{"id":"https://openalex.org/W7166832712","doi":"https://doi.org/10.18653/v1/2026.findings-acl.83","title":"Lunar-Bench: Towards Evaluating Task-Oriented Reasoning of LLMs in Lunar Exploration Scenarios","display_name":"Lunar-Bench: Towards Evaluating Task-Oriented Reasoning of LLMs in Lunar Exploration Scenarios","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166832712","doi":"https://doi.org/10.18653/v1/2026.findings-acl.83"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.83","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.83","pdf_url":"https://aclanthology.org/2026.findings-acl.83.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.findings-acl.83.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139715211","display_name":"Xin-Yu Xiao","orcid":null},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin-Yu Xiao","raw_affiliation_strings":["Tsinghua University \u2663 University of Chinese Academy of Sciences \u2662 Sun Yat-sen University Tianjin Artificial Intelligence Innovation Center (TAIIC) \u22c6 National Key Laboratory of Human Factors Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University \u2663 University of Chinese Academy of Sciences \u2662 Sun Yat-sen University Tianjin Artificial Intelligence Innovation Center (TAIIC) \u22c6 National Key Laboratory of Human Factors Engineering","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139810193","display_name":"Ye Tian","orcid":null},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ye Tian","raw_affiliation_strings":["Tsinghua University \u2663 University of Chinese Academy of Sciences \u2662 Sun Yat-sen University Tianjin Artificial Intelligence Innovation Center (TAIIC) \u22c6 National Key Laboratory of Human Factors Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University \u2663 University of Chinese Academy of Sciences \u2662 Sun Yat-sen University Tianjin Artificial Intelligence Innovation Center (TAIIC) \u22c6 National Key Laboratory of Human Factors Engineering","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139779965","display_name":"Erwei Yin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Erwei Yin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139846460","display_name":"Zhixian He","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhixian He","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139731878","display_name":"Shiqi Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shiqi Wang","raw_affiliation_strings":["Tsinghua University \u2663 University of Chinese Academy of Sciences \u2662 Sun Yat-sen University Tianjin Artificial Intelligence Innovation Center (TAIIC) \u22c6 National Key Laboratory of Human Factors Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University \u2663 University of Chinese Academy of Sciences \u2662 Sun Yat-sen University Tianjin Artificial Intelligence Innovation Center (TAIIC) \u22c6 National Key Laboratory of Human Factors Engineering","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139782390","display_name":"Yalei Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yalei Liu","raw_affiliation_strings":["Tsinghua University \u2663 University of Chinese Academy of Sciences \u2662 Sun Yat-sen University Tianjin Artificial Intelligence Innovation Center (TAIIC) \u22c6 National Key Laboratory of Human Factors Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University \u2663 University of Chinese Academy of Sciences \u2662 Sun Yat-sen University Tianjin Artificial Intelligence Innovation Center (TAIIC) \u22c6 National Key Laboratory of Human Factors Engineering","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5139820272","display_name":"Qianchen Xia","orcid":null},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qianchen Xia","raw_affiliation_strings":["Tsinghua University \u2663 University of Chinese Academy of Sciences \u2662 Sun Yat-sen University Tianjin Artificial Intelligence Innovation Center (TAIIC) \u22c6 National Key Laboratory of Human Factors Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University \u2663 University of Chinese Academy of Sciences \u2662 Sun Yat-sen University Tianjin Artificial Intelligence Innovation Center (TAIIC) \u22c6 National Key Laboratory of Human Factors Engineering","institution_ids":["https://openalex.org/I157773358"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.79742841,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1668","last_page":"1705"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10906","display_name":"AI-based Problem Solving