{"id":"https://openalex.org/W7224253903","doi":"https://doi.org/10.18653/2026.emnlp-industry.5","title":"Lunar-R1: Efficient Reasoning of Large Language Models for Lunar Exploration via Reinforcement Learning","display_name":"Lunar-R1: Efficient Reasoning of Large Language Models for Lunar Exploration via Reinforcement Learning","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7224253903","doi":"https://doi.org/10.18653/2026.emnlp-industry.5"},"language":"en","primary_location":{"id":"doi:10.18653/2026.emnlp-industry.5","doi":"https://doi.org/10.18653/2026.emnlp-industry.5","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.emnlp-industry.5","pdf_url":"https://aclanthology.org/2026.emnlp-industry.5.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Conference on Empirical Methods in Natural Language Processing (EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://aclanthology.org/2026.emnlp-industry.5.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102999463","display_name":"Xinyu Xiao","orcid":"https://orcid.org/0000-0003-4895-632X","observed_orcids":["https://orcid.org/0000-0003-4895-632X"]},"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"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]},{"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":"Xin-Yu Xiao","raw_affiliation_strings":["Tsinghua University \u2663 University of Chinese Academy of Sciences \u2662 Sun Yat-sen University \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 \u22c6 National Key Laboratory of Human Factors Engineering","institution_ids":["https://openalex.org/I157773358","https://openalex.org/I4210165038","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160067238","display_name":"Ye Tian","orcid":null,"observed_orcids":[]},"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"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]},{"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":"Ye Tian","raw_affiliation_strings":["Tsinghua University \u2663 University of Chinese Academy of Sciences \u2662 Sun Yat-sen University \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 \u22c6 National Key Laboratory of Human Factors Engineering","institution_ids":["https://openalex.org/I157773358","https://openalex.org/I4210165038","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160090669","display_name":"Zhixian He","orcid":null,"observed_orcids":[]},"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"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]},{"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":"Zhixian He","raw_affiliation_strings":["Tsinghua University \u2663 University of Chinese Academy of Sciences \u2662 Sun Yat-sen University \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 \u22c6 National Key Laboratory of Human Factors Engineering","institution_ids":["https://openalex.org/I157773358","https://openalex.org/I4210165038","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160082452","display_name":"Qilin Chen","orcid":null,"observed_orcids":[]},"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"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]},{"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":"Qilin Chen","raw_affiliation_strings":["Tsinghua University \u2663 University of Chinese Academy of Sciences \u2662 Sun Yat-sen University \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 \u22c6 National Key Laboratory of Human Factors Engineering","institution_ids":["https://openalex.org/I157773358","https://openalex.org/I4210165038","https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100385190","display_name":"Shiqi Wang","orcid":"https://orcid.org/0009-0003-2011-3272","observed_orcids":["https://orcid.org/0009-0003-2011-3272"]},"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"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]},{"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":"Shiqi Wang","raw_affiliation_strings":["Tsinghua University \u2663 University of Chinese Academy of Sciences \u2662 Sun Yat-sen University \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 \u22c6 National Key Laboratory of Human Factors Engineering","institution_ids":["https://openalex.org/I157773358","https://openalex.org/I4210165038","https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5139820272","display_name":"Qianchen Xia","orcid":null,"observed_orcids":[]},"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"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]},{"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":"Qianchen Xia","raw_affiliation_strings":["Tsinghua University \u2663 University of Chinese Academy of Sciences \u2662 Sun Yat-sen University \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 \u22c6 National Key Laboratory of Human Factors