{"id":"https://openalex.org/W7129626850","doi":"https://doi.org/10.48550/arxiv.2602.15005","title":"Learning User Interests via Reasoning and Distillation for Cross-Domain News Recommendation","display_name":"Learning User Interests via Reasoning and Distillation for Cross-Domain News Recommendation","publication_year":2026,"publication_date":"2026-02-16","ids":{"openalex":"https://openalex.org/W7129626850","doi":"https://doi.org/10.48550/arxiv.2602.15005"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2602.15005","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2602.15005","pdf_url":"https://arxiv.org/pdf/2602.15005","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2602.15005","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100597438","display_name":"Mengdan Zhu","orcid":"https://orcid.org/0009-0001-3881-2966","observed_orcids":["https://orcid.org/0009-0001-3881-2966"]},"institutions":[{"id":"https://openalex.org/I150468666","display_name":"Emory University","ror":"https://ror.org/03czfpz43","country_code":"US","type":"education","lineage":["https://openalex.org/I150468666"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhu, Mengdan","raw_affiliation_strings":["Emory University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Emory University","institution_ids":["https://openalex.org/I150468666"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126180729","display_name":"Yufan Zhao","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I150468666","display_name":"Emory University","ror":"https://ror.org/03czfpz43","country_code":"US","type":"education","lineage":["https://openalex.org/I150468666"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhao, Yufan","raw_affiliation_strings":["Emory University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Emory University","institution_ids":["https://openalex.org/I150468666"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112900210","display_name":"Tao Di","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I150468666","display_name":"Emory University","ror":"https://ror.org/03czfpz43","country_code":"US","type":"education","lineage":["https://openalex.org/I150468666"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Di, Tao","raw_affiliation_strings":["Emory University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Emory University","institution_ids":["https://openalex.org/I150468666"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100517990","display_name":"Yulan Yan","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I150468666","display_name":"Emory University","ror":"https://ror.org/03czfpz43","country_code":"US","type":"education","lineage":["https://openalex.org/I150468666"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yan, Yulan","raw_affiliation_strings":["Emory University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Emory University","institution_ids":["https://openalex.org/I150468666"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5126187952","display_name":"Liang Zhao","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I150468666","display_name":"Emory University","ror":"https://ror.org/03czfpz43","country_code":"US","type":"education","lineage":["https://openalex.org/I150468666"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhao, Liang","raw_affiliation_strings":["Emory University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Emory University","institution_ids":["https://openalex.org/I150468666"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I150468666"],"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/T10203","display_name":"Recommender Systems and Techniques","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10203","display_name":"Recommender Systems and Techniques","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.0008999999845400453,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.0,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/user-interest-modeling","display_name":"user interest modeling","score":0.9430000185966492},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.7160000205039978},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"reinforcement learning","score":0.6850000023841858},{"id":"https://openalex.org/keywords/group-relative-policy-optimization","display_name":"Group Relative Policy Optimization","score":0.6880000233650208},{"id":"https://openalex.org/keywords/model-capacity","display_name":"model capacity","score":0.5350000262260437},{"id":"https://openalex.org/keywords/on-policy-distillation","display_name":"on-policy distillation","score":0.8349999785423279},{"id":"https://openalex.org/keywords/knowledge-distillation","display_name":"knowledge distillation","score":0.8379999995231628}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8184000253677368},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.725600004196167},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.6201000213623047},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5199999809265137},{"id":"https://openalex.org/C557471498","wikidata":"https://www.wikidata.org/wiki/Q554950","display_name":"Recommender system","level":2,"score":0.5184000134468079},{"id":"https://openalex.org/C2776207758","wikidata":"https://www.wikidata.org/wiki/Q5303302","display_name":"Downstream (manufacturing)","level":2,"score":0.5080000162124634},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.4661000072956085},{"id":"https://openalex.org/C190839683","wikidata":"https://www.wikidata.org/wiki/Q2448197","display_name":"Train","level":2,"score":0.4334000051021576},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.41670000553131104},{"id":"https://openalex.org/C2778348673","wikidata":"https://www.wikidata.org/wiki/Q739302","display_name":"Production (economics)","level":2,"score":0.4115999937057495},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.3944999873638153},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.32760000228881836},{"id":"https://openalex.org/C73602740","wikidata":"https://www.wikidata.org/wiki/Q7795822","display_name":"Thompson sampling","level":3,"score":0.2962000072002411},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.29510000348091125},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.28999999165534973},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.28700000047683716},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.27709999680519104},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.271699994802475},{"id":"https://openalex.org/C67712803","wikidata":"https://www.wikidata.org/wiki/Q7901853","display_name":"User modeling","level":3,"score":0.2711000144481659},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.2660999894142151},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.25839999318122864},{"id":"https://openalex.org/C180505990","wikidata":"https://www.wikidata.org/wiki/Q498267","display_name":"News aggregator","level":2,"score":0.2574000060558319},{"id":"https://openalex.org/C2777622855","wikidata":"https://www.wikidata.org/wiki/Q7901844","display_name":"User information","level":3,"score":0.25519999861717224},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.25209999084472656}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2602.15005","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2602.15005","pdf_url":"https://arxiv.org/pdf/2602.15005","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2602.15005","doi":"https://doi.org/10.48550/arxiv.2602.15005","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.15005","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2602.15005","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2602.15005","pdf_url":"https://arxiv.org/pdf/2602.15005","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7129626850.pdf","grobid_xml":"https://content.openalex.org/works/W7129626850.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4412377864","https://openalex.org/W4414692774","https://openalex.org/W4385654080","https://openalex.org/W4366399505","https://openalex.org/W4413853808","https://openalex.org/W7172498289","https://openalex.org/W3118702828","https://openalex.org/W4224315167","https://openalex.org/W4414647313","https://openalex.org/W7161797507"],"abstract_inverted_index":{"News":[0],"recommendation":[1,18,162,174],"plays":[2],"a":[3,63,90,135,140,159],"critical":[4],"role":[5],"in":[6,40,54,158,167],"online":[7,155],"news":[8,17,34,78,161],"platforms":[9],"by":[10],"helping":[11],"users":[12],"discover":[13],"relevant":[14],"content.":[15],"Cross-domain":[16],"further":[19],"requires":[20],"inferring":[21],"user's":[22],"underlying":[23],"information":[24],"needs":[25],"from":[26,81,134],"heterogeneous":[27],"signals":[28],"that":[29,67,120],"often":[30],"extend":[31],"beyond":[32,42],"direct":[33],"consumption.":[35],"A":[36],"key":[37],"challenge":[38],"lies":[39],"moving":[41],"surface-level":[43],"behaviors":[44],"to":[45,72,129,139],"capture":[46],"deeper,":[47],"reusable":[48],"user":[49,83],"interests":[50],"while":[51],"maintaining":[52],"scalability":[53],"large-scale":[55,154],"production":[56,160],"systems.":[57],"In":[58],"this":[59],"paper,":[60],"we":[61,125],"present":[62],"reinforcement":[64],"learning":[65],"framework":[66],"trains":[68],"large":[69],"language":[70],"models":[71],"generate":[73],"high-quality":[74],"lists":[75],"of":[76],"interest-driven":[77],"search":[79],"queries":[80],"cross-domain":[82],"signals.":[84,100],"We":[85,101],"formulate":[86],"query-list":[87],"generation":[88],"as":[89],"policy":[91,133],"optimization":[92],"problem":[93],"and":[94,109,112,153,172],"employ":[95],"GRPO":[96],"with":[97,117],"multiple":[98],"reward":[99],"systematically":[102],"study":[103],"two":[104],"compute":[105,119],"dimensions:":[106],"inference-time":[107],"sampling":[108],"model":[110,143],"capacity,":[111],"empirically":[113],"observe":[114],"consistent":[115,165],"improvements":[116],"increased":[118],"exhibit":[121],"scaling-like":[122],"behavior.":[123],"Finally,":[124],"perform":[126],"on-policy":[127],"distillation":[128],"transfer":[130],"the":[131],"learned":[132],"large,":[136],"compute-intensive":[137],"teacher":[138],"compact":[141],"student":[142],"suitable":[144],"for":[145],"scalable":[146],"deployment.":[147],"Extensive":[148],"offline":[149],"experiments,":[150],"ablation":[151],"studies":[152],"A/B":[156],"tests":[157],"system":[163],"demonstrate":[164],"gains":[166],"both":[168],"interest":[169],"modeling":[170],"quality":[171],"downstream":[173],"performance.":[175]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-02-18T00:00:00"}