{"id":"https://openalex.org/W4416588281","doi":"https://doi.org/10.1088/2632-2153/ae2382","title":"LLM-guided chemical process optimization with a multi-agent approach","display_name":"LLM-guided chemical process optimization with a multi-agent approach","publication_year":2025,"publication_date":"2025-11-24","ids":{"openalex":"https://openalex.org/W4416588281","doi":"https://doi.org/10.1088/2632-2153/ae2382"},"language":"en","primary_location":{"id":"doi:10.1088/2632-2153/ae2382","is_oa":true,"landing_page_url":"https://doi.org/10.1088/2632-2153/ae2382","pdf_url":null,"source":{"id":"https://openalex.org/S4210200687","display_name":"Machine Learning Science and Technology","issn_l":"2632-2153","issn":["2632-2153"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320083","host_organization_name":"IOP Publishing","host_organization_lineage":["https://openalex.org/P4310320083","https://openalex.org/P4310311669"],"host_organization_lineage_names":["IOP Publishing","Institute of Physics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning: Science and Technology","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1088/2632-2153/ae2382","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5041727032","display_name":"Tianqin Zeng","orcid":"https://orcid.org/0009-0001-7416-8522"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Tong Zeng","raw_affiliation_strings":["Carnegie Mellon University, 5000 Forbes Avenue, Pittsburgh, 15213-3815, UNITED STATES"],"raw_orcid":"https://orcid.org/0009-0001-7416-8522","affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, 5000 Forbes Avenue, Pittsburgh, 15213-3815, UNITED STATES","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100279325","display_name":"Srivathsan Badrinarayanan","orcid":"https://orcid.org/0009-0004-6517-3145"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Srivathsan Badrinarayanan","raw_affiliation_strings":["Carnegie Mellon University, 5000 Forbes Avenue, Pittsburgh, Pennsylvania, 15213-3815, UNITED STATES"],"raw_orcid":"https://orcid.org/0009-0004-6517-3145","affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, 5000 Forbes Avenue, Pittsburgh, Pennsylvania, 15213-3815, UNITED STATES","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001832896","display_name":"Janghoon Ock","orcid":"https://orcid.org/0009-0000-0370-4212"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Janghoon Ock","raw_affiliation_strings":["Carnegie Mellon University, 5000 Forbes Avenue, Pittsburgh, Pennsylvania, 15213-3815, UNITED STATES"],"raw_orcid":"https://orcid.org/0009-0000-0370-4212","affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, 5000 Forbes Avenue, Pittsburgh, Pennsylvania, 15213-3815, UNITED STATES","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108995751","display_name":"Cheng-Kai Lai","orcid":"https://orcid.org/0009-0009-2118-2935"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Cheng-Kai Lai","raw_affiliation_strings":["Department of Chemical Engineering, Carnegie Mellon University, 5000 Forbes Avenue, Pittsburgh, 15213-3815, UNITED STATES"],"raw_orcid":"https://orcid.org/0009-0009-2118-2935","affiliations":[{"raw_affiliation_string":"Department of Chemical Engineering, Carnegie Mellon University, 5000 Forbes Avenue, Pittsburgh, 15213-3815, UNITED STATES","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008745801","display_name":"Amir Barati Farimani","orcid":"https://orcid.org/0000-0002-2952-8576"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Amir Barati Farimani","raw_affiliation_strings":["Mechanical Engineering, Carnegie Mellon University, 5000 Forbes Avenue, Pittsburgh, Pennsylvania, 15213-3815, UNITED STATES"],"raw_orcid":"https://orcid.org/0000-0002-2952-8576","affiliations":[{"raw_affiliation_string":"Mechanical Engineering, Carnegie Mellon University, 5000 Forbes Avenue, Pittsburgh, Pennsylvania, 15213-3815, UNITED STATES","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5001832896","https://openalex.org/A5008745801","https://openalex.org/A5041727032","https://openalex.org/A5100279325","https://openalex.org/A5108995751"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":{"value":1600,"currency":"GBP","value_usd":1962},"apc_paid":{"value":1600,"currency":"GBP","value_usd":1962},"fwci":6.5993,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.97017385,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":100},"biblio":{"volume":"6","issue":"4","first_page":"045067","last_page":"045067"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11053","display_name":"Process Optimization and Integration","score":0.8120999932289124,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11053","display_name":"Process Optimization and Integration","score":0.8120999932289124,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.07450000196695328,"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/T11407","display_name":"Innovative Microfluidic and Catalytic Techniques