{"id":"https://openalex.org/W4416750138","doi":"https://doi.org/10.1109/iros60139.2025.11246320","title":"VerifyLLM: LLM-Based Pre-Execution Task Plan Verification for Robots","display_name":"VerifyLLM: LLM-Based Pre-Execution Task Plan Verification for Robots","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416750138","doi":"https://doi.org/10.1109/iros60139.2025.11246320"},"language":null,"primary_location":{"id":"doi:10.1109/iros60139.2025.11246320","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11246320","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5108162740","display_name":"Danil S. Grigorev","orcid":null},"institutions":[{"id":"https://openalex.org/I153845743","display_name":"Moscow Institute of Physics and Technology","ror":"https://ror.org/00v0z9322","country_code":"RU","type":"education","lineage":["https://openalex.org/I153845743"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Danil S. Grigorev","raw_affiliation_strings":["MIPT,Dolgoprudny,Russia,141701"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MIPT,Dolgoprudny,Russia,141701","institution_ids":["https://openalex.org/I153845743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054791318","display_name":"Alexey K. Kovalev","orcid":"https://orcid.org/0000-0003-2180-0990"},"institutions":[{"id":"https://openalex.org/I4210089612","display_name":"United States Air Force","ror":"https://ror.org/006gmme17","country_code":"US","type":"government","lineage":["https://openalex.org/I1330347796","https://openalex.org/I4210089612","https://openalex.org/I4210102105"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alexey K. Kovalev","raw_affiliation_strings":["AIRI,Moscow,Russia,121170"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AIRI,Moscow,Russia,121170","institution_ids":["https://openalex.org/I4210089612"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080806360","display_name":"Aleksandr I. Panov","orcid":"https://orcid.org/0000-0002-9747-3837"},"institutions":[{"id":"https://openalex.org/I4210089612","display_name":"United States Air Force","ror":"https://ror.org/006gmme17","country_code":"US","type":"government","lineage":["https://openalex.org/I1330347796","https://openalex.org/I4210089612","https://openalex.org/I4210102105"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aleksandr I. Panov","raw_affiliation_strings":["AIRI,Moscow,Russia,121170"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AIRI,Moscow,Russia,121170","institution_ids":["https://openalex.org/I4210089612"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.673,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.87770752,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"18489","last_page":"18496"},"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":0.2222999930381775,"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":0.2222999930381775,"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":0.14550000429153442,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.05590000003576279,"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/task","display_name":"Task (project management)","score":0.682200014591217},{"id":"https://openalex.org/keywords/textual-entailment","display_name":"Textual entailment","score":0.5199999809265137},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.5081999897956848},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.4894999861717224},{"id":"https://openalex.org/keywords/linear-temporal-logic","display_name":"Linear temporal logic","score":0.47429999709129333},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.46779999136924744},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4675000011920929},{"id":"https://openalex.org/keywords/model-checking","display_name":"Model checking","score":0.4271000027656555},{"id":"https://openalex.org/keywords/formal-verification","display_name":"Formal verification","score":0.4189000129699707}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7986000180244446},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.682200014591217},{"id":"https://openalex.org/C95318506","wikidata":"https://www.wikidata.org/wiki/Q6588467","display_name":"Textual entailment","level":3,"score":0.5199999809265137},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5081999897956848},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.4894999861717224},{"id":"https://openalex.org/C4777664","wikidata":"https://www.wikidata.org/wiki/Q1536492","display_name":"Linear temporal logic","level":2,"score":0.47429999709129333},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.46779999136924744},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4675000011920929},{"id":"https://openalex.org/C110251889","wikidata":"https://www.wikidata.org/wiki/Q1569697","display_name":"Model checking","level":2,"score":0.4271000027656555},{"id":"https://openalex.org/C111498074","wikidata":"https://www.wikidata.org/wiki/Q173326","display_name":"Formal