{"id":"https://openalex.org/W7203502170","doi":"https://doi.org/10.48550/arxiv.2608.13060","title":"VALG: An Agentic System for ML Theory Research","display_name":"VALG: An Agentic System for ML Theory Research","publication_year":2026,"publication_date":"2026-08-13","ids":{"openalex":"https://openalex.org/W7203502170","doi":"https://doi.org/10.48550/arxiv.2608.13060"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.13060","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.13060","pdf_url":"https://arxiv.org/pdf/2608.13060","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/2608.13060","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5126667968","display_name":"Dechen Zhang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Zhang, Dechen","raw_affiliation_strings":["Shenzhen Loop Area Institute","The University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Loop Area Institute","institution_ids":[]},{"raw_affiliation_string":"The University of Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126682549","display_name":"Xuan Tang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Tang, Xuan","raw_affiliation_strings":["The University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5147200166","display_name":"Xinxiang Yin","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yin, Xinxiang","raw_affiliation_strings":["Northwestern Polytechnical University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern Polytechnical University","institution_ids":["https://openalex.org/I17145004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128259232","display_name":"Xingwu Chen","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Chen, Xingwu","raw_affiliation_strings":["The University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126836934","display_name":"Jian Qian","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Qian, Jian","raw_affiliation_strings":["The University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085848346","display_name":"Difan Zou","orcid":"https://orcid.org/0000-0002-6544-2593","observed_orcids":["https://orcid.org/0000-0002-6544-2593"]},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Zou, Difan","raw_affiliation_strings":["Shenzhen Loop Area Institute","The University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Loop Area Institute","institution_ids":[]},{"raw_affiliation_string":"The University of Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":3,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.353300005197525,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.353300005197525,"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/T13904","display_name":"Artificial Intelligence Applications","score":0.27000001072883606,"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/T13523","display_name":"Mathematics, Computing, and Information Processing","score":0.11330000311136246,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/machine-learning-theory","display_name":"machine learning theory","score":0.800000011920929},{"id":"https://openalex.org/keywords/agentic-systems","display_name":"agentic systems","score":0.6589999794960022},{"id":"https://openalex.org/keywords/automated-theorem-proving","display_name":"automated theorem proving","score":0.7039999961853027},{"id":"https://openalex.org/keywords/proof-development","display_name":"proof development","score":0.550000011920929},{"id":"https://openalex.org/keywords/problem-formulation","display_name":"problem formulation","score":0.5289999842643738},{"id":"https://openalex.org/keywords/mathematical-verification","display_name":"mathematical verification","score":0.35100001096725464}],"concepts":[{"id":"https://openalex.org/C108710211","wikidata":"https://www.wikidata.org/wiki/Q11538","display_name":"Mathematical proof","level":2,"score":0.7034000158309937},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5583000183105469},{"id":"https://openalex.org/C125112378","wikidata":"https://www.wikidata.org/wiki/Q176640","display_name":"Randomness","level":2,"score":0.5436999797821045},{"id":"https://openalex.org/C2777686260","wikidata":"https://www.wikidata.org/wiki/Q144037","display_name":"Calculus (dental)","level":2,"score":0.48809999227523804},{"id":"https://openalex.org/C94461902","wikidata":"https://www.wikidata.org/wiki/Q2762418","display_name":"Formal proof","level":3,"score":0.48030000925064087},{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.4697999954223633},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.4609000086784363},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.41029998660087585},{"id":"https://openalex.org/C98184364","wikidata":"https://www.wikidata.org/wiki/Q1780131","display_name":"Argument (complex analysis)","level":2,"score":0.40119999647140503},{"id":"https://openalex.org/C194886279","wikidata":"https://www.wikidata.org/wiki/Q430271","display_name":"Fundamental theorem","level":3,"score":0.39010000228881836},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.38909998536109924},{"id":"https://openalex.org/C2778012447","wikidata":"https://www.wikidata.org/wiki/Q1034415","display_name":"Scope (computer science)","level":2,"score":0.38370001316070557},{"id":"https://openalex.org/C144237770","wikidata":"https://www.wikidata.org/wiki/Q747534","display_name":"Mathematical economics","level":1,"score":0.3828999996185303},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.37610000371932983},{"id":"https://openalex.org/C2779193601","wikidata":"https://www.wikidata.org/wiki/Q20026918","display_name":"Mathematical theory","level":2,"score":0.3522999882698059},{"id":"https://openalex.org/C206880738","wikidata":"https://www.wikidata.org/wiki/Q431667","display_name":"Automated theorem proving","level":2,"score":0.34310001134872437},{"id":"https://openalex.org/C203265346","wikidata":"https://www.wikidata.org/wiki/Q11387554","display_name":"Proof assistant","level":3,"score":0.3345000147819519},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.329800009727478},{"id":"https://openalex.org/C122203268","wikidata":"https://www.wikidata.org/wiki/Q5862903","display_name":"Probability