{"id":"https://openalex.org/W7166646392","doi":"https://doi.org/10.48550/arxiv.2606.29424","title":"EntroRouter: Learning Efficient Model Routing via Entropy Regulation","display_name":"EntroRouter: Learning Efficient Model Routing via Entropy Regulation","publication_year":2026,"publication_date":"2026-06-28","ids":{"openalex":"https://openalex.org/W7166646392","doi":"https://doi.org/10.48550/arxiv.2606.29424"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.29424","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.29424","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,"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":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2606.29424","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5136681814","display_name":"Kaiyi Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Kaiyi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053213848","display_name":"X Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Xueliang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113034676","display_name":"Zhuocheng Gong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gong, Zhuocheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139677625","display_name":"Wei Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Wei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139644186","display_name":"Yankai Lin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lin, Yankai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.4627000093460083,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.4627000093460083,"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":0.11789999902248383,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.09790000319480896,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.6015999913215637},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.574400007724762},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.4293000102043152},{"id":"https://openalex.org/keywords/q-learning","display_name":"Q-learning","score":0.3653999865055084},{"id":"https://openalex.org/keywords/cross-entropy","display_name":"Cross entropy","score":0.32710000872612},{"id":"https://openalex.org/keywords/local-optimum","display_name":"Local optimum","score":0.31779998540878296},{"id":"https://openalex.org/keywords/principle-of-maximum-entropy","display_name":"Principle of maximum entropy","score":0.30889999866485596}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6658999919891357},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6015999913215637},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.574400007724762},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5034999847412109},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.4293000102043152},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4049000144004822},{"id":"https://openalex.org/C188116033","wikidata":"https://www.wikidata.org/wiki/Q2664563","display_name":"Q-learning","level":3,"score":0.3653999865055084},{"id":"https://openalex.org/C167981619","wikidata":"https://www.wikidata.org/wiki/Q1685498","display_name":"Cross entropy","level":3,"score":0.32710000872612},{"id":"https://openalex.org/C141934464","wikidata":"https://www.wikidata.org/wiki/Q3305386","display_name":"Local optimum","level":2,"score":0.31779998540878296},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.31610000133514404},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.30889999866485596},{"id":"https://openalex.org/C74172769","wikidata":"https://www.wikidata.org/wiki/Q1446839","display_name":"Routing (electronic design automation)","level":2,"score":0.3009999990463257},{"id":"https://openalex.org/C75782508","wikidata":"https://www.wikidata.org/wiki/Q3333633","display_name":"Cross-entropy method","level":4,"score":0.29899999499320984},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.2953999936580658},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.2937999963760376},{"id":"https://openalex.org/C2779714256","wikidata":"https://www.wikidata.org/wiki/Q25305062","display_name":"Multiple Models","level":2,"score":0.275299996137619},{"id":"https://openalex.org/C48677424","wikidata":"https://www.wikidata.org/wiki/Q6888088","display_name":"Mode (computer interface)","level":2,"score":0.26570001244544983},{"id":"https://openalex.org/C3018263672","wikidata":"https://www.wikidata.org/wiki/Q1296251","display_name":"Efficient algorithm","level":2,"score":0.2547999918460846},{"id":"https://openalex.org/C163415756","wikidata":"https://www.wikidata.org/wiki/Q126473","display_name":"Contraction (grammar)","level":2,"score":0.2535000145435333}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.29424","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.29424","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,"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":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2606.29424","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.29424","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,"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":"Preprint"},"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":{"Model":[0],"routing":[1,74],"balances":[2],"solution":[3],"accuracy":[4,140],"and":[5,21,41],"computational":[6,143],"cost":[7],"by":[8,44,145],"selecting":[9],"among":[10],"models":[11,97],"of":[12,39,47,95,136],"varying":[13],"capabilities.":[14],"While":[15],"recent":[16],"multi-round":[17],"frameworks":[18],"interleave":[19],"reasoning":[20,40],"planning,":[22],"we":[23,69,106],"identify":[24],"a":[25,72,81,93,100,111,125],"structural":[26],"failure":[27],"mode":[28],"termed":[29],"Trust":[30],"Region":[31],"Collapse.":[32],"We":[33,84],"demonstrate":[34,131],"that":[35,76,132],"the":[36,45,87,137],"deep":[37],"coupling":[38],"routing,":[42],"exacerbated":[43],"dominance":[46],"strong":[48],"pre-training":[49],"priors":[50],"under":[51],"sparse":[52],"supervision,":[53],"leads":[54],"to":[55,98,119],"degenerate":[56],"local":[57],"optima":[58],"where":[59],"capable":[60],"experts":[61],"are":[62],"systematically":[63],"suppressed.":[64],"To":[65],"decouple":[66],"these":[67],"processes,":[68],"propose":[70],"$\\textbf{EntroRouter}$,":[71],"single-round":[73],"framework":[75],"treats":[77],"entropy":[78,122],"regulation":[79],"as":[80],"core":[82],"objective.":[83],"first":[85],"initialize":[86],"policy":[88],"via":[89],"Soft":[90,112],"Supervision,":[91],"fitting":[92],"distribution":[94],"suitable":[96],"establish":[99],"high-entropy":[101],"prior":[102],"for":[103],"exploration.":[104],"Subsequently,":[105],"stabilize":[107],"Reinforcement":[108],"Learning":[109],"using":[110],"Anchor,":[113],"which":[114],"utilizes":[115],"offline":[116],"capability":[117],"estimates":[118],"orchestrate":[120],"controlled":[121],"contraction":[123],"within":[124],"safe":[126],"trust":[127],"region.":[128],"Extensive":[129],"experiments":[130],"EntroRouter":[133],"retains":[134],"98.3%":[135],"strongest":[138],"expert's":[139],"while":[141],"reducing":[142],"costs":[144],"48.25%.":[146]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-07-01T00:00:00"}