verification","level":2,"score":0.4189000129699707},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39489999413490295},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3935000002384186},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.39239999651908875},{"id":"https://openalex.org/C2776505523","wikidata":"https://www.wikidata.org/wiki/Q4785468","display_name":"Plan (archaeology)","level":2,"score":0.38920000195503235},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.3467999994754791},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.3449000120162964},{"id":"https://openalex.org/C25016198","wikidata":"https://www.wikidata.org/wiki/Q781833","display_name":"Temporal logic","level":2,"score":0.31859999895095825},{"id":"https://openalex.org/C2781181686","wikidata":"https://www.wikidata.org/wiki/Q4226068","display_name":"Coherence (philosophical gambling strategy)","level":2,"score":0.3149000108242035},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.30809998512268066},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.3041999936103821},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.29249998927116394},{"id":"https://openalex.org/C59656382","wikidata":"https://www.wikidata.org/wiki/Q191536","display_name":"Conjunction (astronomy)","level":2,"score":0.2888000011444092},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.27810001373291016},{"id":"https://openalex.org/C62460635","wikidata":"https://www.wikidata.org/wiki/Q5508853","display_name":"Functional verification","level":3,"score":0.2775000035762787},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.27129998803138733},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.25859999656677246},{"id":"https://openalex.org/C195344581","wikidata":"https://www.wikidata.org/wiki/Q2555318","display_name":"Automated reasoning","level":2,"score":0.25450000166893005},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.25360000133514404},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2529999911785126},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.25279998779296875}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros60139.2025.11246320","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11246320","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W2023808162","https://openalex.org/W2071797744","https://openalex.org/W2119709400","https://openalex.org/W2149361370","https://openalex.org/W2151958719","https://openalex.org/W2381901500","https://openalex.org/W2799002257","https://openalex.org/W2969749685","https://openalex.org/W3034758614","https://openalex.org/W3039732322","https://openalex.org/W3205485021","https://openalex.org/W4283788970","https://openalex.org/W4317435073","https://openalex.org/W4377723004","https://openalex.org/W4385574286","https://openalex.org/W4388660746","https://openalex.org/W4390874280","https://openalex.org/W4403232858","https://openalex.org/W4405785696","https://openalex.org/W4405787186","https://openalex.org/W4405787657","https://openalex.org/W4413925704"],"related_works":[],"abstract_inverted_index":{"In":[0,34],"the":[1,28,68,90,94,105,115,119,128,137],"field":[2],"of":[3,31,63,70,84,93,111,118,132],"robotics,":[4],"researchers":[5],"face":[6],"a":[7,81],"critical":[8,138],"challenge":[9],"in":[10,50,104,144],"ensuring":[11],"reliable":[12],"and":[13,26,100,130,135],"efficient":[14],"task":[15,19,45,133],"planning.":[16],"Verifying":[17],"high-level":[18,44],"plans":[20,46],"before":[21,47],"execution":[22,49],"significantly":[23],"reduces":[24],"errors":[25],"enhance":[27],"overall":[29],"performance":[30],"these":[32],"systems.":[33,146],"this":[35],"paper,":[36],"we":[37],"propose":[38],"an":[39],"architecture":[40],"for":[41,140],"automatically":[42],"verifying":[43],"their":[48],"simulator":[51],"or":[52],"real-world":[53],"environments.":[54],"Leveraging":[55],"Large":[56],"Language":[57],"Models":[58],"(LLMs),":[59],"our":[60],"approach":[61],"consists":[62],"two":[64],"key":[65],"steps:":[66],"first,":[67],"conversion":[69],"natural":[71],"language":[72],"instructions":[73],"into":[74],"Linear":[75],"Temporal":[76],"Logic":[77],"(LTL),":[78],"followed":[79],"by":[80],"comprehensive":[82],"analysis":[83],"action":[85],"sequences.":[86],"The":[87,147],"module":[88,120],"uses":[89],"reasoning":[91],"capabilities":[92],"LLM":[95],"to":[96,121,126],"evaluate":[97],"logical":[98],"coherence":[99],"identify":[101],"potential":[102],"gaps":[103],"plan.":[106],"Rigorous":[107],"testing":[108],"on":[109],"datasets":[110],"varying":[112],"complexity":[113],"demonstrates":[114],"broad":[116],"applicability":[117],"household":[122],"tasks.":[123],"We":[124],"contribute":[125],"improving":[127],"reliability":[129],"efficiency":[131],"planning":[134],"addresses":[136],"need":[139],"robust":[141],"pre-execution":[142],"verification":[143],"autonomous":[145],"project":[148],"page":[149],"is":[150],"available":[151],"at":[152],"https://verifyllm.github.io.":[153]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-11-28T00:00:00"}