{"id":"https://openalex.org/W7163336932","doi":"https://doi.org/10.48550/arxiv.2606.03221","title":"VirtualMLE: A Virtual ML Engineer that Optimizes Sequential Recommenders","display_name":"VirtualMLE: A Virtual ML Engineer that Optimizes Sequential Recommenders","publication_year":2026,"publication_date":"2026-06-02","ids":{"openalex":"https://openalex.org/W7163336932","doi":"https://doi.org/10.48550/arxiv.2606.03221"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.03221","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.03221","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":"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"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2606.03221","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/A5136717754","display_name":"Jingwen Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Jingwen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120301766","display_name":"Junda She","orcid":"https://orcid.org/0009-0001-6510-2353"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"She, Junda","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5137772315","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/T12535","display_name":"Machine Learning and Data Classification","score":0.24199999868869781,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.24199999868869781,"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/T11948","display_name":"Machine Learning in Materials Science","score":0.1446000039577484,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.10379999876022339,"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/heuristic","display_name":"Heuristic","score":0.6150000095367432},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.582099974155426},{"id":"https://openalex.org/keywords/bridge","display_name":"Bridge (graph theory)","score":0.5238000154495239},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5127999782562256},{"id":"https://openalex.org/keywords/reflection","display_name":"Reflection (computer programming)","score":0.4690999984741211},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.454800009727478},{"id":"https://openalex.org/keywords/cognition","display_name":"Cognition","score":0.3743000030517578},{"id":"https://openalex.org/keywords/spark","display_name":"SPARK (programming language)","score":0.34880000352859497}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7939000129699707},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.6150000095367432},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.582099974155426},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.5238000154495239},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5127999782562256},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5083000063896179},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4894999861717224},{"id":"https://openalex.org/C65682993","wikidata":"https://www.wikidata.org/wiki/Q1056451","display_name":"Reflection (computer programming)","level":2,"score":0.4690999984741211},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.454800009727478},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.3743000030517578},{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.34880000352859497},{"id":"https://openalex.org/C557471498","wikidata":"https://www.wikidata.org/wiki/Q554950","display_name":"Recommender system","level":2,"score":0.3416999876499176},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.326200008392334},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.32499998807907104},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.29019999504089355},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.288100004196167},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.2847000062465668},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.2791000008583069},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.27799999713897705},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2547999918460846},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2524000108242035}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.03221","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.03221","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2606.03221","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.03221","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":"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"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advancements":[1],"in":[2,11,26,96,177],"Large":[3],"Language":[4],"Models":[5],"(LLMs)":[6],"have":[7],"demonstrated":[8],"remarkable":[9],"capabilities":[10,64],"reasoning,":[12],"reflection,":[13,77],"and":[14,78,91,114,163,173],"tool":[15],"utilization,":[16],"unlocking":[17],"new":[18,36],"paradigms":[19],"for":[20],"automating":[21],"complex":[22],"engineering":[23],"workflows.":[24],"However,":[25],"the":[27,42,62,84,88,138,145],"domain":[28],"of":[29,45,65,75,147],"sequential":[30],"recommendation":[31,119],"(SR),":[32],"tuning":[33,149],"models":[34],"on":[35,41,104,141],"datasets":[37,134],"still":[38],"relies":[39],"heavily":[40],"manual":[43],"trial-and-error":[44],"experienced":[46],"machine":[47],"learning":[48,176],"engineers.":[49],"To":[50],"bridge":[51],"this":[52],"gap,":[53],"we":[54,126],"propose":[55],"\\textbf{VirtualMLE},":[56],"an":[57],"LLM-agent":[58],"framework":[59],"that":[60,128,157],"leverages":[61],"cognitive":[63],"LLMs":[66],"to":[67,171],"organize":[68],"recommender":[69],"optimizing":[70],"into":[71],"a":[72,97],"closed":[73],"loop":[74],"execution,":[76],"memory":[79,99,164],"update.":[80],"After":[81],"each":[82],"trial,":[83],"agent":[85],"explicitly":[86],"analyzes":[87],"observed":[89],"outcomes":[90],"stores":[92],"concise":[93],"heuristic":[94,175],"feedback":[95],"hierarchical":[98],"system.":[100],"We":[101],"evaluate":[102],"VirtualMLE":[103,116],"three":[105],"Amazon":[106],"SR":[107,178],"benchmarks":[108],"with":[109,121,161],"two":[110],"representative":[111],"backbones,":[112],"SASRec":[113],"HSTU.":[115],"reaches":[117],"competitive":[118],"quality":[120],"substantially":[122],"fewer":[123],"trials.":[124],"Furthermore,":[125],"observe":[127],"cognition":[129],"summaries":[130],"distilled":[131],"from":[132],"previous":[133],"can":[135,165],"significantly":[136],"accelerate":[137],"search":[139],"process":[140],"unseen":[142],"datasets,":[143],"demonstrating":[144],"potential":[146],"transferring":[148],"heuristics.":[150],"Overall,":[151],"our":[152],"results":[153],"provide":[154],"compelling":[155],"evidence":[156],"LLM":[158],"agents":[159],"equipped":[160],"reflection":[162],"serve":[166],"as":[167],"practical":[168],"virtual":[169],"engineers":[170],"automate":[172],"amortize":[174],"optimization.":[179],"Our":[180],"codes":[181],"are":[182],"available.":[183]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-04T00:00:00"}