{"id":"https://openalex.org/W4416748821","doi":"https://doi.org/10.1109/iros60139.2025.11247436","title":"LightPlanner: Unleashing the Reasoning Capabilities of Lightweight Large Language Models in Task Planning","display_name":"LightPlanner: Unleashing the Reasoning Capabilities of Lightweight Large Language Models in Task Planning","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416748821","doi":"https://doi.org/10.1109/iros60139.2025.11247436"},"language":null,"primary_location":{"id":"doi:10.1109/iros60139.2025.11247436","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11247436","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":"article","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/A5029399748","display_name":"Weijie Zhou","orcid":"https://orcid.org/0000-0002-6094-3823"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Weijie Zhou","raw_affiliation_strings":["Beijing Jiaotong University,School of Traffic and Transportation"],"affiliations":[{"raw_affiliation_string":"Beijing Jiaotong University,School of Traffic and Transportation","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047036609","display_name":"Manli Tao","orcid":"https://orcid.org/0000-0002-7484-8173"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Manli Tao","raw_affiliation_strings":["Chinese Academy of Sciences,Foundation Model Research Center, Institute of Automation"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Foundation Model Research Center, Institute of Automation","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102990950","display_name":"Chaoyang Zhao","orcid":"https://orcid.org/0009-0005-3896-6542"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chaoyang Zhao","raw_affiliation_strings":["Chinese Academy of Sciences,Foundation Model Research Center, Institute of Automation"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Foundation Model Research Center, Institute of Automation","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032456240","display_name":"Honghui Dong","orcid":null},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Honghui Dong","raw_affiliation_strings":["Beijing Jiaotong University,School of Traffic and Transportation"],"affiliations":[{"raw_affiliation_string":"Beijing Jiaotong University,School of Traffic and Transportation","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100718179","display_name":"Ming Tang","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ming Tang","raw_affiliation_strings":["Chinese Academy of Sciences,Foundation Model Research Center, Institute of Automation"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Foundation Model Research Center, Institute of Automation","institution_ids":["https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5114654052","display_name":"Jinqiao Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinqiao Wang","raw_affiliation_strings":["Chinese Academy of Sciences,Foundation Model Research Center, Institute of Automation"],"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences,Foundation Model Research Center, Institute of Automation","institution_ids":["https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5029399748"],"corresponding_institution_ids":["https://openalex.org/I21193070"],"apc_list":null,"apc_paid":null,"fwci":1.2181,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.85399295,"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":"14813","last_page":"14820"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.7412999868392944,"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"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.7412999868392944,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.023600000888109207,"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/T10028","display_name":"Topic Modeling","score":0.022600000724196434,"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":0.6498000025749207},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5310999751091003},{"id":"https://openalex.org/keywords/correctness","display_name":"Correctness","score":0.5189999938011169},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4666000008583069},{"id":"https://openalex.org/keywords/robotics","display_name":"Robotics","score":0.38929998874664307},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.38850000500679016},{"id":"https://openalex.org/keywords/parsing","display_name":"Parsing","score":0.384799987077713},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.3456000089645386}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7439000010490417},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6498000025749207},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6097999811172485},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5310999751091003},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.5189999938011169},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4666000008583069},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40400001406669617},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.38929998874664307},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