{"id":"https://openalex.org/W7223048865","doi":"https://doi.org/10.13140/rg.2.2.27792.16642","title":"OptScientist: Automated Discovery of Optimization Laws","display_name":"OptScientist: Automated Discovery of Optimization Laws","publication_year":2026,"publication_date":"2026-10-20","ids":{"openalex":"https://openalex.org/W7223048865","doi":"https://doi.org/10.13140/rg.2.2.27792.16642"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.28562","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.28562","pdf_url":"https://arxiv.org/pdf/2610.28562","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/2610.28562","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5143936772","display_name":"Ma Zhenyao","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ma Zhenyao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135259902","display_name":"Yue Liang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yue Liang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5018060667","display_name":"Jian-Qiao Zhu","orcid":"https://orcid.org/0000-0003-0133-9551","observed_orcids":["https://orcid.org/0000-0003-0133-9551"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jian-Qiao Zhu","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":true,"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/T11206","display_name":"Model Reduction and Neural Networks","score":0.322299987077713,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11206","display_name":"Model Reduction and Neural Networks","score":0.322299987077713,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.15199999511241913,"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":0.04800000041723251,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/automated-scientific-discovery","display_name":"automated scientific discovery","score":0.984000027179718},{"id":"https://openalex.org/keywords/model-discovery","display_name":"model discovery","score":0.39500001072883606},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.7739999890327454},{"id":"https://openalex.org/keywords/llm-based-agents","display_name":"LLM agents","score":0.7559999823570251},{"id":"https://openalex.org/keywords/decision-making-under-risk","display_name":"decision making under risk","score":0.8939999938011169},{"id":"https://openalex.org/keywords/central-bank-monetary-policy","display_name":"central bank monetary policy","score":0.7960000038146973},{"id":"https://openalex.org/keywords/theory-development","display_name":"theory development","score":0.5899999737739563}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5644999742507935},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.3400999903678894},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.29899999499320984},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.2892000079154968},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.27709999680519104},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.2563000023365021},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.25380000472068787},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.22840000689029694},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.22540000081062317},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.22220000624656677}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:arXiv.org:2610.28562","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.28562","pdf_url":"https://arxiv.org/pdf/2610.28562","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.2610.28562","doi":"https://doi.org/10.48550/arxiv.2610.28562","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.28562","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},{"id":"doi:10.13140/rg.2.2.27792.16642","doi":"https://doi.org/10.13140/rg.2.2.27792.16642","is_oa":false,"landing_page_url":"https://doi.org/10.13140/rg.2.2.27792.16642","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2610.28562","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.28562","pdf_url":"https://arxiv.org/pdf/2610.28562","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":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7223048865.pdf","grobid_xml":"https://content.openalex.org/works/W7223048865.grobid-xml"},"referenced_works_count":7,"referenced_works":["https://openalex.org/W4368303491","https://openalex.org/W4402413193","https://openalex.org/W7131320074","https://openalex.org/W7164389425","https://openalex.org/W7165385035","https://openalex.org/W7166043594","https://openalex.org/W7202183629"],"related_works":["https://openalex.org/W7206173079","https://openalex.org/W2491838130","https://openalex.org/W7162454801","https://openalex.org/W4400621664","https://openalex.org/W7136918992","https://openalex.org/W3206928367","https://openalex.org/W7119102778","https://openalex.org/W7201984300","https://openalex.org/W3129659301","https://openalex.org/W7202257420"],"abstract_inverted_index":{"Many":[0],"scientific":[1,14,87,181],"phenomena":[2],"are":[3],"best":[4],"understood":[5],"as":[6,59],"outcomes":[7],"of":[8,111,124],"underlying":[9,94],"optimization":[10,38,51,61,114,155,185],"problems,":[11,115],"yet":[12],"automated":[13,32,180,192],"discovery":[15,80,182],"has":[16],"largely":[17],"focused":[18],"on":[19,106],"recovering":[20],"equations":[21],"that":[22,48,82,157,187],"describe":[23],"observed":[24,189],"input-output":[25],"patterns.":[26],"We":[27,102],"introduce":[28],"OptScientist,":[29],"a":[30,46,79,108],"novel":[31,109],"framework":[33],"for":[34,121],"discovering":[35],"compact":[36,153],"symbolic":[37,50,67,154],"laws":[39,120,156,186],"directly":[40],"from":[41,86],"data.":[42],"OptScientist":[43,105,117,151,178],"comprises":[44],"(i)":[45],"model":[47,77],"infers":[49],"problems":[52,126],"by":[53],"first":[54,103],"learning":[55],"to":[56,100,130,183],"represent":[57],"data":[58,99],"an":[60,71],"problem":[62],"and":[63,69,96,127,139,147,170,200],"then":[64],"extracting":[65],"its":[66],"form,":[68],"(ii)":[70],"LLM":[72,175],"agentic":[73],"system":[74],"embedding":[75],"the":[76,125,196],"in":[78],"process":[81],"integrates":[83],"theoretical":[84],"priors":[85],"literature,":[88],"discovers":[89,152],"candidate":[90],"laws,":[91],"abstracts":[92],"their":[93],"mechanisms,":[95],"suggests":[97],"new":[98],"collect.":[101],"evaluate":[104],"OptFeynman,":[107],"benchmark":[110],"99":[112],"physics-derived":[113],"where":[116],"recovers":[118],"ground-truth":[119],"over":[122],"80%":[123],"remains":[128],"robust":[129],"noisy":[131],"contextual":[132],"information,":[133],"while":[134,166],"substantially":[135,171],"outperforming":[136],"machine-learning,":[137],"symbolic,":[138],"LLM-based":[140],"model-discovery":[141],"baselines.":[142,176],"On":[143],"human":[144],"risky":[145],"choice":[146],"central-bank":[148],"monetary":[149],"policy,":[150],"achieve":[158],"held-out":[159],"predictive":[160],"performance":[161],"competitive":[162],"with":[163],"leading":[164],"baselines,":[165],"using":[167],"few":[168],"parameters":[169],"fewer":[172],"tokens":[173],"than":[174],"Overall,":[177],"extends":[179],"uncovering":[184],"generate":[188],"phenomena,":[190],"enabling":[191],"theory":[193],"building":[194],"across":[195],"physical,":[197],"biological,":[198],"behavioral,":[199],"social":[201],"sciences.":[202]},"counts_by_year":[],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2026-10-21T00:00:00"}