{"id":"https://openalex.org/W7215892389","doi":"https://doi.org/10.48550/arxiv.2610.00435","title":"How AI Agents Discover Scientific Equations: From Hydrotope Rediscovery to New Water-Wave Amplitudes","display_name":"How AI Agents Discover Scientific Equations: From Hydrotope Rediscovery to New Water-Wave Amplitudes","publication_year":2026,"publication_date":"2026-09-30","ids":{"openalex":"https://openalex.org/W7215892389","doi":"https://doi.org/10.48550/arxiv.2610.00435"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.00435","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.00435","pdf_url":"https://arxiv.org/pdf/2610.00435","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/2610.00435","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5154666138","display_name":"Zihan Zhou","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhou, Zihan","raw_affiliation_strings":["Department of Physics , Princeton University , Princeton , NJ 08540 , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Physics , Princeton University , Princeton , NJ 08540 , USA","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136078223","display_name":"Digvijay Wadekar","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wadekar, Digvijay","raw_affiliation_strings":["Center for Gravitational Physics , University of Texas at Austin , Austin , TX 78712 , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Gravitational Physics , University of Texas at Austin , Austin , TX 78712 , USA","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5136082949","display_name":"Matias Zaldarriaga","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I40036882","display_name":"Institute for Advanced Study","ror":"https://ror.org/00f809463","country_code":"US","type":"facility","lineage":["https://openalex.org/I40036882"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zaldarriaga, Matias","raw_affiliation_strings":["Institute for Advanced Study , 1 Einstein Drive , Princeton , NJ 08540 , USA","School of Natural Sciences ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Advanced Study , 1 Einstein Drive , Princeton , NJ 08540 , USA","institution_ids":["https://openalex.org/I40036882"]},{"raw_affiliation_string":"School of Natural Sciences ,","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"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/T13904","display_name":"Artificial Intelligence Applications","score":0.38089999556541443,"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/T13904","display_name":"Artificial Intelligence Applications","score":0.38089999556541443,"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/T11206","display_name":"Model Reduction and Neural Networks","score":0.2312999963760376,"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":0.1071000024676323,"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/ai-agents","display_name":"AI agents","score":0.6669999957084656},{"id":"https://openalex.org/keywords/water-wave-scattering","display_name":"water wave scattering","score":0.7480000257492065},{"id":"https://openalex.org/keywords/nonlinear-surface-waves","display_name":"nonlinear surface waves","score":0.734000027179718},{"id":"https://openalex.org/keywords/human-ai-collaboration","display_name":"human-AI collaboration","score":0.7360000014305115},{"id":"https://openalex.org/keywords/multiagent-coordination","display_name":"multi-agent coordination","score":0.5139999985694885},{"id":"https://openalex.org/keywords/six-point-amplitudes","display_name":"six-point amplitudes","score":0.7459999918937683}],"concepts":[{"id":"https://openalex.org/C90119067","wikidata":"https://www.wikidata.org/wiki/Q43260","display_name":"Polynomial","level":2,"score":0.6118000149726868},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.5583999752998352},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4564000070095062},{"id":"https://openalex.org/C110812573","wikidata":"https://www.wikidata.org/wiki/Q175515","display_name":"Symbolic computation","level":2,"score":0.4438999891281128},{"id":"https://openalex.org/C39920418","wikidata":"https://www.wikidata.org/wiki/Q11476","display_name":"Kinematics","level":2,"score":0.41659998893737793},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.40709999203681946},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4004000127315521},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3962000012397766},{"id":"https://openalex.org/C136119220","wikidata":"https://www.wikidata.org/wiki/Q1000660","display_name":"Algebra over a field","level":2,"score":0.3871000111103058},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.36730000376701355},{"id":"https://openalex.org/C158622935","wikidata":"https://www.wikidata.org/wiki/Q660848","display_name":"Nonlinear system","level":2,"score":0.34529998898506165},{"id":"https://openalex.org/C180205008","wikidata":"https://www.wikidata.org/wiki/Q159190","display_name":"Amplitude","level":2,"score":0.33250001072883606},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.3301999866962433},{"id":"https://openalex.org/C83546350","wikidata":"https://www.wikidata.org/wiki/Q1139051","display_name":"Regression","level":2,"score":0.3133000135421753},{"id":"https://openalex.org/C311688","wikidata":"https://www.wikidata.org/wiki/Q2393193","display_name":"Time complexity","level":2,"score":0.3100000023841858},{"id":"https://openalex.org/C2777686260","wikidata":"https://www.wikidata.org/wiki/Q144037","display_name":"Calculus (dental)","level":2,"score":0.27970001101493835},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.2773999869823456},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.26820001006126404},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.2551000118255615},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.25209999084472656}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.00435","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.00435","pdf_url":"https://arxiv.org/pdf/2610.00435","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.2610.00435","doi":"https://doi.org/10.48550/arxiv.2610.00435","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.00435","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","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2610.00435","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.00435","pdf_url":"https://arxiv.org/pdf/2610.00435","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":[{"id":"https://openalex.org/G1204986965","display_name":"NSF-BSF: New Data Analysis Techniques for a New Era in GW Astrophysics","funder_award_id":"2207583","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4223084262","display_name":"Probing Fundamental Physics on Cosmological Scales","funder_award_id":"2209991","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8585541598","display_name":"NSF-Simons AI Institute for Cosmic Origins","funder_award_id":"2421782","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320310620","display_name":"University of Texas at Austin","ror":"https://ror.org/00hj54h04"},{"id":"https://openalex.org/F4320314997","display_name":"Strong","ror":"https://ror.org/041vyzr56"},{"id":"https://openalex.org/F4320320847","display_name":"Science Foundation Ireland","ror":"https://ror.org/0271asj38"},{"id":"https://openalex.org/F4320332414","display_name":"Department of Mechanical Engineering, University of Texas at Austin","ror":"https://ror.org/00hj54h04"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7215892389.pdf","grobid_xml":"https://content.openalex.org/works/W7215892389.grobid-xml"},"referenced_works_count":48,"referenced_works":["https://openalex.org/W1811565114","https://openalex.org/W1979769287","https://openalex.org/W2042902158","https://openalex.org/W2047361236","https://openalex.org/W2077241752","https://openalex.org/W2093828424","https://openalex.org/W2114804859","https://openalex.org/W2136636278","https://openalex.org/W2239232218","https://openalex.org/W2896377340","https://openalex.org/W2923537029","https://openalex.org/W2930380020","https://openalex.org/W2947630964","https://openalex.org/W3042021489","https://openalex.org/W4220870416","https://openalex.org/W4224611958","https://openalex.org/W4239951392","https://openalex.org/W4283323903","https://openalex.org/W4285805167","https://openalex.org/W4289765664","https://openalex.org/W4378509427","https://openalex.org/W4385682136","https://openalex.org/W4389132715","https://openalex.org/W4391876619","https://openalex.org/W4396821501","https://openalex.org/W4400021634","https://openalex.org/W4401023556","https://openalex.org/W4402684050","https://openalex.org/W4404782643","https://openalex.org/W4405425144","https://openalex.org/W4415108068","https://openalex.org/W4415795271","https://openalex.org/W4415797149","https://openalex.org/W4416035220","https://openalex.org/W4416043407","https://openalex.org/W4416131329","https://openalex.org/W4417104313","https://openalex.org/W4417534199","https://openalex.org/W7103754783","https://openalex.org/W7118988031","https://openalex.org/W7128819822","https://openalex.org/W7133214447","https://openalex.org/W7160981551","https://openalex.org/W7161704971","https://openalex.org/W7161734976","https://openalex.org/W7162080497","https://openalex.org/W7163562723","https://openalex.org/W7172382919"],"related_works":["https://openalex.org/W7128803507","https://openalex.org/W7119102778","https://openalex.org/W7203681829","https://openalex.org/W4417104313","https://openalex.org/W7159623293","https://openalex.org/W7147290585","https://openalex.org/W7118914869","https://openalex.org/W7167624605","https://openalex.org/W6941245948","https://openalex.org/W7221803149"],"abstract_inverted_index":{"We":[0,65],"study":[1,14],"how":[2,67],"AI":[3],"agents":[4,185],"discover":[5],"and":[6,58,76,85,98,142,146,179,186],"validate":[7],"scientific":[8],"formulas":[9,43],"using":[10],"a":[11,18,91,99,118,167,172,213],"controlled":[12],"case":[13],"of":[15,29,88],"the":[16,25,51,68,108,154,196,201,206,220],"hydrotope,":[17],"recently":[19],"discovered":[20,72],"geometric":[21],"formula":[22,69,109,156],"that":[23],"combines":[24],"different":[26],"polynomial":[27,120],"pieces":[28],"nonlinear":[30],"surface-wave":[31],"scattering":[32],"into":[33],"one":[34],"global":[35,52,155],"expression.":[36],"This":[37],"problem":[38,211],"is":[39],"deceptively":[40],"difficult:":[41],"simple":[42],"can":[44],"hold":[45],"within":[46],"individual":[47],"frequency":[48],"regions,":[49],"but":[50,131],"result":[53],"must":[54],"identify":[55],"their":[56,138,189],"boundaries":[57],"combine":[59,134],"exponentially":[60],"many":[61],"potentially":[62],"active":[63],"terms.":[64],"reconstruct":[66],"was":[70],"originally":[71],"through":[73],"human--agent":[74],"collaboration":[75],"analyze":[77],"18":[78],"single-prompt":[79],"rediscovery":[80],"runs":[81,126],"under":[82],"no":[83],"hint":[84,93,101],"two":[86,183],"forms":[87],"human":[89],"guidance:":[90],"false":[92],"representing":[94,102],"an":[95],"incorrect":[96],"prior":[97],"true":[100],"domain-informed":[103],"insight.":[104],"Only":[105],"four":[106],"recover":[107,153],"across":[110],"all":[111],"kinematic":[112],"chambers":[113],"(i.e.,":[114],"regions":[115],"in":[116,157,170],"which":[117,171],"single":[119],"form":[121],"applies),":[122],"while":[123,200],"most":[124],"unsuccessful":[125],"find":[127],"correct":[128],"chamber":[129],"polynomials":[130],"fail":[132,151],"to":[133,152,182,205],"them":[135],"or":[136],"test":[137,166],"full":[139],"domain.":[140],"Conventional":[141],"LLM-assisted":[143],"symbolic":[144],"regression":[145],"standard":[147],"machine-learning":[148],"regressors":[149],"likewise":[150],"our":[158],"experiments.":[159],"Guided":[160],"by":[161],"these":[162],"failure":[163],"modes,":[164],"we":[165],"PI$+$two-student":[168,192],"workflow":[169,203],"coordinating":[173],"lead":[174],"agent":[175],"assigns":[176],"complementary":[177],"analytic":[178,217],"numerical":[180],"tasks":[181],"research":[184],"independently":[187],"evaluates":[188],"results.":[190],"The":[191],"team":[193],"successfully":[194],"rediscovers":[195],"complete":[197],"hydrotope":[198],"formula,":[199],"same":[202],"applied":[204],"harder":[207],"three":[208],"negative":[209],"wavenumber":[210],"discovers":[212],"new":[214],"independent":[215],"verified":[216],"expression":[218],"for":[219],"six-point":[221],"amplitude":[222],"$A_6$.":[223]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-10-03T00:00:00"}