{"id":"https://openalex.org/W7204780529","doi":"https://doi.org/10.48550/arxiv.2608.27869","title":"See, Hypothesize, Validate: Multimodal Agentic Framework for Discovering Governing PDEs","display_name":"See, Hypothesize, Validate: Multimodal Agentic Framework for Discovering Governing PDEs","publication_year":2026,"publication_date":"2026-08-28","ids":{"openalex":"https://openalex.org/W7204780529","doi":"https://doi.org/10.48550/arxiv.2608.27869"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.27869","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.27869","pdf_url":"https://arxiv.org/pdf/2608.27869","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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","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/2608.27869","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5148823700","display_name":"Sarang Manoj Pekhale","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I68891433","display_name":"Indian Institute of Technology Delhi","ror":"https://ror.org/049tgcd06","country_code":"IN","type":"education","lineage":["https://openalex.org/I68891433"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Pekhale, Sarang Manoj","raw_affiliation_strings":["Department of Applied Mechanics Indian Institute of Technology Delhi , India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Applied Mechanics Indian Institute of Technology Delhi , India","institution_ids":["https://openalex.org/I68891433"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114473476","display_name":"Amartya Roy","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210151956","display_name":"Robert Bosch (India)","ror":"https://ror.org/04my8ty22","country_code":"IN","type":"company","lineage":["https://openalex.org/I4210151956","https://openalex.org/I889804353"]},{"id":"https://openalex.org/I68891433","display_name":"Indian Institute of Technology Delhi","ror":"https://ror.org/049tgcd06","country_code":"IN","type":"education","lineage":["https://openalex.org/I68891433"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Roy, Amartya","raw_affiliation_strings":["Robert Bosch GmbH , India","The School of Interdisciplinary Research Indian Institute of Technology Delhi , India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Robert Bosch GmbH , India","institution_ids":["https://openalex.org/I4210151956"]},{"raw_affiliation_string":"The School of Interdisciplinary Research Indian Institute of Technology Delhi , India","institution_ids":["https://openalex.org/I68891433"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135448779","display_name":"Rajat Sarkar","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I55215948","display_name":"Tata Consultancy Services (India)","ror":"https://ror.org/01b9n8m42","country_code":"IN","type":"company","lineage":["https://openalex.org/I4210086519","https://openalex.org/I55215948"]},{"id":"https://openalex.org/I68891433","display_name":"Indian Institute of Technology Delhi","ror":"https://ror.org/049tgcd06","country_code":"IN","type":"education","lineage":["https://openalex.org/I68891433"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sarkar, Rajat","raw_affiliation_strings":["Department of Applied Mechanics Indian Institute of Technology Delhi , India","TCS Research , India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Applied Mechanics Indian Institute of Technology Delhi , India","institution_ids":["https://openalex.org/I68891433"]},{"raw_affiliation_string":"TCS Research , India","institution_ids":["https://openalex.org/I55215948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5130600733","display_name":"Souvik Chakraborty","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I68891433","display_name":"Indian Institute of Technology Delhi","ror":"https://ror.org/049tgcd06","country_code":"IN","type":"education","lineage":["https://openalex.org/I68891433"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Chakraborty, Souvik","raw_affiliation_strings":["Department of Applied Mechanics Indian Institute of Technology Delhi , India","Yardi School of Artificial Intelligence (ScAI) Indian Institute of Technology Delhi , India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Applied Mechanics Indian Institute of Technology Delhi , India","institution_ids":["https://openalex.org/I68891433"]},{"raw_affiliation_string":"Yardi School of Artificial Intelligence (ScAI) Indian Institute of Technology Delhi , India","institution_ids":["https://openalex.org/I68891433"]}]}],"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/T11206","display_name":"Model Reduction and Neural Networks","score":0.9990000128746033,"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":0.9990000128746033,"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/T11236","display_name":"Control Systems and Identification","score":0.00039999998989515007,"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/T11416","display_name":"Numerical Solvers for Ordinary Differential Equations","score":0.0,"subfield":{"id":"https://openalex.org/subfields/2612","display_name":"Numerical Analysis"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/agentic-framework","display_name":"agentic framework","score":0.656000018119812},{"id":"https://openalex.org/keywords/multimodal-agents","display_name":"multimodal agents","score":0.5740000009536743},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.7059999704360962},{"id":"https://openalex.org/keywords/vision-language-models","display_name":"vision-language models","score":0.9490000009536743},{"id":"https://openalex.org/keywords/restoring-force-model","display_name":"restoring force model","score":0.4129999876022339}],"concepts":[{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6496000289916992},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5755000114440918},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5393999814987183},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5091999769210815},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.4799000024795532},{"id":"https://openalex.org/C140479938","wikidata":"https://www.wikidata.org/wiki/Q5254619","display_name":"Iterated function","level":2,"score":0.4661000072956085},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4255000054836273},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3955000042915344},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3930000066757202},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3903000056743622},{"id":"https://openalex.org/C143587482","wikidata":"https://www.wikidata.org/wiki/Q1543216","display_name":"Iterative and incremental development","level":2,"score":0.38989999890327454},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.37869998812675476},{"id":"https://openalex.org/C2778067643","wikidata":"https://www.wikidata.org/wiki/Q166507","display_name":"Interval (graph theory)","level":2,"score":0.3750999867916107},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.37470000982284546},{"id":"https://openalex.org/C2779982483","wikidata":"https://www.wikidata.org/wiki/Q6094420","display_name":"Iterative refinement","level":2,"score":0.3666999936103821},{"id":"https://openalex.org/C93779851","wikidata":"https://www.wikidata.org/wiki/Q271977","display_name":"Partial differential equation","level":2,"score":0.36469998955726624},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.3625999987125397},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36010000109672546},{"id":"https://openalex.org/C32230216","wikidata":"https://www.wikidata.org/wiki/Q7882499","display_name":"Uncertainty quantification","level":2,"score":0.3391000032424927},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.32260000705718994},{"id":"https://openalex.org/C159694833","wikidata":"https://www.wikidata.org/wiki/Q2321565","display_name":"Iterative method","level":2,"score":0.29159998893737793},{"id":"https://openalex.org/C2780695315","wikidata":"https://www.wikidata.org/wiki/Q3799040","display_name":"Unobservable","level":2,"score":0.2791999876499176},{"id":"https://openalex.org/C8272713","wikidata":"https://www.wikidata.org/wiki/Q176737","display_name":"Stochastic process","level":2,"score":0.2687999904155731},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.26829999685287476},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.26260000467300415},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.25920000672340393},{"id":"https://openalex.org/C2781170535","wikidata":"https://www.wikidata.org/wiki/Q30587856","display_name":"Noisy data","level":2,"score":0.2524999976158142},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.2524000108242035},{"id":"https://openalex.org/C64357122","wikidata":"https://www.wikidata.org/wiki/Q1149766","display_name":"Causality (physics)","level":2,"score":0.25200000405311584}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.27869","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.27869","pdf_url":"https://arxiv.org/pdf/2608.27869","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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2608.27869","doi":"https://doi.org/10.48550/arxiv.2608.27869","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.27869","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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2608.27869","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.27869","pdf_url":"https://arxiv.org/pdf/2608.27869","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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204780529.pdf","grobid_xml":"https://content.openalex.org/works/W7204780529.grobid-xml"},"referenced_works_count":7,"referenced_works":["https://openalex.org/W1563957082","https://openalex.org/W4403796339","https://openalex.org/W4405903187","https://openalex.org/W4406465766","https://openalex.org/W4415085804","https://openalex.org/W4416063600","https://openalex.org/W7075994024"],"related_works":["https://openalex.org/W7223129229","https://openalex.org/W7168269101","https://openalex.org/W7204752579","https://openalex.org/W7154365636","https://openalex.org/W4416034994","https://openalex.org/W4391972374","https://openalex.org/W4391464168","https://openalex.org/W4303438858","https://openalex.org/W4281782255","https://openalex.org/W4401010061"],"abstract_inverted_index":{"Discovering":[0],"governing":[1],"partial":[2],"differential":[3],"equations":[4],"(PDEs)":[5],"from":[6,86],"observational":[7],"data":[8],"remains":[9,213],"a":[10,51,71,79,97,117,121,163,190],"core":[11],"challenge":[12],"across":[13],"the":[14,59,113,130,142,147,176],"sciences.":[15],"Existing":[16],"sparse-regression,":[17],"symbolic-regression,":[18],"and":[19,65,76,100,106,141,162],"LLM-based":[20],"approaches":[21],"can":[22],"be":[23,215],"constrained":[24],"by":[25,58],"predefined":[26,98],"libraries,":[27],"noise":[28],"sensitivity,":[29],"hallucination,":[30],"or":[31],"limited":[32],"iterative":[33],"refinement.":[34],"We":[35],"introduce":[36],"\\textbf{MAGE}":[37],"(\\textbf{M}ultimodal":[38],"\\textbf{A}gentic":[39],"\\textbf{G}overning":[40],"\\textbf{E}quation":[41],"Discovery),":[42],"an":[43,89,101,125],"agentic":[44,204],"framework":[45],"that":[46],"organizes":[47],"PDE":[48,133],"discovery":[49],"as":[50],"\\textit{confidence":[52],"governed":[53],"hypothesis":[54],"validation":[55],"loop}":[56],"inspired":[57],"scientific":[60],"cycle":[61],"of":[62,155,160,166,170,202],"observation,":[63],"hypothesis,":[64],"falsification.":[66],"Four":[67],"role-specialized":[68],"agents":[69],"collaborate:":[70],"\\textit{Differential":[72],"Observer}":[73],"computing":[74],"derivatives":[75],"diagnostic":[77],"visualizations;":[78],"VLM-powered":[80],"\\textit{Phenomenology":[81],"Extractor}":[82],"distilling":[83],"qualitative":[84],"cues":[85],"multimodal":[87],"diagnostics;":[88],"LLM-driven":[90],"\\textit{Governing":[91],"Law":[92],"Synthesizer}":[93],"proposing":[94],"candidates":[95],"without":[96],"library;":[99],"\\textit{Equation":[102],"Arbiter}":[103],"fitting":[104],"coefficients":[105],"assigning":[107],"confidence":[108],"scores.":[109],"Discovery":[110],"iterates":[111],"until":[112],"top":[114],"candidate":[115],"clears":[116],"user-specified":[118],"threshold,":[119],"providing":[120],"structured":[122,203],"process":[123],"with":[124,153,194],"explicit":[126],"accept-reject":[127],"protocol.":[128],"On":[129],"evaluated":[131],"canonical":[132],"suite,":[134],"MAGE":[135],"obtains":[136],"\\textbf{8/8}":[137],"exact":[138],"structural":[139],"recovery":[140],"lowest":[143],"coefficient":[144],"error":[145],"among":[146],"compared":[148],"methods":[149],"on":[150,184],"\\textbf{7/8}":[151],"systems,":[152],"improvements":[154],"up":[156],"to":[157,214],"\\textbf{4":[158],"orders":[159,169],"magnitude}":[161],"geometric-mean":[164],"improvement":[165],"approximately":[167],"\\textbf{3":[168],"magnitude}.":[171],"The":[172],"pipeline":[173],"also":[174],"recovers":[175],"expected":[177],"operators":[178],"in":[179],"two":[180],"complex":[181],"geometries":[182],"and,":[183],"one":[185],"laboratory":[186],"sensor":[187],"record,":[188],"selects":[189],"cubic":[191],"restoring-force":[192],"model":[193],"held-out":[195],"$R^2=0.98538$.":[196],"These":[197],"results":[198],"support":[199],"further":[200],"study":[201],"reasoning":[205],"for":[206],"library-free":[207],"governing-law":[208],"discovery,":[209],"while":[210],"broader":[211],"generalization":[212],"evaluated.":[216]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-09-01T00:00:00"}