{"id":"https://openalex.org/W7214700883","doi":"https://doi.org/10.48550/arxiv.2609.35058","title":"TIDE: Teacher-Student Transition via Informative Distillation and Exploration for Agentic RL","display_name":"TIDE: Teacher-Student Transition via Informative Distillation and Exploration for Agentic RL","publication_year":2026,"publication_date":"2026-09-28","ids":{"openalex":"https://openalex.org/W7214700883","doi":"https://doi.org/10.48550/arxiv.2609.35058"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.35058","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.35058","pdf_url":"https://arxiv.org/pdf/2609.35058","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2609.35058","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5144353886","display_name":"Yibin Huang","orcid":"https://orcid.org/0009-0006-4952-435X","observed_orcids":["https://orcid.org/0009-0006-4952-435X"]},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huang, Yibin","raw_affiliation_strings":["Faculty of Computing , Harbin Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Computing , Harbin Institute of Technology","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148085379","display_name":"Xinming Xu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu, Xinming","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5153422116","display_name":"Conghui Zhu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhu, Conghui","raw_affiliation_strings":["Faculty of Computing , Harbin Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Computing , Harbin Institute of Technology","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9990000128746033,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9990000128746033,"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/T12031","display_name":"Speech and dialogue systems","score":0.00019999999494757503,"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/T12072","display_name":"Machine Learning and Algorithms","score":9.999999747378752e-05,"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/teacher-student-knowledge-distillation","display_name":"teacher-student distillation","score":0.8220000267028809},{"id":"https://openalex.org/keywords/on-policy-distillation","display_name":"on-policy distillation","score":0.9509999752044678},{"id":"https://openalex.org/keywords/agentic-reinforcement-learning","display_name":"agentic reinforcement learning","score":0.7120000123977661},{"id":"https://openalex.org/keywords/group-relative-policy-optimization","display_name":"Group Relative Policy Optimization","score":0.7039999961853027},{"id":"https://openalex.org/keywords/exploration","display_name":"exploration","score":0.43299999833106995}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6759999990463257},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.570900022983551},{"id":"https://openalex.org/C201236551","wikidata":"https://www.wikidata.org/wiki/Q7310809","display_name":"Relative value","level":2,"score":0.5543000102043152},{"id":"https://openalex.org/C68387754","wikidata":"https://www.wikidata.org/wiki/Q7271585","display_name":"Schedule","level":2,"score":0.5364999771118164},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5350000262260437},{"id":"https://openalex.org/C2777027219","wikidata":"https://www.wikidata.org/wiki/Q1284190","display_name":"Constant (computer programming)","level":2,"score":0.5189999938011169},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.4966999888420105},{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.48669999837875366},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.486299991607666},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.38909998536109924},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.32820001244544983},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3100999891757965},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.2955000102519989},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.28850001096725464},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.2809000015258789},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.25769999623298645},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.2540999948978424},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.2535000145435333}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.35058","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.35058","pdf_url":"https://arxiv.org/pdf/2609.35058","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2609.35058","doi":"https://doi.org/10.48550/arxiv.2609.35058","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.35058","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,"listed_in":[],"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2609.35058","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.35058","pdf_url":"https://arxiv.org/pdf/2609.35058","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Quality education","id":"https://metadata.un.org/sdg/4","score":0.6164000034332275}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7214700883.pdf","grobid_xml":"https://content.openalex.org/works/W7214700883.