{"id":"https://openalex.org/W4416047864","doi":"https://doi.org/10.48550/arxiv.2505.22050","title":"Reinforced Reasoning for Embodied Planning","display_name":"Reinforced Reasoning for Embodied Planning","publication_year":2025,"publication_date":"2025-05-28","ids":{"openalex":"https://openalex.org/W4416047864","doi":"https://doi.org/10.48550/arxiv.2505.22050"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2505.22050","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.22050","pdf_url":"https://arxiv.org/pdf/2505.22050","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2505.22050","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5087166824","display_name":"Di Wu","orcid":"https://orcid.org/0000-0002-6818-1886"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Wu, Di","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120317314","display_name":"Jiaxin Fan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fan, Jiaxin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120317315","display_name":"Junzhe Zang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zang, Junzhe","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120317316","display_name":"Guanbo Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Guanbo","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085841330","display_name":"Wei Yin","orcid":"https://orcid.org/0000-0003-4773-7950"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yin, Wei","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100362633","display_name":"Wenhao Li","orcid":"https://orcid.org/0000-0003-1420-8163"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Wenhao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5080621264","display_name":"Bo Jin","orcid":"https://orcid.org/0000-0001-7304-8468"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jin, Bo","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5087166824"],"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.855400025844574,"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":0.855400025844574,"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":0.04699999839067459,"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/T10586","display_name":"Robotic Path Planning Algorithms","score":0.020099999383091927,"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/embodied-cognition","display_name":"Embodied cognition","score":0.8992000222206116},{"id":"https://openalex.org/keywords/embodied-agent","display_name":"Embodied agent","score":0.5641000270843506},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5622000098228455},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5530999898910522},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.5454000234603882},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.510699987411499},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4657999873161316},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.4075999855995178},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.40070000290870667}],"concepts":[{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.8992000222206116},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6758999824523926},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5875999927520752},{"id":"https://openalex.org/C103683099","wikidata":"https://www.wikidata.org/wiki/Q5370102","display_name":"Embodied agent","level":3,"score":0.5641000270843506},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5622000098228455},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5530999898910522},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.5454000234603882},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.510699987411499},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4657999873161316},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.4075999855995178},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.40070000290870667},{"id":"https://openalex.org/C192327766","wikidata":"https://www.wikidata.org/wiki/Q1038799","display_name":"Cognitive robotics","level":3,"score":0.396699994802475},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.392300009727478},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.374099999666214},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3682999908924103},{"id":"https://openalex.org/C114073186","wikidata":"https://www.wikidata.org/wiki/Q2631895","display_name":"Automated planning and scheduling","level":2,"score":0.3431999981403351},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.3199000060558319},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3142000138759613},{"id":"https://openalex.org/C155911833","wikidata":"https://www.wikidata.org/wiki/Q3817354","display_name":"Spatial intelligence","level":2,"score":0.3140999972820282},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.3131999969482422},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.3116999864578247},{"id":"https://openalex.org/C2776010242","wikidata":"https://www.wikidata.org/wiki/Q4677575","display_name":"Active perception","level":3,"score":0.31150001287460327},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.28949999809265137},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.28519999980926514},{"id":"https://openalex.org/C193221554","wikidata":"https://www.wikidata.org/wiki/Q5153664","display_name":"Commonsense reasoning","level":2,"score":0.28459998965263367},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2736000120639801},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.257999986410141}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2505.22050","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.22050","pdf_url":"https://arxiv.org/pdf/2505.22050","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2505.22050","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2505.22050","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":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2505.22050","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.22050","pdf_url":"https://arxiv.org/pdf/2505.22050","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416047864.pdf","grobid_xml":"https://content.openalex.org/works/W4416047864.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Embodied":[0],"planning":[1,41,165],"requires":[2],"agents":[3],"to":[4,78,94,151,162],"make":[5],"coherent":[6],"multi-step":[7,95],"decisions":[8],"based":[9],"on":[10,112],"dynamic":[11],"visual":[12],"observations":[13],"and":[14,36,73,98,124,143,147],"natural":[15],"language":[16],"goals.":[17],"While":[18],"recent":[19,115],"vision-language":[20],"models":[21,135],"(VLMs)":[22],"excel":[23],"at":[24],"static":[25],"perception":[26],"tasks,":[27,120],"they":[28],"struggle":[29],"with":[30,82],"the":[31,80,100,157],"temporal":[32],"reasoning,":[33],"spatial":[34],"understanding,":[35],"commonsense":[37],"grounding":[38],"needed":[39],"for":[40,117],"in":[42,166],"interactive":[43,118],"environments.":[44,153],"In":[45],"this":[46],"work,":[47],"we":[48],"introduce":[49],"a":[50,65,69,89,114],"reinforcement":[51],"fine-tuning":[52,76],"framework":[53],"that":[54,130],"brings":[55],"R1-style":[56],"reasoning":[57,161],"enhancement":[58],"into":[59],"embodied":[60,119,167],"planning.":[61],"We":[62,86],"first":[63],"distill":[64],"high-quality":[66],"dataset":[67],"from":[68],"powerful":[70],"closed-source":[71],"model":[72,81],"perform":[74],"supervised":[75],"(SFT)":[77],"equip":[79],"structured":[83],"decision-making":[84],"priors.":[85],"then":[87],"design":[88],"rule-based":[90],"reward":[91],"function":[92],"tailored":[93],"action":[96],"quality":[97],"optimize":[99],"policy":[101],"via":[102],"Generalized":[103],"Reinforced":[104],"Preference":[105],"Optimization":[106],"(GRPO).":[107],"Our":[108],"approach":[109],"is":[110],"evaluated":[111],"Embench,":[113],"benchmark":[116],"covering":[121],"both":[122],"in-domain":[123],"out-of-domain":[125],"scenarios.":[126],"Experimental":[127],"results":[128],"show":[129],"our":[131],"method":[132],"significantly":[133],"outperforms":[134],"of":[136,159],"similar":[137],"or":[138],"larger":[139],"scale,":[140],"including":[141],"GPT-4o-mini":[142],"70B+":[144],"open-source":[145],"baselines,":[146],"exhibits":[148],"strong":[149],"generalization":[150],"unseen":[152],"This":[154],"work":[155],"highlights":[156],"potential":[158],"reinforcement-driven":[160],"advance":[163],"long-horizon":[164],"AI.":[168]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-10T00:00:00"}