.38850000500679016},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.384799987077713},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.3456000089645386},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.34389999508857727},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.34060001373291016},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.3197999894618988},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3125999867916107},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.3068999946117401},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.29409998655319214},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.28690001368522644},{"id":"https://openalex.org/C165464430","wikidata":"https://www.wikidata.org/wiki/Q1570441","display_name":"Parameterized complexity","level":2,"score":0.2773999869823456},{"id":"https://openalex.org/C179603123","wikidata":"https://www.wikidata.org/wiki/Q1941921","display_name":"Modeling language","level":3,"score":0.27219998836517334},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.2711000144481659},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2599000036716461},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.25589999556541443},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.25279998779296875}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros60139.2025.11247436","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11247436","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":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W4383097638","https://openalex.org/W4391407102","https://openalex.org/W4392251692","https://openalex.org/W4401414182","https://openalex.org/W4401414318","https://openalex.org/W4401414856","https://openalex.org/W4401415213","https://openalex.org/W4401416769","https://openalex.org/W4402890475","https://openalex.org/W4405022959","https://openalex.org/W4405347088","https://openalex.org/W4406321977","https://openalex.org/W4409368288","https://openalex.org/W4413917664","https://openalex.org/W4414281281","https://openalex.org/W4416036482"],"related_works":[],"abstract_inverted_index":{"In":[0,209],"recent":[1],"years,":[2],"lightweight":[3,60],"large":[4],"language":[5],"models":[6],"(LLMs)":[7],"have":[8,42],"garnered":[9],"significant":[10],"attention":[11],"in":[12,29,62,105],"the":[13,57,142,171,197,204,215],"robotics":[14],"field":[15],"due":[16],"to":[17,154,187,229],"their":[18,69],"low":[19],"computational":[20],"resource":[21],"requirements":[22],"and":[23,99,134,162],"suitability":[24],"for":[25,32,95,166],"edge":[26,232],"deployment.":[27],"However,":[28],"task":[30,52,64,101,199],"planning\u2014particularly":[31],"complex":[33,63,106],"tasks":[34,184,210],"that":[35,75,193,219],"involve":[36],"dynamic":[37],"semantic":[38,129,213],"logic":[39],"reasoning\u2014lightweight":[40],"LLMs":[41,61],"underperformed.":[43],"To":[44],"address":[45],"this":[46],"limitation,":[47],"we":[48,109,149,225],"propose":[49],"a":[50,151],"novel":[51],"planner,":[53],"LightPlanner,":[54],"which":[55,178],"enhances":[56],"performance":[58],"of":[59,144,207,220],"planning":[65,102,164],"by":[66,222],"fully":[67],"leveraging":[68],"reasoning":[70],"capabilities.":[71],"Unlike":[72],"conventional":[73],"planners":[74],"use":[76],"fixed":[77],"skill":[78,97],"templates,":[79],"LightPlanner":[80,120],"controls":[81,182],"robot":[82],"actions":[83],"via":[84],"parameterized":[85],"function":[86],"calls,":[87],"dynamically":[88],"generating":[89,115],"parameter":[90,135],"values.":[91],"This":[92,140],"approach":[93],"allows":[94],"fine-grained":[96],"control":[98],"improves":[100],"success":[103,200,216],"rates":[104],"scenarios.":[107],"Furthermore,":[108],"introduce":[110],"hierarchical":[111],"deep":[112],"reasoning.":[113],"Before":[114],"each":[116],"action":[117,125,146,181,189],"decision":[118],"step,":[119],"thoroughly":[121],"considers":[122],"three":[123],"levels:":[124],"execution":[126],"(feedback":[127],"verification),":[128,133],"parsing":[130],"(goal":[131],"consistency":[132],"generation":[136],"(parameter":[137],"validity":[138],"verification).":[139],"ensures":[141],"correctness":[143],"subsequent":[145],"controls.":[147],"Additionally,":[148],"incorporate":[150],"memory":[152],"module":[153],"store":[155],"historical":[156],"actions,":[157],"thereby":[158],"reducing":[159],"context":[160],"length":[161],"enhancing":[163],"efficiency":[165],"long-term":[167],"tasks.":[168],"We":[169],"train":[170],"LightPlanner-1.5B":[172],"model":[173,195],"on":[174,231],"our":[175,194],"LightPlan-40k":[176],"dataset,":[177],"comprises":[179],"40,000":[180],"across":[183],"with":[185],"2":[186],"13":[188],"steps.":[190],"Experiments":[191],"demonstrate":[192,226],"achieves":[196],"highest":[198],"rate":[201,217],"despite":[202],"having":[203],"smallest":[205],"number":[206],"parameters.":[208],"involving":[211],"spatial":[212],"reasoning,":[214],"exceeds":[218],"ReAct":[221],"14.9%.":[223],"Moreover,":[224],"LightPlanner\u2019s":[227],"potential":[228],"operate":[230],"devices.":[233]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-11-28T00:00:00"}