{"id":"https://openalex.org/W7214718381","doi":"https://doi.org/10.48550/arxiv.2609.32073","title":"Reinforcement learning amortizes transition-state physics into one-step flow models","display_name":"Reinforcement learning amortizes transition-state physics into one-step flow models","publication_year":2026,"publication_date":"2026-09-25","ids":{"openalex":"https://openalex.org/W7214718381","doi":"https://doi.org/10.48550/arxiv.2609.32073"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.32073","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.32073","pdf_url":"https://arxiv.org/pdf/2609.32073","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/2609.32073","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5153447805","display_name":"Yunyang Li","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I32971472","display_name":"Yale University","ror":"https://ror.org/03v76x132","country_code":"US","type":"education","lineage":["https://openalex.org/I32971472"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Li, Yunyang","raw_affiliation_strings":["Yale University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yale University","institution_ids":["https://openalex.org/I32971472"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153491942","display_name":"Zechang Sun","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I32971472","display_name":"Yale University","ror":"https://ror.org/03v76x132","country_code":"US","type":"education","lineage":["https://openalex.org/I32971472"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sun, Zechang","raw_affiliation_strings":["Yale University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yale University","institution_ids":["https://openalex.org/I32971472"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153455202","display_name":"Kuang Yu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I32971472","display_name":"Yale University","ror":"https://ror.org/03v76x132","country_code":"US","type":"education","lineage":["https://openalex.org/I32971472"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yu, Kuang","raw_affiliation_strings":["Yale University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yale University","institution_ids":["https://openalex.org/I32971472"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153402686","display_name":"Wen Yan","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I32971472","display_name":"Yale University","ror":"https://ror.org/03v76x132","country_code":"US","type":"education","lineage":["https://openalex.org/I32971472"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yan, Wen","raw_affiliation_strings":["Yale University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yale University","institution_ids":["https://openalex.org/I32971472"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042321575","display_name":"Mark Gerstein","orcid":"https://orcid.org/0000-0002-9746-3719","observed_orcids":["https://orcid.org/0000-0002-9746-3719"]},"institutions":[{"id":"https://openalex.org/I32971472","display_name":"Yale University","ror":"https://ror.org/03v76x132","country_code":"US","type":"education","lineage":["https://openalex.org/I32971472"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gerstein, Mark","raw_affiliation_strings":["Yale University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yale University","institution_ids":["https://openalex.org/I32971472"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068239619","display_name":"Hung Q. Pham","orcid":"https://orcid.org/0000-0003-3608-1298","observed_orcids":["https://orcid.org/0000-0003-3608-1298"]},"institutions":[{"id":"https://openalex.org/I32971472","display_name":"Yale University","ror":"https://ror.org/03v76x132","country_code":"US","type":"education","lineage":["https://openalex.org/I32971472"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pham, Hung Q.","raw_affiliation_strings":["Yale University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yale University","institution_ids":["https://openalex.org/I32971472"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I32971472"],"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/T11948","display_name":"Machine Learning in Materials Science","score":0.8695999979972839,"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":0.8695999979972839,"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/T10211","display_name":"Computational