{"id":"https://openalex.org/W7161011059","doi":"https://doi.org/10.48550/arxiv.2605.11553","title":"TwiSTAR:Think Fast, Think Slow, Then Act,Generative Recommendation with Adaptive Reasoning","display_name":"TwiSTAR:Think Fast, Think Slow, Then Act,Generative Recommendation with Adaptive Reasoning","publication_year":2026,"publication_date":"2026-05-12","ids":{"openalex":"https://openalex.org/W7161011059","doi":"https://doi.org/10.48550/arxiv.2605.11553"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.11553","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.11553","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.2605.11553","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5036246048","display_name":"Shiteng Cao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cao, Shiteng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136086507","display_name":"Kaian Jiang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiang, Kaian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136088275","display_name":"Yunlong Gong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gong, Yunlong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5136075130","display_name":"Zhiheng Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Zhiheng","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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.23800000548362732,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.23800000548362732,"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/T10203","display_name":"Recommender Systems and Techniques","score":0.23119999468326569,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.1348000019788742,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.684499979019165},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.49729999899864197},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.49570000171661377},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.4544000029563904},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.429500013589859},{"id":"https://openalex.org/keywords/commonsense-reasoning","display_name":"Commonsense reasoning","score":0.42320001125335693},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.3993000090122223},{"id":"https://openalex.org/keywords/language-understanding","display_name":"Language understanding","score":0.3578000068664551},{"id":"https://openalex.org/keywords/non-monotonic-logic","display_name":"Non-monotonic logic","score":0.3402000069618225}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8194000124931335},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.684499979019165},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.590399980545044},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.49729999899864197},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.49570000171661377},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.4544000029563904},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.44350001215934753},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.429500013589859},{"id":"https://openalex.org/C193221554","wikidata":"https://www.wikidata.org/wiki/Q5153664","display_name":"Commonsense reasoning","level":2,"score":0.42320001125335693},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3993000090122223},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.3578000068664551},{"id":"https://openalex.org/C159032336","wikidata":"https://www.wikidata.org/wiki/Q2488768","display_name":"Non-monotonic logic","level":2,"score":0.3402000069618225},{"id":"https://openalex.org/C195344581","wikidata":"https://www.wikidata.org/wiki/Q2555318","display_name":"Automated reasoning","level":2,"score":0.32249999046325684},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.3174999952316284},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.3149999976158142},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.30730000138282776},{"id":"https://openalex.org/C89288958","wikidata":"https://www.wikidata.org/wiki/Q7301504","display_name":"Reasoning system","level":2,"score":0.30480000376701355},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.28790000081062317},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.28540000319480896},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.2849999964237213},{"id":"https://openalex.org/C2776999362","wikidata":"https://www.wikidata.org/wiki/Q2349274","display_name":"Planner","level":2,"score":0.2791999876499176},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.27570000290870667},{"id":"https://openalex.org/C37335422","wikidata":"https://www.wikidata.org/wiki/Q6888134","display_name":"Model-based reasoning","level":3,"score":0.26739999651908875},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.2551000118255615},{"id":"https://openalex.org/C140843580","wikidata":"https://www.wikidata.org/wiki/Q840067","display_name":"Defeasible reasoning","level":2,"score":0.2506999969482422}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.11553","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.11553","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.2605.11553","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.11553","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Generative":[0],"recommendation":[1,39],"with":[2,89],"Semantic":[3],"IDs":[4],"(SIDs)":[5],"has":[6],"emerged":[7],"as":[8],"a":[9,16,36,72,93,97,102],"promising":[10],"paradigm,":[11],"yet":[12],"existing":[13],"methods":[14],"apply":[15],"fixed":[17],"inference":[18,163],"strategy,":[19],"either":[20],"fast":[21,38,94],"direct":[22],"generation":[23],"or":[24],"slow":[25,50,103,119,168],"chain-of-thought":[26],"reasoning,":[27],"uniformly":[28],"across":[29],"all":[30],"user":[31,82],"histories.":[32],"This":[33],"approach":[34],"creates":[35],"trade-off:":[37],"model":[40,105,120],"produces":[41],"suboptimal":[42],"accuracy":[43,159],"on":[44,58,147],"hard":[45],"samples,":[46],"while":[47,161],"always":[48],"invoking":[49],"reasoning":[51,79,104],"incurs":[52],"prohibitive":[53],"latency":[54,164],"and":[55,101],"wastes":[56],"computation":[57],"easy":[59],"cases.":[60],"To":[61],"address":[62],"this,":[63],"we":[64,113],"propose":[65],"Think":[66,68],"Fast,":[67],"Slow,":[69],"Then":[70],"Act,":[71],"framework":[73],"that":[74,106,151],"learns":[75],"to":[76,144,166],"adaptively":[77],"allocate":[78],"effort":[80],"per":[81],"sequence.":[83],"Our":[84],"system":[85],"equips":[86],"an":[87],"LLM":[88],"three":[90,148],"complementary":[91],"tools:":[92],"SID-based":[95],"retriever,":[96],"lightweight":[98],"candidate":[99],"ranker,":[100],"generates":[107],"explicit":[108],"rationales":[109],"before":[110],"recommending.":[111],"Crucially,":[112],"inject":[114],"collaborative":[115],"commonsense":[116],"into":[117,125],"the":[118],"by":[121,136],"transforming":[122],"item-to-item":[123],"knowledge":[124],"natural":[126],"language":[127],"explanations.":[128],"A":[129],"planner,":[130],"trained":[131],"through":[132],"supervised":[133],"warm-up":[134],"followed":[135],"agentic":[137],"reinforcement":[138],"learning,":[139],"dynamically":[140],"decides":[141],"which":[142],"tool":[143],"invoke.":[145],"Experiments":[146],"datasets":[149],"demonstrate":[150],"our":[152],"method":[153],"outperforms":[154],"strong":[155],"baselines,":[156],"achieving":[157],"consistent":[158],"gains":[160],"reducing":[162],"compared":[165],"uniform":[167],"reasoning.":[169]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-14T00:00:00"}