{"id":"https://openalex.org/W7134256057","doi":"https://doi.org/10.48550/arxiv.2603.06243","title":"MLLMRec-R1: Incentivizing Reasoning Capability in Large Language Models for Multimodal Sequential Recommendation","display_name":"MLLMRec-R1: Incentivizing Reasoning Capability in Large Language Models for Multimodal Sequential Recommendation","publication_year":2026,"publication_date":"2026-03-06","ids":{"openalex":"https://openalex.org/W7134256057","doi":"https://doi.org/10.48550/arxiv.2603.06243"},"language":null,"primary_location":{"id":"pmh:doi:10.48550/arxiv.2603.06243","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"type":"article","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":null,"any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5128612713","display_name":"Yu Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Yu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128468423","display_name":"Yonghui Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Yonghui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128629611","display_name":"Le Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Le","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128586495","display_name":"Jiancan Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Jiancan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5117243215","display_name":"Hefei Xu","orcid":"https://orcid.org/0000-0001-7975-6844"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Hefei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5128453485","display_name":"Hui Lin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lin, Hui","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":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.29762168,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.6718000173568726,"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"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.6718000173568726,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.07530000060796738,"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":0.03460000082850456,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6504999995231628},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5906999707221985},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5577999949455261},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.5374000072479248},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5214999914169312},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5127000212669373},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.4684000015258789},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.46639999747276306}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8395000100135803},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6504999995231628},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5906999707221985},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5720999836921692},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5577999949455261},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.5374000072479248},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5214999914169312},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5142999887466431},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5127000212669373},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4684000015258789},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.46639999747276306},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.4431999921798706},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.392300009727478},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.3849000036716461},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.36730000376701355},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.3382999897003174},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3303000032901764},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.29179999232292175},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.25690001249313354},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.25609999895095825},{"id":"https://openalex.org/C2780660688","wikidata":"https://www.wikidata.org/wiki/Q25052564","display_name":"Multimodal learning","level":2,"score":0.2540999948978424},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.2531999945640564},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2522999942302704}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:doi:10.48550/arxiv.2603.06243","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"doi:10.48550/arxiv.2603.06243","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.06243","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":"pmh:doi:10.48550/arxiv.2603.06243","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"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":{"Group":[0],"relative":[1],"policy":[2],"optimization":[3],"(GRPO)":[4],"has":[5,23],"become":[6],"a":[7,167,203],"standard":[8,179],"post-training":[9],"paradigm":[10],"for":[11,58,137,210],"improving":[12,186],"reasoning":[13,35,135,208],"and":[14,22,62,73,84,118,132,155,163,185,205],"preference":[15],"alignment":[16],"in":[17,28,103],"large":[18,44],"language":[19,45],"models":[20,46],"(LLMs),":[21],"recently":[24],"shown":[25],"strong":[26],"effectiveness":[27],"LLM-based":[29],"recommender":[30],"systems.":[31],"However,":[32],"extending":[33],"GRPO-based":[34,90,134,207],"pipelines":[36],"to":[37,69,146],"multimodal":[38,43,138,153,158,211],"sequential":[39,139,212],"recommendation":[40,104],"(MSR)":[41],"with":[42,81],"(MLLMs)":[47],"faces":[48],"fundamental":[49],"obstacles.":[50],"First,":[51],"MSR":[52],"requires":[53],"jointly":[54],"encoding":[55],"visual":[56,67,143,149],"content":[57],"both":[59],"historical":[60],"interactions":[61],"multiple":[63],"candidate":[64,85],"items,":[65],"causing":[66],"tokens":[68,150],"dominate":[70],"the":[71,75],"input":[72],"making":[74],"cost":[76],"of":[77],"group-based":[78],"rollout":[79],"scale":[80],"history":[82],"length":[83],"set":[86],"size,":[87],"which":[88],"renders":[89],"training":[91,108,180],"prohibitively":[92],"expensive.":[93],"Second,":[94],"existing":[95],"Chain-of-Thought":[96],"(CoT)":[97],"supervision":[98,160],"suffers":[99],"from":[100],"reward":[101,183],"inflation":[102,184],"scenarios,":[105],"where":[106],"higher":[107],"rewards":[109],"do":[110],"not":[111],"reliably":[112],"translate":[113],"into":[114],"improved":[115],"ranking":[116],"performance":[117],"may":[119],"induce":[120],"shortcut":[121],"learning.":[122],"To":[123],"address":[124],"these":[125],"challenges,":[126],"we":[127],"propose":[128],"MLLMRec-R1,":[129],"an":[130],"efficient":[131],"stable":[133],"framework":[136],"recommendation.":[140,213],"MLLMRec-R1":[141,197],"textualizes":[142],"signals":[144],"offline":[145],"eliminate":[147],"expensive":[148],"while":[151,177],"preserving":[152],"semantics,":[154],"constructs":[156],"high-quality":[157],"CoT":[159,175],"through":[161],"refinement":[162],"confidence-aware":[164],"assessment.":[165],"Furthermore,":[166],"mixed-grained":[168],"data":[169],"augmentation":[170],"strategy":[171],"selectively":[172],"injects":[173],"reliable":[174],"samples":[176],"retaining":[178],"data,":[181],"mitigating":[182],"generalization":[187],"stability.":[188],"Extensive":[189],"experiments":[190],"on":[191],"three":[192],"benchmark":[193],"datasets":[194],"demonstrate":[195],"that":[196],"consistently":[198],"outperforms":[199],"state-of-the-art":[200],"methods,":[201],"establishing":[202],"practical":[204],"effective":[206],"pipeline":[209],"The":[214],"code":[215],"is":[216],"available":[217],"at":[218],"https://github.com/wangyu0627/MLLMRec-R1.":[219]},"counts_by_year":[],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2026-03-10T00:00:00"}