Innovation","score":0.01269999984651804,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/bayesian-optimization","display_name":"Bayesian optimization","score":0.7597000002861023},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5598999857902527},{"id":"https://openalex.org/keywords/constrained-optimization","display_name":"Constrained optimization","score":0.5238000154495239},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.5095999836921692},{"id":"https://openalex.org/keywords/grid","display_name":"Grid","score":0.48249998688697815},{"id":"https://openalex.org/keywords/optimization-problem","display_name":"Optimization problem","score":0.4652000069618225},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.444599986076355},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.42570000886917114},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.421099990606308}],"concepts":[{"id":"https://openalex.org/C2778049539","wikidata":"https://www.wikidata.org/wiki/Q17002908","display_name":"Bayesian optimization","level":2,"score":0.7597000002861023},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.6705999970436096},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6614999771118164},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5598999857902527},{"id":"https://openalex.org/C55660270","wikidata":"https://www.wikidata.org/wiki/Q5164377","display_name":"Constrained optimization","level":2,"score":0.5238000154495239},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.5095999836921692},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.48249998688697815},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.4652000069618225},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.444599986076355},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.42570000886917114},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.421099990606308},{"id":"https://openalex.org/C115952470","wikidata":"https://www.wikidata.org/wiki/Q332172","display_name":"Process optimization","level":2,"score":0.3944999873638153},{"id":"https://openalex.org/C193254401","wikidata":"https://www.wikidata.org/wiki/Q2160088","display_name":"Robust optimization","level":2,"score":0.3598000109195709},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.35249999165534973},{"id":"https://openalex.org/C122357587","wikidata":"https://www.wikidata.org/wiki/Q6934508","display_name":"Multi-swarm optimization","level":3,"score":0.34689998626708984},{"id":"https://openalex.org/C110850998","wikidata":"https://www.wikidata.org/wiki/Q5377895","display_name":"Engineering optimization","level":3,"score":0.3310999870300293},{"id":"https://openalex.org/C92995354","wikidata":"https://www.wikidata.org/wiki/Q5165499","display_name":"Continuous optimization","level":4,"score":0.30880001187324524},{"id":"https://openalex.org/C68781425","wikidata":"https://www.wikidata.org/wiki/Q2052203","display_name":"Multi-objective optimization","level":2,"score":0.30640000104904175},{"id":"https://openalex.org/C143587482","wikidata":"https://www.wikidata.org/wiki/Q1543216","display_name":"Iterative and incremental development","level":2,"score":0.29980000853538513},{"id":"https://openalex.org/C85617194","wikidata":"https://www.wikidata.org/wiki/Q2072794","display_name":"Particle swarm optimization","level":2,"score":0.2971999943256378},{"id":"https://openalex.org/C29282572","wikidata":"https://www.wikidata.org/wiki/Q16977029","display_name":"Derivative-free optimization","level":4,"score":0.28769999742507935},{"id":"https://openalex.org/C44616089","wikidata":"https://www.wikidata.org/wiki/Q30158686","display_name":"Constraint satisfaction","level":3,"score":0.2766999900341034},{"id":"https://openalex.org/C161036016","wikidata":"https://www.wikidata.org/wiki/Q956095","display_name":"Theory of constraints","level":2,"score":0.26989999413490295},{"id":"https://openalex.org/C174998907","wikidata":"https://www.wikidata.org/wiki/Q357662","display_name":"Work in process","level":2,"score":0.2630999982357025},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.26089999079704285}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1088/2632-2153/ae2382","is_oa":true,"landing_page_url":"https://doi.org/10.1088/2632-2153/ae2382","pdf_url":null,"source":{"id":"https://openalex.org/S4210200687","display_name":"Machine Learning Science and Technology","issn_l":"2632-2153","issn":["2632-2153"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320083","host_organization_name":"IOP Publishing","host_organization_lineage":["https://openalex.org/P4310320083","https://openalex.org/P4310311669"],"host_organization_lineage_names":["IOP Publishing","Institute of Physics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning: Science and Technology","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:297fcfd2be134027a54263c414e155e6","is_oa":true,"landing_page_url":"https://doaj.org/article/297fcfd2be134027a54263c414e155e6","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Machine