Engineering","institution_ids":["https://openalex.org/I157773358","https://openalex.org/I4210165038","https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"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":0.88968051,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"50","last_page":"69"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.5859000086784363,"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/T10028","display_name":"Topic Modeling","score":0.5859000086784363,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.17980000376701355,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.050599999725818634,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/large-language-models","display_name":"large language models","score":0.746999979019165},{"id":"https://openalex.org/keywords/lunar-exploration","display_name":"lunar exploration","score":0.8650000095367432},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"reinforcement learning","score":0.734000027179718},{"id":"https://openalex.org/keywords/reasoning","display_name":"reasoning","score":0.4970000088214874},{"id":"https://openalex.org/keywords/space-exploration","display_name":"space exploration","score":0.4009999930858612}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6154999732971191},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5074999928474426},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.4722000062465668},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3334999978542328},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.30880001187324524},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.30790001153945923},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.26910001039505005},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2662000060081482},{"id":"https://openalex.org/C195344581","wikidata":"https://www.wikidata.org/wiki/Q2555318","display_name":"Automated reasoning","level":2,"score":0.26179999113082886},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.2605000138282776},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.25369998812675476},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.25049999356269836}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/2026.emnlp-industry.5","doi":"https://doi.org/10.18653/2026.emnlp-industry.5","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.emnlp-industry.5","pdf_url":"https://aclanthology.org/2026.emnlp-industry.5.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Conference on Empirical Methods in Natural Language Processing (EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/2026.emnlp-industry.5","doi":"https://doi.org/10.18653/2026.emnlp-industry.5","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.emnlp-industry.5","pdf_url":"https://aclanthology.org/2026.emnlp-industry.5.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Conference on Empirical Methods in Natural Language Processing (EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"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/W7224253903.pdf","grobid_xml":"https://content.openalex.org/works/W7224253903.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7166878713","https://openalex.org/W7094953006","https://openalex.org/W7196963086","https://openalex.org/W7224408794","https://openalex.org/W7106525592","https://openalex.org/W7213495915","https://openalex.org/W7166824454","https://openalex.org/W7224223240","https://openalex.org/W7166832712","https://openalex.org/W7166891425"],"abstract_inverted_index":{"We":[0],"present":[1],"Lunar-R1,":[2],"an":[3,56,90],"8B-parameter":[4],"reasoning":[5,87],"model":[6],"tailored":[7],"for":[8,105],"lunar":[9,62,106],"science":[10],"and":[11,20,45,65,73,98],"mission":[12,63],"operations,":[13],"developed":[14],"through":[15],"continued":[16],"pre-training,":[17],"supervised":[18],"fine-tuning,":[19],"reinforcement":[21],"learning.To":[22],"optimize":[23],"the":[24],"accuracyefficiency":[25],"trade-off,":[26],"we":[27],"introduce":[28],"Latent":[29],"Difficulty":[30],"Perception":[31],"(LDP),":[32],"a":[33],"lightweight":[34],"mechanism":[35],"that":[36,77],"leverages":[37],"final-layer":[38],"hidden":[39],"states":[40],"to":[41],"estimate":[42],"query":[43],"difficulty":[44],"regulates":[46],"Chainof-Thought":[47],"generation":[48],"length":[49],"via":[50],"difficultyaware":[51],"reward":[52],"modeling.We":[53],"construct":[54],"Lunar-QA,":[55],"expert-verified":[57],"benchmark":[58],"derived":[59],"from":[60],"authentic":[61],"materials,":[64],"further":[66],"evaluate":[67],"on":[68,89],"domain-specific":[69],"tasks":[70],"spanning":[71],"astronomy":[72],"astrodynamics.Experimental":[74],"results":[75],"demonstrate":[76],"LDP":[78],"reduces":[79],"average":[80],"token":[81],"consumption":[82],"by":[83],"38.9%":[84],"while":[85],"improving":[86],"accuracy.Profiling":[88],"RK3588":[91],"NPU":[92],"yields":[93],"0.54":[94],"J/token":[95],"energy":[96],"efficiency":[97],"380":[99],"ms":[100],"time-to-first-token":[101],"latency,":[102],"validating":[103],"feasibility":[104],"surface":[107],"edge":[108],"deployment.":[109]},"counts_by_year":[],"updated_date":"2026-11-01T11:40:01.658920","created_date":"2026-10-30T00:00:00"}