{"id":"https://openalex.org/W7165892340","doi":"https://doi.org/10.48550/arxiv.2606.25039","title":"LLM-ACES: Closed-Loop Discovery of Dynamical Systems with LLM-Guided Adaptive Search","display_name":"LLM-ACES: Closed-Loop Discovery of Dynamical Systems with LLM-Guided Adaptive Search","publication_year":2026,"publication_date":"2026-06-23","ids":{"openalex":"https://openalex.org/W7165892340","doi":"https://doi.org/10.48550/arxiv.2606.25039"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.25039","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.25039","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.2606.25039","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139307994","display_name":"Nikhil Abhyankar","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Abhyankar, Nikhil","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139361101","display_name":"Sha Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Sha","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120456386","display_name":"Sanchit Kabra","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kabra, Sanchit","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139342729","display_name":"Naren Ramakrishnan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ramakrishnan, Naren","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139355633","display_name":"Yulia Gel","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gel, Yulia","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139327483","display_name":"Chandan K. Reddy","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Reddy, Chandan K.","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/T11206","display_name":"Model Reduction and Neural Networks","score":0.6331999897956848,"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":0.6331999897956848,"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/T11948","display_name":"Machine Learning in Materials Science","score":0.06449999660253525,"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/T12611","display_name":"Neural Networks and Reservoir Computing","score":0.03519999980926514,"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/identifiability","display_name":"Identifiability","score":0.6567000150680542},{"id":"https://openalex.org/keywords/dynamical-systems-theory","display_name":"Dynamical systems theory","score":0.6563000082969666},{"id":"https://openalex.org/keywords/ordinary-differential-equation","display_name":"Ordinary differential equation","score":0.6398000121116638},{"id":"https://openalex.org/keywords/ode","display_name":"Ode","score":0.6018999814987183},{"id":"https://openalex.org/keywords/spurious-relationship","display_name":"Spurious relationship","score":0.5580999851226807},{"id":"https://openalex.org/keywords/dynamical-system","display_name":"Dynamical system (definition)","score":0.4429999887943268},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.4244000017642975},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.40720000863075256},{"id":"https://openalex.org/keywords/observer","display_name":"Observer (physics)","score":0.3878999948501587}],"concepts":[{"id":"https://openalex.org/C122770356","wikidata":"https://www.wikidata.org/wiki/Q1656753","display_name":"Identifiability","level":2,"score":0.6567000150680542},{"id":"https://openalex.org/C79379906","wikidata":"https://www.wikidata.org/wiki/Q3174497","display_name":"Dynamical systems theory","level":2,"score":0.6563000082969666},{"id":"https://openalex.org/C51544822","wikidata":"https://www.wikidata.org/wiki/Q465274","display_name":"Ordinary differential equation","level":3,"score":0.6398000121116638},{"id":"https://openalex.org/C34862557","wikidata":"https://www.wikidata.org/wiki/Q178985","display_name":"Ode","level":2,"score":0.6018999814987183},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5611000061035156},{"id":"https://openalex.org/C97256817","wikidata":"https://www.wikidata.org/wiki/Q1462316","display_name":"Spurious relationship","level":2,"score":0.5580999851226807},{"id":"https://openalex.org/C33962884","wikidata":"https://www.wikidata.org/wiki/Q378637","display_name":"Dynamical system (definition)","level":3,"score":0.4429999887943268},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.4244000017642975},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.40720000863075256},{"id":"https://openalex.org/C2780704645","wikidata":"https://www.wikidata.org/wiki/Q9251458","display_name":"Observer (physics)","level":2,"score":0.3878999948501587},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.36959999799728394},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.367900013923645},{"id":"https://openalex.org/C73586568","wikidata":"https://www.wikidata.org/wiki/Q2600211","display_name":"Parameter