{"id":"https://openalex.org/W7214760404","doi":"https://doi.org/10.48550/arxiv.2609.34188","title":"AlphaPareto: Formulaic Alpha Discovery with LLM-Guided Multi-Objective Reinforcement Learning","display_name":"AlphaPareto: Formulaic Alpha Discovery with LLM-Guided Multi-Objective Reinforcement Learning","publication_year":2026,"publication_date":"2026-09-28","ids":{"openalex":"https://openalex.org/W7214760404","doi":"https://doi.org/10.48550/arxiv.2609.34188"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.34188","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.34188","pdf_url":"https://arxiv.org/pdf/2609.34188","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2609.34188","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5153484348","display_name":"Yingbo Zhao","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhao, Yingbo","raw_affiliation_strings":["School of Economics Xiamen University Fujian , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Economics Xiamen University Fujian , China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153537137","display_name":"Zeyu Yang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang, Zeyu","raw_affiliation_strings":["Institute for Studies in Economics Xiamen University Fujian , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Studies in Economics Xiamen University Fujian , China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102003533","display_name":"Zhoufan Zhu","orcid":"https://orcid.org/0000-0001-9800-6344","observed_orcids":["https://orcid.org/0000-0001-9800-6344"]},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhu, Zhoufan","raw_affiliation_strings":["School of Economics & Wang Yanan Institute for Studies in Economics Xiamen University Fujian , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Economics & Wang Yanan Institute for Studies in Economics Xiamen University Fujian , China","institution_ids":["https://openalex.org/I191208505"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I191208505"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"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/T11326","display_name":"Stock Market Forecasting Methods","score":0.98580002784729,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11326","display_name":"Stock Market Forecasting Methods","score":0.98580002784729,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10047","display_name":"Financial Markets and Investment Strategies","score":0.008899999782443047,"subfield":{"id":"https://openalex.org/subfields/2003","display_name":"Finance"},"field":{"id":"https://openalex.org/fields/20","display_name":"Economics, Econometrics and Finance"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10848","display_name":"Advanced Multi-Objective Optimization Algorithms","score":0.0013000000035390258,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/quantitative-trading","display_name":"quantitative trading","score":0.7269999980926514},{"id":"https://openalex.org/keywords/multi-objective-reinforcement-learning","display_name":"multi-objective reinforcement learning","score":0.9079999923706055},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.890999972820282},{"id":"https://openalex.org/keywords/non-stationary-markov-decision-processes","display_name":"non-stationary Markov decision processes","score":0.8379999995231628},{"id":"https://openalex.org/keywords/multi-objective-optimization","display_name":"multi-objective optimization","score":0.6290000081062317},{"id":"https://openalex.org/keywords/temporal-stability","display_name":"temporal stability","score":0.6259999871253967},{"id":"https://openalex.org/keywords/robustness-to-disturbances","display_name":"robustness to disturbances","score":0.9380000233650208},{"id":"https://openalex.org/keywords/alpha-diversity","display_name":"alpha diversity","score":0.800000011920929},{"id":"https://openalex.org/keywords/reward-function-design","display_name":"reward function design","score":0.4519999921321869}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7968999743461609},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6517000198364258},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5846999883651733},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5629000067710876},{"id":"https://openalex.org/C64943373","wikidata":"https://www.wikidata.org/wiki/Q2651003","display_name":"Alpha (finance)","level":4,"score":0.5439000129699707},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.43869999051094055},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.4226999878883362},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.40070000290870667},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.38909998536109924},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.36320000886917114},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3052999973297119},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.29980000853538513},{"id":"https://openalex.org/C98763669","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov chain","level":2,"score":0.2854999899864197},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.2768000066280365},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.2685999870300293},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.2624000012874603}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.34188","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.34188","pdf_url":"https://arxiv.org/pdf/2609.34188","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2609.34188","doi":"https://doi.org/10.48550/arxiv.2609.34188","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.34188","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2609.34188","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.34188","pdf_url":"https://arxiv.org/pdf/2609.34188","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7214760404.pdf","grobid_xml":"https://content.openalex.org/works/W7214760404.grobid-xml"},"referenced_works_count":7,"referenced_works":["https://openalex.org/W2952541584","https://openalex.org/W3008079393","https://openalex.org/W3087827640","https://openalex.org/W4391912539","https://openalex.org/W4404351574","https://openalex.org/W4414990942","https://openalex.org/W4416037885"],"related_works":["https://openalex.org/W4415271275","https://openalex.org/W4400024219","https://openalex.org/W4400277517","https://openalex.org/W7220675449","https://openalex.org/W7083818009","https://openalex.org/W7135425110","https://openalex.org/W4381795742","https://openalex.org/W7161733598","https://openalex.org/W7138201557","https://openalex.org/W4417093948"],"abstract_inverted_index":{"Formulaic":[0],"alpha":[1,42,74,88,101,107],"discovery":[2],"is":[3],"a":[4,28,60,72,111,146,166],"core":[5],"challenge":[6],"in":[7],"quantitative":[8],"trading,":[9],"as":[10,27,40],"identifying":[11],"alphas":[12],"that":[13,150,176],"work":[14],"well":[15],"together":[16],"remains":[17],"difficult.":[18],"Recent":[19],"reinforcement":[20],"learning":[21,168],"(RL)":[22],"methods":[23,58],"formulate":[24],"this":[25],"task":[26],"Markov":[29],"decision":[30],"process":[31],"(MDP),":[32],"but":[33],"two":[34],"important":[35,69],"issues":[36],"remain":[37],"unresolved.":[38],"First,":[39],"the":[41,45,51,95,100,105,118,123,128,134,142],"pool":[43],"evolves,":[44],"reward":[46,138,144,149],"function":[47],"changes":[48],"accordingly,":[49],"making":[50],"MDP":[52],"inherently":[53],"non-stationary.":[54],"Second,":[55],"most":[56],"existing":[57],"optimize":[59],"single":[61],"objective,":[62],"typically":[63],"predictive":[64,153],"power,":[65,154],"while":[66],"ignoring":[67],"other":[68],"properties":[70],"of":[71,136],"high-quality":[73],"pool.":[75,119],"Motivated":[76],"by":[77],"these":[78,163],"challenges,":[79],"we":[80],"propose":[81],"AlphaPareto,":[82],"an":[83],"RL":[84],"method":[85,179],"for":[86],"formulaic":[87],"discovery.":[89],"To":[90,132],"address":[91],"non-stationarity,":[92],"AlphaPareto":[93,140,178],"augments":[94],"state":[96],"to":[97,116,125,127,172],"include":[98],"both":[99],"under":[102],"construction":[103],"and":[104,109,159,161],"current":[106],"pool,":[108],"applies":[110],"large":[112],"language":[113],"model":[114],"(LLM)":[115],"encode":[117],"This":[120],"design":[121],"allows":[122],"agent":[124],"adapt":[126],"evolving":[129],"search":[130],"environment.":[131],"overcome":[133],"limitation":[135],"single-objective":[137],"design,":[139],"replaces":[141],"scalar":[143],"with":[145],"multi-objective":[147],"vector-valued":[148],"simultaneously":[151],"captures":[152],"temporal":[155],"stability,":[156],"perturbation":[157],"robustness,":[158],"diversity,":[160],"optimizes":[162],"objectives":[164],"through":[165],"Pareto-regularized":[167],"procedure.":[169],"Empirical":[170],"applications":[171],"real-world":[173],"datasets":[174],"show":[175],"our":[177],"outperforms":[180],"its":[181],"competitors.":[182]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-09-30T00:00:00"}