{"id":"https://openalex.org/W7128803507","doi":"https://doi.org/10.48550/arxiv.2602.12259","title":"Think like a Scientist: Physics-guided LLM Agent for Equation Discovery","display_name":"Think like a Scientist: Physics-guided LLM Agent for Equation Discovery","publication_year":2026,"publication_date":"2026-02-12","ids":{"openalex":"https://openalex.org/W7128803507","doi":"https://doi.org/10.48550/arxiv.2602.12259"},"language":null,"primary_location":{"id":"pmh:doi:10.48550/arxiv.2602.12259","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":null,"any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5054430698","display_name":"Jianke Yang","orcid":"https://orcid.org/0000-0001-5247-1152"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Jianke","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093410279","display_name":"Ohm Rishabh Venkatachalam","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Venkatachalam, Ohm","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125929038","display_name":"Mohammad Kianezhad","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kianezhad, Mohammad","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022575807","display_name":"Sharvaree Vadgama","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vadgama, Sharvaree","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5057778679","display_name":"Rose Yu","orcid":"https://orcid.org/0000-0002-8491-7937"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu, Rose","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/T11948","display_name":"Machine Learning in Materials Science","score":0.7949000000953674,"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"}},"topics":[{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.7949000000953674,"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/T11206","display_name":"Model Reduction and Neural Networks","score":0.03759999945759773,"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/T10028","display_name":"Topic Modeling","score":0.02019999921321869,"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/robustness","display_name":"Robustness (evolution)","score":0.6416000127792358},{"id":"https://openalex.org/keywords/suite","display_name":"Suite","score":0.6395000219345093},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4781999886035919},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.42419999837875366},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.3855000138282776},{"id":"https://openalex.org/keywords/domain-knowledge","display_name":"Domain knowledge","score":0.3630000054836273},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.35409998893737793}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6416000127792358},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.6395000219345093},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6075999736785889},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4781999886035919},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4560999870300293},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4438999891281128},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.42419999837875366},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.3855000138282776},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.3630000054836273},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.35409998893737793},{"id":"https://openalex.org/C2776400721","wikidata":"https://www.wikidata.org/wiki/Q18171762","display_name":"Symbolic regression","level":3,"score":0.32519999146461487},{"id":"https://openalex.org/C2984917352","wikidata":"https://www.wikidata.org/wiki/Q12772819","display_name":"Scientific discovery","level":2,"score":0.31679999828338623},{"id":"https://openalex.org/C2776095079","wikidata":"https://www.wikidata.org/wiki/Q489538","display_name":"The Symbolic","level":2,"score":0.31189998984336853},{"id":"https://openalex.org/C116672817","wikidata":"https://www.wikidata.org/wiki/Q1454986","display_name":"Physical system","level":2,"score":0.31150001287460327},{"id":"https://openalex.org/C71104824","wikidata":"https://www.wikidata.org/wiki/Q1476639","display_name":"Structural equation modeling","level":2,"score":0.30410000681877136},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.29670000076293945},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2865999937057495},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2824999988079071},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.26759999990463257},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.26669999957084656},{"id":"https://openalex.org/C65620979","wikidata":"https://www.wikidata.org/wiki/Q7661176","display_name":"Symbolic data analysis","level":2,"score":0.2572999894618988}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:doi:10.48550/arxiv.2602.12259","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"doi:10.48550/arxiv.2602.12259","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.12259","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:doi:10.48550/arxiv.2602.12259","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Explaining":[0],"observed":[1],"phenomena":[2],"through":[3],"symbolic,":[4],"interpretable":[5],"formulas":[6],"is":[7],"a":[8,122],"fundamental":[9],"goal":[10],"of":[11,75,124],"science.":[12],"Recently,":[13],"large":[14],"language":[15],"models":[16],"(LLMs)":[17],"have":[18],"emerged":[19],"as":[20,64,69,110],"promising":[21],"tools":[22,95],"for":[23],"symbolic":[24,106,132],"equation":[25,126],"discovery,":[26],"owing":[27],"to":[28,43,71,96,104,137],"their":[29,115],"broad":[30],"domain":[31],"knowledge":[32],"and":[33,100,112,118,134,143],"strong":[34],"reasoning":[35,53,89],"capabilities.":[36],"However,":[37],"most":[38],"existing":[39],"LLM-based":[40],"systems":[41],"try":[42],"guess":[44],"equations":[45],"directly":[46],"from":[47],"data,":[48],"without":[49],"modeling":[50],"the":[51,73],"multi-step":[52],"process":[54],"that":[55,84],"scientists":[56],"often":[57],"follow:":[58],"first":[59],"inferring":[60],"physical":[61,125],"properties":[62],"such":[63,109],"symmetries,":[65],"then":[66],"using":[67],"these":[68,102],"priors":[70],"restrict":[72],"space":[74],"candidate":[76],"equations.":[77],"We":[78],"introduce":[79],"KeplerAgent,":[80],"an":[81],"agentic":[82],"framework":[83],"explicitly":[85],"follows":[86],"this":[87],"scientific":[88],"process.":[90],"The":[91],"agent":[92],"coordinates":[93],"physics-based":[94],"extract":[97],"intermediate":[98],"structure":[99],"uses":[101],"results":[103],"configure":[105],"regression":[107],"engines":[108],"PySINDy":[111],"PySR,":[113],"including":[114],"function":[116],"libraries":[117],"structural":[119],"constraints.":[120],"Across":[121],"suite":[123],"benchmarks,":[127],"KeplerAgent":[128],"achieves":[129],"substantially":[130],"higher":[131],"accuracy":[133],"greater":[135],"robustness":[136],"noisy":[138],"data":[139],"than":[140],"both":[141],"LLM":[142],"traditional":[144],"baselines.":[145]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-02-14T00:00:00"}