{"id":"https://openalex.org/W7119740875","doi":"https://doi.org/10.48550/arxiv.2601.04334","title":"Autonomous Reasoning for Spacecraft Control: A Large Language Model Framework with Group Relative Policy Optimization","display_name":"Autonomous Reasoning for Spacecraft Control: A Large Language Model Framework with Group Relative Policy Optimization","publication_year":2026,"publication_date":"2026-01-07","ids":{"openalex":"https://openalex.org/W7119740875","doi":"https://doi.org/10.48550/arxiv.2601.04334"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2601.04334","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2601.04334","pdf_url":"https://arxiv.org/pdf/2601.04334","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/2601.04334","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5140656738","display_name":"Amit Jain","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jain, Amit","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5087614402","display_name":"Richard Linares","orcid":"https://orcid.org/0000-0001-8325-7378","observed_orcids":["https://orcid.org/0000-0001-8325-7378","https://orcid.org/0000-0003-0797-2470"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Linares, Richard","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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9765999913215637,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9765999913215637,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.009800000116229057,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T11082","display_name":"Spacecraft Dynamics and Control","score":0.003800000064074993,"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/spacecraft-attitude-control","display_name":"spacecraft attitude control","score":0.7570000290870667},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.8519999980926514},{"id":"https://openalex.org/keywords/group-relative-policy-optimization","display_name":"Group Relative Policy Optimization","score":0.871999979019165},{"id":"https://openalex.org/keywords/autonomous-reasoning","display_name":"autonomous reasoning","score":0.7739999890327454},{"id":"https://openalex.org/keywords/guidance-and-control","display_name":"guidance and control","score":0.6439999938011169},{"id":"https://openalex.org/keywords/supervised-fine-tuning","display_name":"supervised fine-tuning","score":0.8080000281333923},{"id":"https://openalex.org/keywords/two-stage-training","display_name":"two-stage training","score":0.6140000224113464},{"id":"https://openalex.org/keywords/gyroscopic-coupling","display_name":"gyroscopic coupling","score":0.8669999837875366},{"id":"https://openalex.org/keywords/thrust-constraints","display_name":"thrust constraints","score":0.9750000238418579},{"id":"https://openalex.org/keywords/safety-critical-control-systems","display_name":"safety-critical control systems","score":0.6800000071525574}],"concepts":[{"id":"https://openalex.org/C29829512","wikidata":"https://www.wikidata.org/wiki/Q40218","display_name":"Spacecraft","level":2,"score":0.5116000175476074},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.510699987411499},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5058000087738037},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.5056999921798706},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.49549999833106995},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4348999857902527},{"id":"https://openalex.org/C79420006","wikidata":"https://www.wikidata.org/wiki/Q533668","display_name":"Thrust","level":2,"score":0.4016999900341034},{"id":"https://openalex.org/C91581856","wikidata":"https://www.wikidata.org/wiki/Q2707001","display_name":"Nonlinear control","level":3,"score":0.38609999418258667},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.3831000030040741},{"id":"https://openalex.org/C131584629","wikidata":"https://www.wikidata.org/wiki/Q4308705","display_name":"Coupling (piping)","level":2,"score":0.38260000944137573},{"id":"https://openalex.org/C2781311116","wikidata":"https://www.wikidata.org/wiki/Q83306","display_name":"Group (periodic