{"id":"https://openalex.org/W4416401444","doi":"https://doi.org/10.48550/arxiv.2510.08044","title":"Towards Reliable LLM-based Robot Planning via Combined Uncertainty Estimation","display_name":"Towards Reliable LLM-based Robot Planning via Combined Uncertainty Estimation","publication_year":2025,"publication_date":"2025-10-09","ids":{"openalex":"https://openalex.org/W4416401444","doi":"https://doi.org/10.48550/arxiv.2510.08044"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2510.08044","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.08044","pdf_url":"https://arxiv.org/pdf/2510.08044","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/2510.08044","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Yin, Shiyuan","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I36152291","display_name":"Henan University of Technology","ror":"https://ror.org/05sbgwt55","country_code":"CN","type":"education","lineage":["https://openalex.org/I36152291"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yin, Shiyuan","raw_affiliation_strings":["School of Artificial Intelligence , Henan University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence , Henan University of Technology","institution_ids":["https://openalex.org/I36152291"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044788927","display_name":"Chenjia Bai","orcid":"https://orcid.org/0000-0002-8379-9385","observed_orcids":["https://orcid.org/0000-0002-8379-9385"]},"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"]},{"id":"https://openalex.org/I4387153335","display_name":"China Telecom","ror":"https://ror.org/05p67dv18","country_code":"CN","type":"company","lineage":["https://openalex.org/I4387153335"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bai, Chenjia","raw_affiliation_strings":["Institute of Artificial Intelligence (TeleAI) , China Telecom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence (TeleAI) , China Telecom","institution_ids":["https://openalex.org/I4210136246","https://openalex.org/I4387153335"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015096973","display_name":"Zihao Zhang","orcid":"https://orcid.org/0000-0001-5610-0260","observed_orcids":["https://orcid.org/0000-0001-5610-0260"]},"institutions":[{"id":"https://openalex.org/I36152291","display_name":"Henan University of Technology","ror":"https://ror.org/05sbgwt55","country_code":"CN","type":"education","lineage":["https://openalex.org/I36152291"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhang, Zihao","raw_affiliation_strings":["School of Artificial Intelligence , Henan University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence , Henan University of Technology","institution_ids":["https://openalex.org/I36152291"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075136696","display_name":"Junwei Jin","orcid":"https://orcid.org/0000-0002-3747-1004","observed_orcids":["https://orcid.org/0000-0002-3747-1004"]},"institutions":[{"id":"https://openalex.org/I36152291","display_name":"Henan University of Technology","ror":"https://ror.org/05sbgwt55","country_code":"CN","type":"education","lineage":["https://openalex.org/I36152291"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jin, Junwei","raw_affiliation_strings":["School of Artificial Intelligence , Henan University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence , Henan University of Technology","institution_ids":["https://openalex.org/I36152291"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100375473","display_name":"Xinxin Zhang","orcid":"https://orcid.org/0000-0002-8239-7050","observed_orcids":["https://orcid.org/0000-0002-8239-7050"]},"institutions":[{"id":"https://openalex.org/I36152291","display_name":"Henan University of Technology","ror":"https://ror.org/05sbgwt55","country_code":"CN","type":"education","lineage":["https://openalex.org/I36152291"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhang, Xinxin","raw_affiliation_strings":["School of Artificial Intelligence , Henan University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence , Henan University of Technology","institution_ids":["https://openalex.org/I36152291"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhang, Chi","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Chi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5106943753","display_name":"Xuelong Li","orcid":"https://orcid.org/0000-0003-2924-946X","observed_orcids":["https://orcid.org/0000-0003-2924-946X"]},"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"]},{"id":"https://openalex.org/I4387153335","display_name":"China Telecom","ror":"https://ror.org/05p67dv18","country_code":"CN","type":"company","lineage":["https://openalex.org/I4387153335"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li, Xuelong","raw_affiliation_strings":["Institute of Artificial Intelligence (TeleAI) , China Telecom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Artificial Intelligence (TeleAI) , China Telecom","institution_ids":["https://openalex.org/I4210136246","https://openalex.org/I4387153335"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.7875999808311462,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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/T10653","display_name":"Robot Manipulation and Learning","score":0.7875999808311462,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.18459999561309814,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.006800000090152025,"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/uncertainty-estimation","display_name":"uncertainty estimation","score":0.9399999976158142},{"id":"https://openalex.org/keywords/epistemic-uncertainty","display_name":"epistemic uncertainty","score":0.9950000047683716},{"id":"https://openalex.org/keywords/intrinsic-uncertainty","display_name":"intrinsic uncertainty","score":0.9890000224113464},{"id":"https://openalex.org/keywords/llm-hallucination","display_name":"LLM hallucination","score":0.8009999990463257},{"id":"https://openalex.org/keywords/task-clarity","display_name":"task clarity","score":0.6230000257492065},{"id":"https://openalex.org/keywords/task-familiarity","display_name":"task familiarity","score":0.9980000257492065},{"id":"https://openalex.org/keywords/random-network-distillation","display_name":"random network distillation","score":0.9309999942779541},{"id":"https://openalex.org/keywords/natural-language-instructions","display_name":"natural language instructions","score":0.6520000100135803}],"concepts":[{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6955999732017517},{"id":"https://openalex.org/C32230216","wikidata":"https://www.wikidata.org/wiki/Q7882499","display_name":"Uncertainty