and Planning","score":0.3325999975204468,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.3325999975204468,"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/T11596","display_name":"Constraint Satisfaction and Optimization","score":0.18029999732971191,"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/T11010","display_name":"Logic, Reasoning, and Knowledge","score":0.1582999974489212,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.289000004529953},{"id":"https://openalex.org/keywords/work","display_name":"Work (physics)","score":0.27869999408721924},{"id":"https://openalex.org/keywords/climate-change","display_name":"Climate change","score":0.27160000801086426}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4009999930858612},{"id":"https://openalex.org/C91375879","wikidata":"https://www.wikidata.org/wiki/Q15473274","display_name":"Environmental planning","level":1,"score":0.3537999987602234},{"id":"https://openalex.org/C107826830","wikidata":"https://www.wikidata.org/wiki/Q929380","display_name":"Environmental resource management","level":1,"score":0.3522000014781952},{"id":"https://openalex.org/C62649853","wikidata":"https://www.wikidata.org/wiki/Q199687","display_name":"Remote sensing","level":1,"score":0.30070000886917114},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.289000004529953},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.27869999408721924},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.27379998564720154},{"id":"https://openalex.org/C132651083","wikidata":"https://www.wikidata.org/wiki/Q7942","display_name":"Climate change","level":2,"score":0.27160000801086426},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.2660999894142151},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.25940001010894775}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.83","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.83","pdf_url":"https://aclanthology.org/2026.findings-acl.83.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-acl.83","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.83","pdf_url":"https://aclanthology.org/2026.findings-acl.83.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7434553541","display_name":null,"funder_award_id":"62502269","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320316328","display_name":"National Key Laboratory of Human Factors Engineering","ror":null},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166832712.pdf","grobid_xml":"https://content.openalex.org/works/W7166832712.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0],"increasing":[1],"complexity":[2],"of":[3,11,59,79],"lunar":[4,60],"exploration":[5],"calls":[6],"for":[7,31,123,133,137],"intelligent":[8],"systems":[9,136],"capable":[10],"supporting":[12],"autonomous":[13],"operations":[14],"and":[15,20,51,57,76,88,104,126],"scientific":[16],"decision-making":[17,77],"under":[18],"uncertain":[19],"resourcelimited":[21],"conditions.Advances":[22],"in":[23,37],"large":[24],"language":[25],"models":[26,112],"(LLMs)":[27],"create":[28],"new":[29],"opportunities":[30],"mission":[32,86],"planning,":[33],"but":[34],"their":[35],"reliability":[36],"dynamic,":[38],"safety-critical":[39],"environments":[40],"remains":[41],"insufficiently":[42],"evaluated.Existing":[43],"benchmarks":[44],"focus":[45],"on":[46,109],"static,":[47],"context-independent":[48],"reasoning":[49,75],"tasks":[50,83],"fail":[52],"to":[53,71],"capture":[54],"the":[55,73,92,115],"constraints":[56],"dependencies":[58],"missions.To":[61],"address":[62],"this":[63],"gap,":[64],"we":[65],"introduce":[66],"Lunar-Bench,":[67],"a":[68,96,130],"benchmark":[69],"designed":[70],"assess":[72],"task-oriented":[74],"performance":[78],"LLMs":[80],"through":[81],"3,000":[82],"derived":[84],"from":[85],"procedures":[87],"documentation.We":[89],"further":[90],"propose":[91],"Environmental":[93],"Scenario":[94],"Indicators,":[95],"process-based":[97],"framework":[98],"that":[99,114],"evaluates":[100],"safety,":[101],"efficiency,":[102],"integrity,":[103],"alignment":[105],"beyond":[106],"conventional":[107],"accuracy.Experiments":[108],"36":[110],"representative":[111],"show":[113],"best":[116],"achieves":[117],"47.8%":[118],"accuracy":[119],"compared":[120],"with":[121],"65.1%":[122],"human":[124],"experts.Lunar-Bench":[125],"ESI":[127],"together":[128],"provide":[129],"principled":[131],"foundation":[132],"developing":[134],"reliable":[135],"future":[138],"missions.":[139]},"counts_by_year":[],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2026-07-02T00:00:00"}
