{"id":"https://openalex.org/W7162797745","doi":"https://doi.org/10.48550/arxiv.2605.29940","title":"Make LLM Learn to Synthesize from Streaming Experiences through Feedback","display_name":"Make LLM Learn to Synthesize from Streaming Experiences through Feedback","publication_year":2026,"publication_date":"2026-05-28","ids":{"openalex":"https://openalex.org/W7162797745","doi":"https://doi.org/10.48550/arxiv.2605.29940"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.29940","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.29940","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":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.29940","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5137379911","display_name":"Zhenlin Hu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hu, Zhenlin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137371299","display_name":"Yan Wang","orcid":"https://orcid.org/0000-0001-7265-778X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Yan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137388381","display_name":"Zhen Bi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bi, Zhen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123295002","display_name":"Zihao Xue","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xue, Zihao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016024790","display_name":"Bingyu Zhu","orcid":"https://orcid.org/0000-0002-7286-8955"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhu, Bingyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137397810","display_name":"Longtao Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Longtao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137387921","display_name":"Xiongtao Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Xiongtao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137397387","display_name":"Zeyu Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Zeyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137373129","display_name":"Zhixuan Chu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chu, Zhixuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5137311225","display_name":"Jungang Lou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lou, Jungang","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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.1462000012397766,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.1462000012397766,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.11630000174045563,"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/T10028","display_name":"Topic Modeling","score":0.10409999638795853,"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":0.7071999907493591},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.640500009059906},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5774000287055969},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4650999903678894},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.45419999957084656},{"id":"https://openalex.org/keywords/synthetic-data","display_name":"Synthetic data","score":0.38600000739097595},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.31859999895095825}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7379000186920166},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7071999907493591},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.640500009059906},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5774000287055969},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4846000075340271},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4650999903678894},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.45419999957084656},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42660000920295715},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.38600000739097595},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32739999890327454},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.31859999895095825},{"id":"https://openalex.org/C2781316041","wikidata":"https://www.wikidata.org/wiki/Q1230584","display_name":"Diversity (politics)","level":2,"score":0.2809000015258789},{"id":"https://openalex.org/C2776449333","wikidata":"https://www.wikidata.org/wiki/Q7928781","display_name":"View synthesis","level":3,"score":0.2784999907016754},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.2653999924659729},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.25769999623298645},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.2572000026702881},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2567000091075897},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.25519999861717224}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.29940","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.29940","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":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.29940","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.29940","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":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"language":[1],"models":[2,92],"(LLMs)":[3],"have":[4],"been":[5],"widely":[6],"adopted":[7],"for":[8,76,107,161],"synthetic":[9,168],"data":[10,105,169],"generation,":[11],"significantly":[12],"reducing":[13],"annotation":[14],"costs.":[15],"However,":[16],"most":[17],"existing":[18],"studies":[19],"treat":[20],"synthesis":[21,64,91,96,117,148],"as":[22,129,171],"a":[23,30,35,59,86,99],"set":[24],"of":[25,103,164],"isolated":[26],"tasks":[27,46,65,72,130,145],"and":[28,47,68,122,166],"overlook":[29],"more":[31],"fundamental":[32],"question:":[33],"whether":[34],"model":[36,113],"can":[37,176],"learn":[38,119],"to":[39,50,93,114,146],"synthesize":[40],"by":[41],"accumulating":[42],"experience":[43,69,97,142],"from":[44,70,120,143,178],"past":[45],"transferring":[48],"it":[49],"future":[51,77],"ones.":[52],"In":[53],"this":[54,81],"work,":[55],"we":[56,83],"introduce":[57],"StreamSynth,":[58],"new":[60],"setting":[61],"in":[62],"which":[63],"arrive":[66],"sequentially":[67],"historical":[71],"provides":[73],"informative":[74],"signals":[75],"synthesis.":[78],"To":[79],"address":[80],"setting,":[82],"propose":[84],"SynLearner,":[85],"general":[87],"framework":[88],"that":[89,138,175],"enables":[90],"acquire":[94],"reusable":[95],"over":[98],"task":[100,179],"stream.":[101],"Instead":[102],"generating":[104],"independently":[106],"each":[108],"task,":[109],"SynLearner":[110,139],"encourages":[111],"the":[112,162],"explore":[115],"diverse":[116],"patterns,":[118],"feedback,":[121],"balance":[123],"sample":[124],"quality":[125],"with":[126],"set-level":[127],"diversity":[128],"evolve.":[131],"Extensive":[132],"experiments":[133],"across":[134],"multiple":[135],"benchmarks":[136],"show":[137],"effectively":[140],"leverages":[141],"earlier":[144],"improve":[147],"performance":[149],"on":[150],"later":[151],"ones,":[152],"exhibiting":[153],"consistent":[154],"cross-task":[155],"transferability.":[156],"These":[157],"findings":[158],"provide":[159],"evidence":[160],"feasibility":[163],"StreamSynth":[165],"highlight":[167],"generation":[170],"an":[172],"experience-driven":[173],"process":[174],"benefit":[177],"streams.":[180]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-30T00:00:00"}