{"id":"https://openalex.org/W7166865127","doi":"https://doi.org/10.18653/v1/2026.acl-long.518","title":"Beyond Pedagogical Principles: Multi-Horizon Preference Optimization for Efficient Socratic Tutoring","display_name":"Beyond Pedagogical Principles: Multi-Horizon Preference Optimization for Efficient Socratic Tutoring","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166865127","doi":"https://doi.org/10.18653/v1/2026.acl-long.518"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.acl-long.518","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.518","pdf_url":"https://aclanthology.org/2026.acl-long.518.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.acl-long.518.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139788493","display_name":"Xin Shi","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Shi","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139771161","display_name":"Chao Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Zhang","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139843456","display_name":"Yifan Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yifan Zhu","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061124954","display_name":"Xueqiao Zhang","orcid":"https://orcid.org/0009-0003-8185-6002"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xueqiao Zhang","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010961909","display_name":"Yawei Luo","orcid":"https://orcid.org/0000-0002-7037-1806"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yawei Luo","raw_affiliation_strings":["Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I76130692"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.85394723,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"11289","last_page":"11306"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11902","display_name":"Intelligent Tutoring Systems and Adaptive Learning","score":0.7358999848365784,"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/T11902","display_name":"Intelligent Tutoring Systems and Adaptive Learning","score":0.7358999848365784,"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/T10636","display_name":"Innovative Teaching and Learning Methods","score":0.021199999377131462,"subfield":{"id":"https://openalex.org/subfields/3204","display_name":"Developmental and Educational Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10456","display_name":"Multi-Agent Systems and Negotiation","score":0.009700000286102295,"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/preference","display_name":"Preference","score":0.5250999927520752},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.3416999876499176},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.2766000032424927},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.2531999945640564},{"id":"https://openalex.org/keywords/natural","display_name":"Natural (archaeology)","score":0.24950000643730164}],"concepts":[{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.5250999927520752},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4812999963760376},{"id":"https://openalex.org/C145420912","wikidata":"https://www.wikidata.org/wiki/Q853077","display_name":"Mathematics education","level":1,"score":0.41119998693466187},{"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/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3824999928474426},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.3416999876499176},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.2766000032424927},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2531999945640564},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.24950000643730164},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.24660000205039978}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.518","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.518","pdf_url":"https://aclanthology.org/2026.acl-long.518.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.acl-long.518","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.518","pdf_url":"https://aclanthology.org/2026.acl-long.518.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5310141444206238}],"awards":[{"id":"https://openalex.org/G1661763918","display_name":null,"funder_award_id":"62293554","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1999039755","display_name":null,"funder_award_id":"2023ZD0121300","funder_id":"https://openalex.org/F4320329860","funder_display_name":"National Science and Technology Major Project"},{"id":"https://openalex.org/G6814649951","display_name":"\u667a\u80fd\u6c89\u6d78\u5f0f\u5b66\u4e60\u5173\u952e\u6280\u672f\u7814\u7a76","funder_award_id":"LZ24F020002","funder_id":"https://openalex.org/F4320338464","funder_display_name":"Natural Science Foundation of Zhejiang Province"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320329860","display_name":"National Science and Technology Major Project","ror":null},{"id":"https://openalex.org/F4320338464","display_name":"Natural Science Foundation of Zhejiang Province","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166865127.pdf","grobid_xml":"https://content.openalex.org/works/W7166865127.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0],"development":[1],"of":[2],"LLM-based":[3],"tutor":[4,54],"agents":[5,55],"faces":[6],"challenges":[7],"in":[8,21,36],"simultaneously":[9],"ensuring":[10],"adherence":[11],"to":[12,72,94,119],"pedagogical":[13,18,76,80],"principles":[14,115],"and":[15,78,116],"achieving":[16,110],"optimal":[17],"effectiveness,":[19,81],"particularly":[20],"dynamic,":[22],"multi-turn":[23],"interactions.Existing":[24],"methods":[25],"are":[26],"often":[27],"constrained":[28],"by":[29],"static":[30],"data":[31],"or":[32],"sparse":[33],"reward":[34,59,68],"signals":[35],"online":[37],"settings.To":[38],"address":[39],"this":[40,67],"gap,":[41],"we":[42],"propose":[43],"Multi-Horizon":[44],"Preference":[45],"Optimization":[46],"(MHPO),":[47],"a":[48,57,62,111],"novel":[49],"framework":[50],"that":[51,103],"iteratively":[52],"refines":[53],"using":[56],"multi-horizon":[58],"function":[60,69],"within":[61],"dynamic":[63],"teacher-student":[64],"simulation":[65],"environment.Specifically,":[66],"is":[70,83],"designed":[71],"capture":[73],"both":[74],"turn-level":[75],"quality":[77],"trajectory-level":[79],"which":[82],"estimated":[84],"via":[85],"Monte":[86],"Carlo":[87],"rollouts.We":[88],"further":[89],"investigate":[90],"two":[91],"distinct":[92],"strategies":[93],"aggregate":[95],"these":[96],"rewards":[97],"for":[98],"policy":[99],"optimization.Our":[100],"experiments":[101],"demonstrate":[102],"MHPO":[104],"significantly":[105],"enhances":[106],"base":[107],"model":[108],"performance,":[109],"superior":[112],"balance":[113],"between":[114],"effectiveness":[117],"compared":[118],"various":[120],"baselines.":[121]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}