table)","level":2,"score":0.361299991607666},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.36039999127388},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35249999165534973},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.3506999909877777},{"id":"https://openalex.org/C190839683","wikidata":"https://www.wikidata.org/wiki/Q2448197","display_name":"Train","level":2,"score":0.3424000144004822},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.335999995470047},{"id":"https://openalex.org/C158488048","wikidata":"https://www.wikidata.org/wiki/Q483400","display_name":"Gyroscope","level":2,"score":0.3231000006198883},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.31439998745918274},{"id":"https://openalex.org/C76969082","wikidata":"https://www.wikidata.org/wiki/Q486902","display_name":"Mathematical model","level":2,"score":0.2969000041484833},{"id":"https://openalex.org/C163175372","wikidata":"https://www.wikidata.org/wiki/Q3339222","display_name":"Linear model","level":2,"score":0.2962000072002411},{"id":"https://openalex.org/C167740415","wikidata":"https://www.wikidata.org/wiki/Q2876213","display_name":"Aerospace","level":2,"score":0.2892000079154968},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.288100004196167},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2791000008583069},{"id":"https://openalex.org/C77405623","wikidata":"https://www.wikidata.org/wiki/Q598451","display_name":"System dynamics","level":2,"score":0.27300000190734863},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.26809999346733093}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2601.04334","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2601.04334","pdf_url":"https://arxiv.org/pdf/2601.04334","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.2601.04334","doi":"https://doi.org/10.48550/arxiv.2601.04334","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2601.04334","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:2601.04334","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2601.04334","pdf_url":"https://arxiv.org/pdf/2601.04334","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":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7165402555","https://openalex.org/W4416408611","https://openalex.org/W4402501061","https://openalex.org/W4396649061","https://openalex.org/W7147062114","https://openalex.org/W4416330782","https://openalex.org/W4413392752","https://openalex.org/W7171568675","https://openalex.org/W7167886587","https://openalex.org/W4393924139"],"abstract_inverted_index":{"This":[0,124],"paper":[1],"presents":[2],"a":[3,9,56,127],"learning-based":[4],"guidance-and-control":[5],"approach":[6],"that":[7,82],"couples":[8],"reasoning-enabled":[10],"Large":[11],"Language":[12],"Model":[13],"(LLM)":[14],"with":[15,74,85,137],"Group":[16],"Relative":[17],"Policy":[18],"Optimization":[19],"(GRPO).":[20],"A":[21],"two-stage":[22,107],"procedure":[23],"consisting":[24],"of":[25,58,120],"Supervised":[26],"Fine-Tuning":[27],"(SFT)":[28],"to":[29,69,112,133],"learn":[30],"formatting":[31],"and":[32,77,103,142],"control":[33,53,73,114,135],"primitives,":[34],"followed":[35],"by":[36],"GRPO":[37],"for":[38,44,129],"interaction-driven":[39],"policy":[40],"improvement,":[41],"trains":[42],"controllers":[43],"each":[45],"environment.":[46],"The":[47,106],"framework":[48],"is":[49],"demonstrated":[50],"on":[51],"four":[52],"problems":[54],"spanning":[55],"gradient":[57],"dynamical":[59],"complexity,":[60],"from":[61],"canonical":[62],"linear":[63,102],"systems":[64],"through":[65],"nonlinear":[66,104],"oscillatory":[67],"dynamics":[68],"three-dimensional":[70],"spacecraft":[71],"attitude":[72],"gyroscopic":[75],"coupling":[76],"thrust":[78],"constraints.":[79],"Results":[80],"demonstrate":[81],"an":[83],"LLM":[84],"explicit":[86],"reasoning,":[87],"optimized":[88],"via":[89],"GRPO,":[90],"can":[91],"synthesize":[92],"feasible":[93],"stabilizing":[94],"policies":[95],"under":[96],"consistent":[97],"training":[98,108],"settings":[99],"across":[100],"both":[101],"systems.":[105],"methodology":[109],"enables":[110],"models":[111],"generate":[113],"sequences":[115],"while":[116],"providing":[117],"human-readable":[118],"explanations":[119],"their":[121],"decision-making":[122],"process.":[123],"work":[125],"establishes":[126],"foundation":[128],"applying":[130],"GRPO-based":[131],"reasoning":[132],"autonomous":[134],"systems,":[136],"potential":[138],"applications":[139],"in":[140],"aerospace":[141],"other":[143],"safety-critical":[144],"domains.":[145]},"counts_by_year":[],"updated_date":"2026-10-31T12:09:11.096373","created_date":"2026-01-10T00:00:00"}