Drug Discovery Methods","score":0.0640999972820282,"subfield":{"id":"https://openalex.org/subfields/3002","display_name":"Drug Discovery"},"field":{"id":"https://openalex.org/fields/30","display_name":"Pharmacology, Toxicology and Pharmaceutics"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10002","display_name":"Advanced Chemical Physics Studies","score":0.04149999842047691,"subfield":{"id":"https://openalex.org/subfields/3107","display_name":"Atomic and Molecular Physics, and Optics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/transition-state-search","display_name":"transition state search","score":0.8510000109672546},{"id":"https://openalex.org/keywords/reaction-discovery","display_name":"reaction discovery","score":0.7749999761581421},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"reinforcement learning","score":0.7360000014305115},{"id":"https://openalex.org/keywords/generative-chemistry","display_name":"generative chemistry","score":0.5960000157356262},{"id":"https://openalex.org/keywords/reaction-pathways","display_name":"reaction pathways","score":0.4819999933242798},{"id":"https://openalex.org/keywords/bimolecular-reactions","display_name":"bimolecular reactions","score":0.7889999747276306},{"id":"https://openalex.org/keywords/zero-shot-generalization","display_name":"zero-shot generalization","score":0.6269999742507935},{"id":"https://openalex.org/keywords/transition-metals","display_name":"transition metals","score":0.4059999883174896}],"concepts":[{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.7799999713897705},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5932000279426575},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5419999957084656},{"id":"https://openalex.org/C38349280","wikidata":"https://www.wikidata.org/wiki/Q1434290","display_name":"Flow (mathematics)","level":2,"score":0.49720001220703125},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.484499990940094},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48089998960494995},{"id":"https://openalex.org/C90673727","wikidata":"https://www.wikidata.org/wiki/Q901718","display_name":"Product (mathematics)","level":2,"score":0.4284000098705292},{"id":"https://openalex.org/C194232998","wikidata":"https://www.wikidata.org/wiki/Q1606712","display_name":"Transition (genetics)","level":3,"score":0.39480000734329224},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.38089999556541443},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34360000491142273},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.33809998631477356},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.3043000102043152},{"id":"https://openalex.org/C52740198","wikidata":"https://www.wikidata.org/wiki/Q1539564","display_name":"Importance sampling","level":3,"score":0.29120001196861267},{"id":"https://openalex.org/C138777275","wikidata":"https://www.wikidata.org/wiki/Q6884054","display_name":"Mixing (physics)","level":2,"score":0.28130000829696655},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2791000008583069},{"id":"https://openalex.org/C131675550","wikidata":"https://www.wikidata.org/wiki/Q7646884","display_name":"Surrogate model","level":2,"score":0.27570000290870667},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2700999975204468},{"id":"https://openalex.org/C152365726","wikidata":"https://www.wikidata.org/wiki/Q1048589","display_name":"Density functional theory","level":2,"score":0.2671000063419342}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.32073","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.32073","pdf_url":"https://arxiv.org/pdf/2609.32073","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.2609.32073","doi":"https://doi.org/10.48550/arxiv.2609.32073","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.32073","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:2609.32073","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.32073","pdf_url":"https://arxiv.org/pdf/2609.32073","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/W7214718381.pdf","grobid_xml":"https://content.openalex.org/works/W7214718381.grobid-xml"},"referenced_works_count":55,"referenced_works":["https://openalex.org/W1977178778","https://openalex.org/W1986614779","https://openalex.org/W1988675445","https://openalex.org/W1991029743","https://openalex.org/W1998162823","https://openalex.org/W2035220448","https://openalex.org/W2