116],"performance":[117],"differ":[118],"28":[122],"points":[123],"score,":[126],"we":[128],"observe":[129],"recurrent":[130],"failures":[131],"including":[132],"violations":[134],"under":[135],"plausible":[137],"instability":[140],"rollouts.":[143],"These":[144],"results":[145],"show":[146],"safety-critical":[150],"domains":[151],"should":[152],"constraint":[154],"satisfaction":[155],"validity":[158],"explicitly":[159],"rather":[160],"rely":[162],"on":[163],"accuracy-centric":[164],"reporting":[165],"alone.":[166]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-09-05T00:00:00"}