space","level":2,"score":0.36489999294281006},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.36329999566078186},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.35690000653266907},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.3547999858856201},{"id":"https://openalex.org/C17020691","wikidata":"https://www.wikidata.org/wiki/Q139677","display_name":"Operator (biology)","level":5,"score":0.34290000796318054},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3407000005245209},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.33309999108314514},{"id":"https://openalex.org/C23130292","wikidata":"https://www.wikidata.org/wiki/Q5275358","display_name":"Differential privacy","level":2,"score":0.33219999074935913},{"id":"https://openalex.org/C78045399","wikidata":"https://www.wikidata.org/wiki/Q11214","display_name":"Differential equation","level":2,"score":0.32330000400543213},{"id":"https://openalex.org/C2781170535","wikidata":"https://www.wikidata.org/wiki/Q30587856","display_name":"Noisy data","level":2,"score":0.3215999901294708},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.321399986743927},{"id":"https://openalex.org/C114275822","wikidata":"https://www.wikidata.org/wiki/Q621512","display_name":"Linear dynamical system","level":3,"score":0.2955000102519989},{"id":"https://openalex.org/C163985040","wikidata":"https://www.wikidata.org/wiki/Q1172399","display_name":"Data acquisition","level":2,"score":0.2851000130176544},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.28450000286102295},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.2797999978065491}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.25039","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.25039","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.2606.25039","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.25039","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":{"Recovering":[0],"governing":[1,65,225],"Ordinary":[2],"Differential":[3],"Equations":[4],"(ODEs)":[5],"from":[6],"data":[7,49,90,198,219],"is":[8,186],"a":[9,24,79,94,133,171],"central":[10],"challenge":[11],"in":[12],"modeling":[13],"dynamical":[14,40],"systems":[15,41,150],"across":[16],"scientific":[17],"domains.":[18],"Existing":[19],"approaches":[20],"cast":[21],"discovery":[22],"as":[23],"static":[25],"inference":[26],"problem":[27],"over":[28,43],"fixed":[29],"datasets,":[30],"assuming":[31],"that":[32,82,102,136,184,216],"the":[33,61,104,118,127,140,144,157,193,207,218,223],"observed":[34,119],"trajectories":[35],"are":[36,115],"sufficiently":[37],"informative.":[38],"However,":[39],"evolve":[42],"large":[44,95,105],"state":[45],"spaces,":[46],"and":[47,60,88,143,153,177,205],"limited":[48],"can":[50],"make":[51],"multiple":[52],"equations":[53,114],"observationally":[54],"indistinguishable,":[55],"leading":[56],"to":[57,117,203],"identifiability":[58],"gaps":[59],"recovery":[62],"of":[63,129,167,175],"incorrect":[64],"equations.":[66],"To":[67],"address":[68],"this,":[69],"we":[70],"introduce":[71,213],"LLM-ACES,":[72,93],"or":[73],"LLM-guided":[74],"Active":[75],"Closed-loop":[76],"Equation":[77],"Search,":[78],"closed-loop":[80],"framework":[81],"jointly":[83],"optimizes":[84],"symbolic":[85,173,209],"hypothesis":[86,141],"construction":[87],"adaptive":[89],"acquisition.":[91],"In":[92],"language":[96],"model":[97],"(LLM)":[98],"proposes":[99],"operator":[100],"priors":[101],"partition":[103],"search":[106],"space":[107,142],"into":[108],"distinct":[109],"regions,":[110],"within":[111],"which":[112],"candidate":[113],"fit":[116,217],"data.":[120,194],"The":[121],"disagreement":[122],"among":[123],"these":[124],"candidates":[125],"guides":[126],"acquisition":[128,199],"informative":[130],"trajectories,":[131],"creating":[132],"feedback":[134],"loop":[135],"iteratively":[137],"refines":[138],"both":[139],"discovered":[145],"dynamics.":[146],"On":[147],"122":[148],"ODE":[149],"spanning":[151],"ODEBench":[152],"ODEBase,":[154],"LLM-ACES":[155,185],"achieves":[156],"lowest":[158],"median":[159],"NMSE,":[160],"outperforming":[161],"state-of-the-art":[162],"baselines":[163,212],"by":[164],"several":[165],"orders":[166],"magnitude":[168],"while":[169,211],"achieving":[170,188],"high":[172],"accuracy":[174],"46.2%":[176],"52.4%,":[178],"respectively.":[179],"Our":[180],"analysis":[181],"further":[182],"shows":[183],"sample-efficient,":[187],"better":[189],"performance":[190],"with":[191],"one-tenth":[192],"Furthermore,":[195],"LLM-ACES's":[196],"feedback-driven":[197],"makes":[200],"it":[201],"robust":[202],"noise":[204],"recovers":[206],"correct":[208],"structure,":[210],"spurious":[214],"terms":[215],"locally":[220],"but":[221],"obscure":[222],"true":[224],"relationships.":[226]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-26T00:00:00"}