theory","level":2,"score":0.32190001010894775},{"id":"https://openalex.org/C2318724","wikidata":"https://www.wikidata.org/wiki/Q852732","display_name":"Proof theory","level":3,"score":0.3197000026702881},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.3172000050544739},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.3100999891757965},{"id":"https://openalex.org/C2780861221","wikidata":"https://www.wikidata.org/wiki/Q913849","display_name":"Minimax theorem","level":3,"score":0.30790001153945923},{"id":"https://openalex.org/C50335755","wikidata":"https://www.wikidata.org/wiki/Q483247","display_name":"Phenomenon","level":2,"score":0.30140000581741333},{"id":"https://openalex.org/C2778029271","wikidata":"https://www.wikidata.org/wiki/Q5421931","display_name":"Extension (predicate logic)","level":2,"score":0.30059999227523804},{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.29280000925064087},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.29100000858306885},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2815999984741211},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.2662000060081482},{"id":"https://openalex.org/C47884741","wikidata":"https://www.wikidata.org/wiki/Q1166618","display_name":"Mathematical logic","level":2,"score":0.2651999890804291},{"id":"https://openalex.org/C132010649","wikidata":"https://www.wikidata.org/wiki/Q189222","display_name":"Intuition","level":2,"score":0.25619998574256897},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.2526000142097473},{"id":"https://openalex.org/C136119220","wikidata":"https://www.wikidata.org/wiki/Q1000660","display_name":"Algebra over a field","level":2,"score":0.2526000142097473},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2526000142097473}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.13060","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.13060","pdf_url":"https://arxiv.org/pdf/2608.13060","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.2608.13060","doi":"https://doi.org/10.48550/arxiv.2608.13060","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.13060","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:2608.13060","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.13060","pdf_url":"https://arxiv.org/pdf/2608.13060","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":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7203502170.pdf","grobid_xml":"https://content.openalex.org/works/W7203502170.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7220660083","https://openalex.org/W7215053185","https://openalex.org/W7140920674","https://openalex.org/W1532644","https://openalex.org/W7161740980","https://openalex.org/W7119511112","https://openalex.org/W4415981230","https://openalex.org/W1500667683","https://openalex.org/W7159760178","https://openalex.org/W7212321358"],"abstract_inverted_index":{"Machine":[0],"learning":[1,4],"theory":[2,83],"studies":[3,221],"procedures":[5],"through":[6,56],"mathematical":[7,113,171],"setups":[8],"in":[9,49,130,144],"which":[10],"the":[11,23,38,116,141,147,151,156,170,174,178,202,208],"data":[12],"model,":[13],"training":[14],"protocol,":[15],"oracle":[16],"access,":[17],"loss,":[18],"metric,":[19],"and":[20,43,62,66,100,124,126,154,177,231],"randomness":[21],"define":[22],"phenomenon":[24],"that":[25,91,200],"a":[26,111,120,134,145],"theorem":[27,41,107,152,176,198],"is":[28,237],"meant":[29],"to":[30,46],"explain.":[31],"Solving":[32],"an":[33,77,88,163],"open":[34,191,238],"problem":[35,39],"therefore":[36],"requires":[37],"formulation,":[40],"target,":[42],"proof":[44,102,135,148],"mechanism":[45],"be":[47,74],"developed":[48],"concert.":[50],"Researchers":[51],"formulate":[52],"hypotheses,":[53],"test":[54],"them":[55],"preliminary":[57],"theoretical":[58],"or":[59,150,167,216],"empirical":[60],"analysis,":[61],"refine":[63],"both":[64],"assumptions":[65],"proofs.":[67],"We":[68,85,181],"investigate":[69],"whether":[70,140],"this":[71],"process":[72],"can":[73],"organized":[75],"as":[76],"autonomous":[78],"agentic":[79,89],"workflow":[80],"for":[81],"ML":[82],"research.":[84],"develop":[86],"VALG,":[87],"system":[90],"combines":[92],"multi-level":[93],"Verification,":[94],"Adaptive":[95],"formulation":[96,153],"of":[97,119,204],"Learning-theory":[98],"problems,":[99],"Graph-structured":[101],"development.":[103],"Within":[104],"each":[105],"source-relative":[106],"branch,":[108],"VALG":[109,138,183,224,236],"maintains":[110],"fixed":[112],"specification,":[114],"checks":[115],"theorem-level":[117],"composition":[118],"typed":[121],"proof-dependency":[122],"graph,":[123],"constructs":[125],"reviews":[127],"local":[128],"proofs":[129],"dependency":[131],"order.":[132],"When":[133],"attempt":[136,158],"fails,":[137],"identifies":[139],"obstruction":[142],"lies":[143],"derivation,":[146],"structure,":[149],"routes":[155],"next":[157],"accordingly.":[159],"Formulation-level":[160],"obstructions":[161],"initiate":[162],"explicitly":[164],"related":[165],"variant":[166],"relaxation,":[168],"preserving":[169],"relation":[172],"between":[173],"resulting":[175],"source":[179,206,239],"problem.":[180],"evaluate":[182],"on":[184],"nine":[185],"subproblems":[186],"from":[187],"five":[188],"COLT":[189],"2026":[190],"problems.":[192],"Two":[193],"runs":[194],"produce":[195],"internally":[196],"finalized":[197],"candidates":[199],"match":[201],"scope":[203],"their":[205],"briefs;":[207],"remaining":[209],"seven":[210],"yield":[211],"restricted-method":[212],"results,":[213,230],"special":[214],"cases,":[215],"conditional":[217,229],"theorems.":[218],"These":[219],"case":[220],"show":[222],"how":[223],"keeps":[225],"source-scope":[226],"matches,":[227],"relaxations,":[228],"blocked":[232],"attempts":[233],"mathematically":[234],"distinct.":[235],"at":[240],"https://github.com/DechenZhang/VALG-ML-Theory-Agent.":[241]},"counts_by_year":[{"year":2026,"cited_by_count":3}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-08-15T00:00:00"}