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W1821462560","https://openalex.org/W2609826708","https://openalex.org/W3126325318","https://openalex.org/W4310923309","https://openalex.org/W4391631327","https://openalex.org/W4399597391","https://openalex.org/W4403852025","https://openalex.org/W4405655184","https://openalex.org/W4407174758","https://openalex.org/W7125861034","https://openalex.org/W7126034091","https://openalex.org/W7148703720","https://openalex.org/W7150828934","https://openalex.org/W7154206010","https://openalex.org/W7154299763","https://openalex.org/W7160594571","https://openalex.org/W7161165287","https://openalex.org/W7161258139","https://openalex.org/W7162494674","https://openalex.org/W7166046835","https://openalex.org/W7166587246","https://openalex.org/W7169575253","https://openalex.org/W7169874691","https://openalex.org/W7172442714","https://openalex.org/W7172541540","https://openalex.org/W7202134906","https://openalex.org/W7203675926","https://openalex.org/W7204222579","https://openalex.org/W7204249312","https://openalex.org/W7208738284","https://openalex.org/W7213576900"],"related_works":["https://openalex.org/W7166587246","https://openalex.org/W7214957320","https://openalex.org/W7164915140","https://openalex.org/W7221505051","https://openalex.org/W7213576900","https://openalex.org/W7223141401","https://openalex.org/W7221176786","https://openalex.org/W7161258139","https://openalex.org/W7213329161","https://openalex.org/W7172399155"],"abstract_inverted_index":{"Effective":[0],"multi-turn":[1],"agents":[2],"require":[3],"interaction":[4,70],"strategies":[5],"that":[6,54,112,128],"coordinate":[7],"information":[8],"gathering,":[9],"actions,":[10],"and":[11,57,68,131,140,175,188,194,208,226,242],"feedback":[12],"over":[13,138],"long":[14],"horizons.":[15],"GRPO":[16],"is":[17,114,127],"a":[18,46,50,62,159],"reinforcement":[19],"learning":[20],"algorithm":[21],"used":[22],"to":[23],"train":[24],"these":[25],"agents,":[26],"but":[27,108,172],"sparse":[28],"trajectory-level":[29],"rewards":[30],"limit":[31],"early":[32,225],"exploration":[33,115],"in":[34,149,234],"small":[35],"models.":[36],"Recent":[37],"methods":[38],"augment":[39],"RL":[40,206],"with":[41,216],"on-policy":[42],"distillation":[43,85],"(OPD)":[44],"from":[45,91,105],"stronger":[47,222],"teacher.":[48],"However,":[49],"fixed":[51],"mixture":[52],"assumes":[53],"teacher":[55,129,223],"guidance":[56,130,224],"reward":[58,132],"optimization":[59,133],"should":[60,134],"retain":[61],"constant":[63],"relative":[64,179,191,201,231],"role":[65],"throughout":[66],"training":[67,81,139],"across":[69,143,213,237],"turns.":[71,144,214],"This":[72],"assumption":[73],"can":[74,87],"fail":[75],"at":[76],"two":[77],"scales.":[78],"Globally,":[79,151],"as":[80,158],"progresses,":[82],"maintaining":[83],"strong":[84],"pressure":[86],"constrain":[88],"the":[89,94,102,106,154,178,197,205,217,246],"model":[90],"moving":[92],"beyond":[93],"teacher's":[95],"capabilities.":[96],"Locally,":[97,183],"teacher--student":[98],"disagreement":[99,156,195,210],"identifies":[100],"where":[101],"student":[103,240],"departs":[104],"teacher,":[107],"cannot":[109],"tell":[110],"whether":[111],"departure":[113],"supported":[116],"by":[117],"better":[118],"outcomes":[119],"or":[120],"low-quality":[121],"policy":[122],"drift.":[123],"Our":[124],"methodological":[125],"insight":[126,148],"be":[135],"dynamically":[136],"rebalanced":[137],"jointly":[141,185],"allocated":[142],"We":[145],"instantiate":[146],"this":[147],"\\tide.":[150],"\\tide":[152,184,220],"uses":[153],"measured":[155],"trend":[157],"practical":[160],"schedule":[161],"signal,":[162,199],"advancing":[163],"an":[164],"OPD-to-RL":[165],"handoff":[166],"when":[167],"discrepancy":[168],"reduction":[169],"becomes":[170],"slow":[171],"remains":[173],"positive":[174],"progressively":[176],"increasing":[177],"weight":[180,232],"of":[181,248],"RL.":[182],"modulates":[186],"teacher-guided":[187],"reward-driven":[189,228],"updates:":[190],"action":[192,202],"value":[193,203],"prioritize":[196],"OPD":[198],"whereas":[200],"supplies":[204],"advantage":[207],"normalized":[209],"reweights":[211],"it":[212],"Coupled":[215],"global":[218],"handoff,":[219],"allocates":[221],"gives":[227],"updates":[229],"greater":[230],"later":[233],"training.":[235],"Experiments":[236],"multiple":[238],"benchmarks,":[239],"scales,":[241],"controlled":[243],"ablations":[244],"support":[245],"effectiveness":[247],"TIDE's":[249],"adaptive":[250],"OPD--RL":[251],"coordination.":[252]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-09-30T00:00:00"}