{"id":"https://openalex.org/W7153354821","doi":"https://doi.org/10.48550/arxiv.2604.08232","title":"HiRO-Nav: Hybrid ReasOning Enables Efficient Embodied Navigation","display_name":"HiRO-Nav: Hybrid ReasOning Enables Efficient Embodied Navigation","publication_year":2026,"publication_date":"2026-04-09","ids":{"openalex":"https://openalex.org/W7153354821","doi":"https://doi.org/10.48550/arxiv.2604.08232"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.08232","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.08232","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":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2604.08232","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5133337486","display_name":"He Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, He","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133378132","display_name":"Yijun Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Yijun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133363264","display_name":"Zichuan Lin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lin, Zichuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133316928","display_name":"Deheng Ye","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ye, Deheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5123042037","display_name":"Chunyan Miao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Miao, Chunyan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.7242000102996826,"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":0.7242000102996826,"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":0.11299999803304672,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.02410000003874302,"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":0.545799970626831},{"id":"https://openalex.org/keywords/embodied-cognition","display_name":"Embodied cognition","score":0.5333999991416931},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.4668999910354614},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4535999894142151},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.41609999537467957},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.41260001063346863},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.4115000069141388},{"id":"https://openalex.org/keywords/embodied-agent","display_name":"Embodied agent","score":0.36250001192092896},{"id":"https://openalex.org/keywords/reasoning-system","display_name":"Reasoning system","score":0.3596999943256378}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7328000068664551},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6236000061035156},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.545799970626831},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.5333999991416931},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.4668999910354614},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4535999894142151},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42730000615119934},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.41609999537467957},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.41260001063346863},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.4115000069141388},{"id":"https://openalex.org/C103683099","wikidata":"https://www.wikidata.org/wiki/Q5370102","display_name":"Embodied agent","level":3,"score":0.36250001192092896},{"id":"https://openalex.org/C89288958","wikidata":"https://www.wikidata.org/wiki/Q7301504","display_name":"Reasoning system","level":2,"score":0.3596999943256378},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.34619998931884766},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3393000066280365},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.3147999942302704},{"id":"https://openalex.org/C74072328","wikidata":"https://www.wikidata.org/wiki/Q1142726","display_name":"Intelligent agent","level":2,"score":0.3138999938964844},{"id":"https://openalex.org/C115086926","wikidata":"https://www.wikidata.org/wiki/Q17004651","display_name":"Causal reasoning","level":3,"score":0.30630001425743103},{"id":"https://openalex.org/C159032336","wikidata":"https://www.wikidata.org/wiki/Q2488768","display_name":"Non-monotonic logic","level":2,"score":0.2980000078678131},{"id":"https://openalex.org/C20162079","wikidata":"https://www.wikidata.org/wiki/Q1151406","display_name":"Case-based reasoning","level":2,"score":0.29670000076293945},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.2838999927043915},{"id":"https://openalex.org/C192327766","wikidata":"https://www.wikidata.org/wiki/Q1038799","display_name":"Cognitive robotics","level":3,"score":0.2815000116825104},{"id":"https://openalex.org/C195344581","wikidata":"https://www.wikidata.org/wiki/Q2555318","display_name":"Automated reasoning","level":2,"score":0.28029999136924744},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.2777000069618225},{"id":"https://openalex.org/C50897621","wikidata":"https://www.wikidata.org/wiki/Q2665508","display_name":"Hybrid system","level":2,"score":0.2637999951839447},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.25600001215934753},{"id":"https://openalex.org/C13687954","wikidata":"https://www.wikidata.org/wiki/Q4826847","display_name":"Autonomous agent","level":2,"score":0.25519999861717224}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.08232","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.08232","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":"doi:10.48550/arxiv.2604.08232","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.08232","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":"article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Embodied":[0],"navigation":[1,47,112],"agents":[2,52],"built":[3],"upon":[4],"large":[5],"reasoning":[6,18,36,67,185,190],"models":[7],"(LRMs)":[8],"can":[9,34],"handle":[10],"complex,":[11],"multimodal":[12],"environmental":[13],"input":[14],"and":[15,43,126,146,220,226],"perform":[16,90],"grounded":[17],"per":[19],"step":[20,94],"to":[21,55,89,159,187],"improve":[22],"sequential":[23],"decision-making":[24],"for":[25,45,192],"long-horizon":[26,46],"tasks.":[27],"However,":[28],"a":[29,118,164,173,214],"critical":[30,137],"question":[31],"remains:":[32],"\\textit{how":[33],"the":[35,79,105,111,131,141,182,206],"capabilities":[37],"of":[38,82,85,121],"LRMs":[39],"be":[40],"harnessed":[41],"intelligently":[42],"efficiently":[44],"tasks?}":[48],"In":[49],"simple":[50],"scenes,":[51],"are":[53],"expected":[54],"act":[56],"reflexively,":[57],"while":[58,199],"in":[59,65],"complex":[60],"ones":[61],"they":[62],"should":[63],"engage":[64],"deliberate":[66],"before":[68],"acting.To":[69],"achieve":[70],"this,":[71],"we":[72,114,162],"introduce":[73],"\\textbf{H}ybr\\textbf{i}d":[74],"\\textbf{R}eas\\textbf{O}ning":[75],"\\textbf{Nav}igation":[76],"(\\textbf{HiRO-Nav})":[77],"agent,":[78],"first":[80],"kind":[81],"agent":[83,132],"capable":[84],"adaptively":[86],"determining":[87],"whether":[88],"thinking":[91],"at":[92],"every":[93],"based":[95],"on":[96,205],"its":[97],"own":[98],"action":[99,107,144],"entropy.":[100],"Specifically,":[101],"by":[102,177],"examining":[103],"how":[104],"agent's":[106],"entropy":[108,145],"evolves":[109],"over":[110],"trajectories,":[113],"observed":[115],"that":[116,152,211],"only":[117,191],"small":[119],"fraction":[120],"actions":[122,128,155],"exhibit":[123],"high":[124],"entropy,":[125],"these":[127],"often":[129],"steer":[130],"toward":[133],"novel":[134],"scenes":[135],"or":[136],"objects.":[138],"Furthermore,":[139],"studying":[140],"relationship":[142],"between":[143,217],"task":[147,160],"completion":[148],"(i.e.,":[149],"Q-value)":[150],"reveals":[151],"improving":[153,200],"high-entropy":[154,193],"contributes":[156],"more":[157],"positively":[158],"success.Hence,":[161],"propose":[163],"tailored":[165],"training":[166],"pipeline":[167],"comprising":[168],"hybrid":[169,184],"supervised":[170],"fine-tuning":[171],"as":[172],"cold":[174],"start,":[175],"followed":[176],"online":[178],"reinforcement":[179],"learning":[180],"with":[181],"proposed":[183],"strategy":[186],"explicitly":[188],"activate":[189],"actions,":[194],"significantly":[195],"reducing":[196],"computational":[197],"overhead":[198],"decision":[201],"quality.":[202],"Extensive":[203],"experiments":[204],"\\textsc{CHORES}-$\\mathbb{S}$":[207],"ObjectNav":[208],"benchmark":[209],"showcases":[210],"HiRO-Nav":[212],"achieves":[213],"better":[215],"trade-off":[216],"success":[218],"rates":[219],"token":[221],"efficiency":[222],"than":[223],"both":[224],"dense-thinking":[225],"no-thinking":[227],"baselines.":[228]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-04-11T00:00:00"}