{"id":"https://openalex.org/W7163397270","doi":"https://doi.org/10.48550/arxiv.2606.03963","title":"AgenticRL: Self-Refining Agentic Reinforcement Learning for Vision-Conditioned UAV Navigation","display_name":"AgenticRL: Self-Refining Agentic Reinforcement Learning for Vision-Conditioned UAV Navigation","publication_year":2026,"publication_date":"2026-06-02","ids":{"openalex":"https://openalex.org/W7163397270","doi":"https://doi.org/10.48550/arxiv.2606.03963"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.03963","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.03963","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2606.03963","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5114102036","display_name":"Roohan Ahmed Khan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Khan, Roohan Ahmed","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104621266","display_name":"Yasheerah Yaqoot","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yaqoot, Yasheerah","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Habel, Amir Atef","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Habel, Amir Atef","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137738418","display_name":"Muhammad Ahsan Mustafa","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mustafa, Muhammad Ahsan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Tsetserukou, Dzmitry","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tsetserukou, Dzmitry","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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.3199999928474426,"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"}},"topics":[{"id":"https://openalex.org/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.3199999928474426,"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"}},{"id":"https://openalex.org/T10586","display_name":"Robotic Path Planning Algorithms","score":0.19259999692440033,"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"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.1137000024318695,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8411999940872192},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6600000262260437},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5967000126838684},{"id":"https://openalex.org/keywords/obstacle-avoidance","display_name":"Obstacle avoidance","score":0.5320000052452087},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.4932999908924103},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4603999853134155},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.3894999921321869},{"id":"https://openalex.org/keywords/obstacle","display_name":"Obstacle","score":0.36550000309944153},{"id":"https://openalex.org/keywords/markov-decision-process","display_name":"Markov decision process","score":0.3359000086784363}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8411999940872192},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6966000199317932},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6600000262260437},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5967000126838684},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5896000266075134},{"id":"https://openalex.org/C6683253","wikidata":"https://www.wikidata.org/wiki/Q7075535","display_name":"Obstacle avoidance","level":4,"score":0.5320000052452087},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.4932999908924103},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4603999853134155},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.3894999921321869},{"id":"https://openalex.org/C2776650193","wikidata":"https://www.wikidata.org/wiki/Q264661","display_name":"Obstacle","level":2,"score":0.36550000309944153},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.35760000348091125},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3425999879837036},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.3359000086784363},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.33239999413490295},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.33059999346733093},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.328000009059906},{"id":"https://openalex.org/C13687954","wikidata":"https://www.wikidata.org/wiki/Q4826847","display_name":"Autonomous agent","level":2,"score":0.326200008392334},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.322299987077713},{"id":"https://openalex.org/C173246807","wikidata":"https://www.wikidata.org/wiki/Q7833062","display_name":"Trajectory optimization","level":3,"score":0.31630000472068787},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.3133000135421753},{"id":"https://openalex.org/C193611912","wikidata":"https://www.wikidata.org/wiki/Q4677596","display_name":"Active vision","level":2,"score":0.2727999985218048},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.2653999924659729},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2639999985694885},{"id":"https://openalex.org/C201004817","wikidata":"https://www.wikidata.org/wiki/Q1707071","display_name":"Guidance system","level":2,"score":0.2605000138282776},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.25619998574256897},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.2524000108242035}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.03963","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.03963","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2606.03963","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.03963","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Deep":[0],"reinforcement":[1,53],"learning":[2,54],"has":[3],"shown":[4],"strong":[5],"potential":[6],"for":[7,68,174],"enabling":[8],"autonomous":[9],"robots":[10],"to":[11,84,119,162],"learn":[12],"complex":[13],"navigational":[14,182],"tasks.":[15,74],"However,":[16],"its":[17],"practical":[18],"use":[19],"still":[20],"depends":[21],"heavily":[22],"on":[23,123,180],"human":[24],"designed":[25],"reward":[26,60,95,134],"functions":[27],"and":[28,37,64,88,105,131,157,168,196,235],"repeated":[29],"manual":[30],"fine":[31],"tuning,":[32],"which":[33],"is":[34,178],"time":[35],"consuming":[36],"does":[38],"not":[39],"guarantee":[40],"high":[41],"success":[42,231],"in":[43,59,136],"the":[44,113,126,133,146,165,170,204,224],"desired":[45],"task.":[46],"This":[47],"paper":[48],"presents":[49],"AgenticRL,":[50],"agent":[51,83,127,149],"guided":[52],"framework":[55,177],"that":[56,203],"increases":[57],"autonomy":[58],"design,":[61],"policy":[62,115,173,210],"refinement,":[63],"real":[65,154,229],"world":[66,155,230],"deployment":[67],"unmanned":[69],"aerial":[70],"vehicles":[71],"(UAV)":[72],"navigation":[73],"AgenticRL":[75,152],"uses":[76,153],"a":[77,109,137,228,236],"multimodal":[78,147],"generative":[79],"pre-trained":[80],"transformer":[81],"(GPT)":[82],"interpret":[85],"task":[86,93,160],"information":[87,161],"visual":[89],"scene":[90],"observations,":[91],"generate":[92,120],"specific":[94],"functions,":[96],"train":[97],"policies":[98],"using":[99],"Proximal":[100],"Policy":[101],"Optimization":[102],"(PPO)":[103],"algorithm,":[104],"then":[106],"act":[107],"as":[108],"critic":[110],"by":[111,216],"evaluating":[112],"trained":[114,172],"through":[116],"diagnosis":[117],"packets":[118],"feedback.":[121],"Based":[122],"this":[124],"feedback,":[125],"identifies":[128],"failure":[129],"modes":[130],"refines":[132],"function":[135],"closed":[138,205],"loop":[139,206],"self":[140],"improvement":[141],"process.":[142],"To":[143],"further":[144],"leverage":[145],"GPT":[148],"during":[150],"inference,":[151],"images":[156],"natural":[158],"language":[159],"automatically":[163],"identify":[164],"active":[166],"scenario":[167],"select":[169],"appropriate":[171],"execution.":[175],"The":[176],"evaluated":[179],"multiple":[181],"tasks,":[183],"including":[184],"gate":[185],"traversal,":[186],"obstacle":[187],"avoidance,":[188],"wall":[189],"barrier":[190],"crossing":[191],"with":[192,213],"landing,":[193],"trajectory":[194],"following,":[195],"motion":[197],"behavior":[198,211],"learning.":[199],"Experimental":[200],"results":[201],"show":[202],"refinement":[207],"process":[208],"improves":[209],"compared":[212],"initial":[214],"rewards":[215],"71%.":[217],"We":[218],"also":[219],"demonstrate":[220],"sim-to-real":[221,237],"transfer":[222],"of":[223,233,239],"proposed":[225],"framework,":[226],"achieving":[227],"rate":[232],"91%":[234],"accuracy":[238],"94%.":[240]},"counts_by_year":[],"updated_date":"2026-07-21T08:15:58.654021","created_date":"2026-06-04T00:00:00"}