Learning: Science and Technology, Vol 6, Iss 4, p 045067 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1088/2632-2153/ae2382","is_oa":true,"landing_page_url":"https://doi.org/10.1088/2632-2153/ae2382","pdf_url":null,"source":{"id":"https://openalex.org/S4210200687","display_name":"Machine Learning Science and Technology","issn_l":"2632-2153","issn":["2632-2153"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320083","host_organization_name":"IOP Publishing","host_organization_lineage":["https://openalex.org/P4310320083","https://openalex.org/P4310311669"],"host_organization_lineage_names":["IOP Publishing","Institute of Physics"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning: Science and Technology","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W1970101292","https://openalex.org/W2045343588","https://openalex.org/W2123871098","https://openalex.org/W2149518557","https://openalex.org/W2160960847","https://openalex.org/W3157530322","https://openalex.org/W3216733725","https://openalex.org/W4387332734","https://openalex.org/W4392601766","https://openalex.org/W4396723768","https://openalex.org/W4400032157","https://openalex.org/W4410018123","https://openalex.org/W4414099476","https://openalex.org/W4416663776"],"related_works":[],"abstract_inverted_index":{"Abstract":[0],"Chemical":[1],"process":[2,69,129,178],"optimization":[3,74,98,144,190,194,249],"is":[4],"crucial":[5],"to":[6,35,40,154,167,240],"maximize":[7],"production":[8],"efficiency":[9],"and":[10,20,97,111,133,162,184,263],"economic":[11],"performance.":[12],"Optimization":[13],"algorithms,":[14],"including":[15],"gradient-based":[16],"solvers,":[17],"numerical":[18],"methods,":[19],"parameter":[21,43,93,209],"grid":[22,155],"searches,":[23],"become":[24],"impractical":[25],"when":[26],"operating":[27,65],"constraints":[28,66,253],"are":[29,231,254],"ill-defined":[30],"or":[31,257],"unavailable,":[32,258],"requiring":[33,163],"engineers":[34],"rely":[36],"on":[37,126],"subjective":[38],"heuristics":[39],"estimate":[41],"feasible":[42],"ranges.":[44],"To":[45],"address":[46],"this":[47],"constraint":[48,91,105,204],"definition":[49],"bottleneck,":[50],"we":[51],"present":[52],"a":[53,148],"multi-agent":[54,114],"framework":[55,82,117,138],"of":[56],"large":[57],"language":[58],"model":[59,222],"(LLM)":[60],"agents":[61,89],"that":[62,195,225],"autonomously":[63],"infer":[64],"from":[67],"minimal":[68],"descriptions,":[70],"then":[71],"collaboratively":[72],"guide":[73],"using":[75,107],"the":[76,116,119,127,137,172],"inferred":[77],"constraints.":[78],"Our":[79],"AutoGen-based":[80],"agentic":[81],"employs":[83],"OpenAI\u2019s":[84],"o3":[85],"model,":[86],"with":[87,142,206,236],"specialized":[88],"for":[90,121,233,248,260],"generation,":[92],"validation,":[94],"simulation":[95],"execution,":[96],"guidance.":[99],"Through":[100],"two":[101],"phases:":[102],"(i)":[103],"autonomous":[104,203],"generation":[106,205],"embedded":[108],"domain":[109],"knowledge,":[110],"(ii)":[112],"iterative":[113],"optimization,":[115,235],"eliminates":[118],"need":[120],"predefined":[122,197],"operational":[123,252],"bounds.":[124],"Validated":[125],"hydrodealkylation":[128],"across":[130,213],"cost,":[131],"yield,":[132],"yield-to-cost":[134],"ratio":[135],"metrics,":[136],"demonstrated":[139],"competitive":[140],"performance":[141],"conventional":[143,189],"methods":[145,191],"while":[146,221],"achieving":[147],"31-fold":[149],"reduction":[150],"in":[151,158],"wall-time":[152],"relative":[153],"search,":[156],"converging":[157],"under":[159],"20":[160],"min":[161],"far":[164],"fewer":[165],"iterations":[166],"converge.":[168],"Beyond":[169],"computational":[170],"efficiency,":[171],"framework\u2019s":[173],"reasoning-guided":[174,208],"search":[175],"demonstrates":[176,217],"sophisticated":[177],"understanding,":[179],"correctly":[180],"identifying":[181],"utility":[182],"trade-offs,":[183],"applying":[185],"domain-informed":[186],"heuristics.":[187],"Unlike":[188],"like":[192],"Bayesian":[193],"require":[196],"constraints,":[198],"our":[199],"approach":[200,244],"uniquely":[201],"combines":[202],"interpretable,":[207],"exploration.":[210],"Reproducibility":[211],"analysis":[212],"five":[214],"independent":[215],"trials":[216],"consistent":[218],"convergence":[219],"behavior,":[220],"comparison":[223],"reveals":[224],"reasoning-capable":[226],"LLM":[227],"architectures":[228],"(o3,":[229],"o1)":[230],"essential":[232],"successful":[234],"standard":[237],"models":[238],"failing":[239],"converge":[241],"effectively.":[242],"This":[243],"shows":[245],"significant":[246],"potential":[247],"scenarios":[250],"where":[251],"poorly":[255],"characterized":[256],"particularly":[259],"emerging":[261],"processes":[262],"retrofit":[264],"applications.":[265]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":2}],"updated_date":"2025-12-16T23:43:54.943958","created_date":"2025-11-25T00:00:00"}