057980421","https://openalex.org/W2081159460","https://openalex.org/W2086513155","https://openalex.org/W2088615896","https://openalex.org/W2092157292","https://openalex.org/W2096747776","https://openalex.org/W2122427541","https://openalex.org/W2136567909","https://openalex.org/W2200369217","https://openalex.org/W2324747868","https://openalex.org/W2911997094","https://openalex.org/W2937798275","https://openalex.org/W2942194104","https://openalex.org/W3007178273","https://openalex.org/W3008606298","https://openalex.org/W3092617600","https://openalex.org/W3173507260","https://openalex.org/W3177590463","https://openalex.org/W4288099666","https://openalex.org/W4306721721","https://openalex.org/W4308917845","https://openalex.org/W4316507319","https://openalex.org/W4327900113","https://openalex.org/W4389786948","https://openalex.org/W4390640165","https://openalex.org/W4391631327","https://openalex.org/W4394450114","https://openalex.org/W4406763461","https://openalex.org/W4408757666","https://openalex.org/W4409729665","https://openalex.org/W4411571563","https://openalex.org/W4414742673","https://openalex.org/W4416070669","https://openalex.org/W4416524231","https://openalex.org/W4416981842","https://openalex.org/W4417082410","https://openalex.org/W4417298370","https://openalex.org/W6891811738","https://openalex.org/W7103191517","https://openalex.org/W7125490151","https://openalex.org/W7125705062","https://openalex.org/W7127392817","https://openalex.org/W7148589921","https://openalex.org/W7158836336","https://openalex.org/W7162340663","https://openalex.org/W7165648010","https://openalex.org/W7167049889","https://openalex.org/W7169544084","https://openalex.org/W7169615833"],"related_works":["https://openalex.org/W7127392817","https://openalex.org/W4415402587","https://openalex.org/W7212248898","https://openalex.org/W7203639767","https://openalex.org/W7168239980","https://openalex.org/W4389786948","https://openalex.org/W7164654107","https://openalex.org/W7169615833","https://openalex.org/W7140316645","https://openalex.org/W7125838024"],"abstract_inverted_index":{"Transition-state":[0],"searches":[1,136],"remain":[2],"a":[3,47,60,70,76],"major":[4],"bottleneck":[5],"in":[6,127],"reaction":[7,165],"discovery,":[8],"as":[9],"identifying":[10],"valid":[11],"saddle-point":[12],"structures":[13],"requires":[14],"numerous":[15],"expensive":[16],"quantum-chemical":[17],"calculations.":[18],"Generative":[19],"models":[20],"can":[21],"reduce":[22],"this":[23],"burden":[24],"by":[25],"proposing":[26],"candidates":[27],"from":[28,148],"reactant":[29],"and":[30,86,118,132],"product":[31],"geometries,":[32],"but":[33],"supervised":[34],"training":[35],"on":[36],"geometries":[37],"alone":[38],"does":[39],"not":[40],"enforce":[41,92],"the":[42,105],"physical":[43],"conditions":[44,94],"required":[45],"of":[46,107],"transition":[48,101,116],"state,":[49],"while":[50,143],"enforcing":[51],"them":[52],"during":[53],"sampling":[54],"is":[55],"costly.":[56],"We":[57],"introduce":[58],"Tr\u00e8fle,":[59],"one-step":[61],"flow":[62],"model":[63],"that":[64,91],"amortizes":[65],"physics-guided":[66],"generation":[67],"into":[68],"training:":[69],"mean-flow":[71],"objective":[72],"replaces":[73,79,95],"multi-step":[74,108],"sampling,":[75],"low-cost":[77],"surrogate":[78],"density":[80],"functional":[81],"theory":[82],"(DFT)":[83],"reward":[84],"evaluations,":[85],"reinforcement-learning":[87],"post-training":[88,144],"with":[89],"rewards":[90],"those":[93],"inference-time":[96],"guidance.":[97],"Tr\u00e8fle":[98,157],"generates":[99],"accurate":[100],"states":[102],"at":[103],"$30\\times$":[104],"throughput":[106],"baselines.":[109],"It":[110],"transfers":[111],"few-shot":[112],"to":[113,121,150],"ten":[114],"unseen":[115,140,154],"metals":[117],"generalizes":[119],"zero-shot":[120],"molecules":[122],"far":[123],"larger":[124],"than":[125],"any":[126],"training.":[128],"With":[129],"DFT":[130],"refinement":[131],"reaction-path":[133],"validation,":[134],"Tr\u00e8fle-seeded":[135],"recover":[137],"all":[138],"13":[139],"$\u03b3$-ketohydroperoxide":[141],"channels,":[142],"raises":[145],"per-attempt":[146],"recovery":[147],"28%":[149],"50%":[151],"across":[152],"85":[153],"bimolecular":[155],"channels.":[156],"thus":[158],"provides":[159],"fast,":[160],"reliable":[161],"seeds":[162],"for":[163],"automated":[164],"discovery.":[166]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-09-30T00:00:00"}