{"id":"https://openalex.org/W7166855863","doi":"https://doi.org/10.18653/v1/2026.acl-long.964","title":"ReRec: Reasoning-Augmented LLM-based Recommendation Assistant via Reinforcement Fine-tuning","display_name":"ReRec: Reasoning-Augmented LLM-based Recommendation Assistant via Reinforcement Fine-tuning","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166855863","doi":"https://doi.org/10.18653/v1/2026.acl-long.964"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.acl-long.964","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.964","pdf_url":"https://aclanthology.org/2026.acl-long.964.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.964.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139833928","display_name":"Jiani Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiani Huang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139744009","display_name":"Shijie Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shijie Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115857042","display_name":"Liang-bo Ning","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liang-Bo Ning","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139843811","display_name":"Wenqi Fan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wenqi Fan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139742005","display_name":"Li Qing","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li Qing","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":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.85510438,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"21040","last_page":"21055"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10203","display_name":"Recommender Systems and Techniques","score":0.5392000079154968,"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":0.5392000079154968,"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/T10028","display_name":"Topic Modeling","score":0.05290000140666962,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.050599999725818634,"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/control","display_name":"Control (management)","score":0.328900009393692},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.2921999990940094},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.28349998593330383},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.26010000705718994},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.24420000612735748}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5618000030517578},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34439998865127563},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.328900009393692},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.2921999990940094},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.28349998593330383},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.26010000705718994},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.24420000612735748},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.24330000579357147},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.24289999902248383},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.2410999983549118}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.964","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.964","pdf_url":"https://aclanthology.org/2026.acl-long.964.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.964","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.964","pdf_url":"https://aclanthology.org/2026.acl-long.964.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":[],"awards":[{"id":"https://openalex.org/G4078110728","display_name":null,"funder_award_id":"P0048625","funder_id":"https://openalex.org/F4320322598","funder_display_name":"Hong Kong Polytechnic University"},{"id":"https://openalex.org/G4230321938","display_name":null,"funder_award_id":"P0051361","funder_id":"https://openalex.org/F4320322598","funder_display_name":"Hong Kong Polytechnic University"},{"id":"https://openalex.org/G528947399","display_name":null,"funder_award_id":"P0042693","funder_id":"https://openalex.org/F4320322598","funder_display_name":"Hong Kong Polytechnic University"}],"funders":[{"id":"https://openalex.org/F4320307285","display_name":"Impact Fund","ror":"https://ror.org/00jb20j87"},{"id":"https://openalex.org/F4320322598","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166855863.pdf","grobid_xml":"https://content.openalex.org/works/W7166855863.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"With":[0],"the":[1,34],"rise":[2],"of":[3,108],"LLMs,":[4],"there":[5],"is":[6],"an":[7],"increasing":[8],"need":[9,35],"for":[10,36,87],"intelligent":[11],"recommendation":[12,58,71],"assistants":[13],"that":[14,130],"can":[15],"handle":[16],"complex":[17,57],"queries":[18],"and":[19,78,101,110,119,135,141],"provide":[20,83],"personalized,":[21],"reasoning-driven":[22],"recommendations.LLM-based":[23],"recommenders":[24],"show":[25],"potential":[26],"but":[27],"face":[28],"challenges":[29],"in":[30,56],"multi-step":[31],"reasoning,":[32],"underscoring":[33],"reasoningaugmented":[37],"systems.To":[38],"address":[39],"this":[40],"gap,":[41],"we":[42],"propose":[43],"ReRec,":[44],"a":[45],"novel":[46],"reinforcement":[47],"finetuning":[48],"(RFT)":[49],"framework":[50,60],"designed":[51],"to":[52,82,105,123],"improve":[53],"LLM":[54,88,96],"reasoning":[55,99,107],"tasks.Our":[59],"introduces":[61],"three":[62],"key":[63],"components:":[64],"(1)":[65],"Dual-Graph":[66],"Enhanced":[67],"Reward":[68],"Shaping,":[69],"integrating":[70],"metrics":[72],"like":[73,139],"NDCG@K":[74],"with":[75],"Query":[76],"Alignment":[77,80],"Preference":[79],"Scores":[81],"fine-grained":[84],"reward":[85],"signals":[86],"optimization;":[89],"(2)":[90],"Reasoning-aware":[91],"Advantage":[92],"Estimation,":[93],"which":[94],"decomposes":[95],"outputs":[97],"into":[98],"segments":[100],"penalizes":[102],"incorrect":[103],"steps":[104],"enhance":[106],"recommendation;":[109],"(3)":[111],"Online":[112],"Curriculum":[113],"Scheduler,":[114],"dynamically":[115],"assess":[116],"query":[117],"difficulty":[118],"organize":[120],"training":[121],"curriculum":[122],"ensure":[124],"stable":[125],"learning":[126],"during":[127],"RFT.Experiments":[128],"demonstrate":[129],"ReRec":[131],"outperforms":[132],"state-of-the-art":[133],"baselines":[134],"preserves":[136],"core":[137],"abilities":[138],"instruction-following":[140],"general":[142],"knowledge.Our":[143],"codes":[144],"are":[145],"available":[146],"at":[147],"https://github.com/jiani-huang/ReRec.":[148]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}