quantification","level":2,"score":0.6410999894142151},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6381999850273132},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.5999000072479248},{"id":"https://openalex.org/C2777146004","wikidata":"https://www.wikidata.org/wiki/Q14949826","display_name":"CLARITY","level":2,"score":0.5935999751091003},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.588699996471405},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.49799999594688416},{"id":"https://openalex.org/C137209882","wikidata":"https://www.wikidata.org/wiki/Q1403517","display_name":"Measurement uncertainty","level":2,"score":0.4846999943256378},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4699000120162964},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.4388999938964844},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.3982999920845032},{"id":"https://openalex.org/C177803969","wikidata":"https://www.wikidata.org/wiki/Q29205","display_name":"Uncertainty analysis","level":2,"score":0.3684000074863434},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.3555000126361847},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.3278999924659729},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.325300008058548},{"id":"https://openalex.org/C94361409","wikidata":"https://www.wikidata.org/wiki/Q7882500","display_name":"Uncertainty reduction theory","level":2,"score":0.3244999945163727},{"id":"https://openalex.org/C60908668","wikidata":"https://www.wikidata.org/wiki/Q690207","display_name":"Perceptron","level":3,"score":0.3165000081062317},{"id":"https://openalex.org/C2983703474","wikidata":"https://www.wikidata.org/wiki/Q17088227","display_name":"Probability estimation","level":2,"score":0.31459999084472656},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.30559998750686646},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.30320000648498535},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.2827000021934509},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2824000120162964},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.2809000015258789},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.27880001068115234},{"id":"https://openalex.org/C51110983","wikidata":"https://www.wikidata.org/wiki/Q16503490","display_name":"Overconfidence effect","level":2,"score":0.27799999713897705},{"id":"https://openalex.org/C176147448","wikidata":"https://www.wikidata.org/wiki/Q1889114","display_name":"Sensitivity analysis","level":3,"score":0.2718000113964081},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.2648000121116638},{"id":"https://openalex.org/C2776505523","wikidata":"https://www.wikidata.org/wiki/Q4785468","display_name":"Plan (archaeology)","level":2,"score":0.2621000111103058},{"id":"https://openalex.org/C123614077","wikidata":"https://www.wikidata.org/wiki/Q1364905","display_name":"Propagation of uncertainty","level":2,"score":0.26109999418258667},{"id":"https://openalex.org/C2776548248","wikidata":"https://www.wikidata.org/wiki/Q12621536","display_name":"Judgement","level":2,"score":0.2605000138282776},{"id":"https://openalex.org/C179717631","wikidata":"https://www.wikidata.org/wiki/Q2991667","display_name":"Multilayer perceptron","level":3,"score":0.2572000026702881},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.25519999861717224}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2510.08044","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.08044","pdf_url":"https://arxiv.org/pdf/2510.08044","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.2510.08044","doi":"https://doi.org/10.48550/arxiv.2510.08044","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2510.08044","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":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2510.08044","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.08044","pdf_url":"https://arxiv.org/pdf/2510.08044","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":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G7742334228","display_name":null,"funder_award_id":"2024YFE0210900","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416401444.pdf","grobid_xml":"https://content.openalex.org/works/W4416401444.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"language":[1,13],"models":[2],"(LLMs)":[3],"demonstrate":[4],"advanced":[5],"reasoning":[6],"abilities,":[7],"enabling":[8],"robots":[9],"to":[10,31,45,148],"understand":[11],"natural":[12],"instructions":[14],"and":[15,60,88,102,119,139],"generate":[16],"high-level":[17],"plans":[18],"with":[19,161],"appropriate":[20],"grounding.":[21],"However,":[22],"LLM":[23,126],"hallucinations":[24],"present":[25,73],"a":[26],"significant":[27],"challenge,":[28],"often":[29],"leading":[30],"overconfident":[32],"yet":[33],"potentially":[34],"misaligned":[35],"or":[36],"unsafe":[37],"plans.":[38],"While":[39],"researchers":[40],"have":[41,54],"explored":[42],"uncertainty":[43,67,85,96,111,154],"estimation":[44,76],"improve":[46],"the":[47,64,84,162],"reliability":[48],"of":[49,66],"LLM-based":[50],"planning,":[51],"existing":[52,149],"studies":[53],"not":[55],"sufficiently":[56],"differentiated":[57],"between":[58],"epistemic":[59,87,95],"intrinsic":[61,89],"uncertainty,":[62,90],"limiting":[63],"effectiveness":[65],"estimation.":[68],"In":[69],"this":[70],"paper,":[71],"we":[72],"Combined":[74],"Uncertainty":[75],"for":[77,105],"Reliable":[78],"Embodied":[79],"planning":[80],"(CURE),":[81],"which":[82],"decomposes":[83],"into":[86,99],"each":[91],"estimated":[92],"separately.":[93],"Furthermore,":[94],"is":[97],"subdivided":[98],"task":[100,103],"clarity":[101],"familiarity":[104],"more":[106,158],"accurate":[107],"evaluation.":[108],"The":[109,143],"overall":[110],"assessments":[112],"are":[113,157],"obtained":[114],"using":[115],"random":[116],"network":[117],"distillation":[118],"multi-layer":[120],"perceptron":[121],"regression":[122],"heads":[123],"driven":[124],"by":[125],"features.":[127],"We":[128],"validated":[129],"our":[130,151],"approach":[131,152],"in":[132],"two":[133],"distinct":[134],"experimental":[135],"settings:":[136],"kitchen":[137],"manipulation":[138],"tabletop":[140],"rearrangement":[141],"experiments.":[142],"results":[144],"show":[145],"that,":[146],"compared":[147],"methods,":[150],"yields":[153],"estimates":[155],"that":[156],"closely":[159],"aligned":[160],"actual":[163],"execution":[164],"outcomes.":[165]},"counts_by_year":[],"updated_date":"2026-09-30T09:27:27.532063","created_date":"2025-10-11T00:00:00"}