{"id":"https://openalex.org/W7126045895","doi":"https://doi.org/10.48550/arxiv.2601.20789","title":"SERA: Soft-Verified Efficient Repository Agents","display_name":"SERA: Soft-Verified Efficient Repository Agents","publication_year":2026,"publication_date":"2026-01-28","ids":{"openalex":"https://openalex.org/W7126045895","doi":"https://doi.org/10.48550/arxiv.2601.20789"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2601.20789","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2601.20789","pdf_url":"https://arxiv.org/pdf/2601.20789","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2601.20789","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5124178526","display_name":"Ethan Shen","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]},{"id":"https://openalex.org/I4210156221","display_name":"Allen Institute for Artificial Intelligence","ror":"https://ror.org/05w520734","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210156221"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shen, Ethan","raw_affiliation_strings":["Allen Institute for AI","University of Washington"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Allen Institute for AI","institution_ids":["https://openalex.org/I4210156221"]},{"raw_affiliation_string":"University of Washington","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114367900","display_name":"Danny Tormoen","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210156221","display_name":"Allen Institute for Artificial Intelligence","ror":"https://ror.org/05w520734","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210156221"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tormoen, Daniel","raw_affiliation_strings":["Allen Institute for AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Allen Institute for AI","institution_ids":["https://openalex.org/I4210156221"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124280868","display_name":"Saurabh Shah","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210156221","display_name":"Allen Institute for Artificial Intelligence","ror":"https://ror.org/05w520734","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210156221"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shah, Saurabh","raw_affiliation_strings":["Allen Institute for AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Allen Institute for AI","institution_ids":["https://openalex.org/I4210156221"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122490804","display_name":"Ali Farhadi","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]},{"id":"https://openalex.org/I4210156221","display_name":"Allen Institute for Artificial Intelligence","ror":"https://ror.org/05w520734","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210156221"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Farhadi, Ali","raw_affiliation_strings":["Allen Institute for AI","University of Washington"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Allen Institute for AI","institution_ids":["https://openalex.org/I4210156221"]},{"raw_affiliation_string":"University of Washington","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067514564","display_name":"Tim Dettmers","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210156221","display_name":"Allen Institute for Artificial Intelligence","ror":"https://ror.org/05w520734","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210156221"]},{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dettmers, Tim","raw_affiliation_strings":["Allen Institute for AI","Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Allen Institute for AI","institution_ids":["https://openalex.org/I4210156221"]},{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]}],"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/T10260","display_name":"Software Engineering Research","score":0.9940999746322632,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10260","display_name":"Software Engineering Research","score":0.9940999746322632,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10028","display_name":"Topic Modeling","score":0.001500000013038516,"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/T10430","display_name":"Software Engineering Techniques and Practices","score":0.00039999998989515007,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/ai-coding-agents","display_name":"coding agents","score":0.9160000085830688},{"id":"https://openalex.org/keywords/synthetic-data-generation","display_name":"synthetic data generation","score":0.5059999823570251},{"id":"https://openalex.org/keywords/supervised-fine-tuning","display_name":"supervised fine-tuning","score":0.6830000281333923},{"id":"https://openalex.org/keywords/training-cost-reduction","display_name":"training cost reduction","score":0.6570000052452087},{"id":"https://openalex.org/keywords/scaling-laws","display_name":"scaling laws","score":0.8270000219345093},{"id":"https://openalex.org/keywords/open-source-models","display_name":"open-source models","score":0.4309999942779541}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7509999871253967},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.6118000149726868},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.3991999924182892},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39739999175071716},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.39340001344680786},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.39089998602867126},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3716999888420105},{"id":"https://openalex.org/C99221444","wikidata":"https://www.wikidata.org/wiki/Q1532069","display_name":"Private information retrieval","level":2,"score":0.36660000681877136},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.35010001063346863},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3499000072479248},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.33340001106262207},{"id":"https://openalex.org/C202629362","wikidata":"https://www.wikidata.org/wiki/Q2078","display_name":"Scalable Vector Graphics","level":2,"score":0.26660001277923584},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.266400009393692},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.2612999975681305},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.25949999690055847},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.2565000057220459},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2542000114917755}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2601.20789","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2601.20789","pdf_url":"https://arxiv.org/pdf/2601.20789","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2601.20789","doi":"https://doi.org/10.48550/arxiv.2601.20789","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2601.20789","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:2601.20789","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2601.20789","pdf_url":"https://arxiv.org/pdf/2601.20789","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"display_name":"Partnerships for the goals","score":0.4055052697658539,"id":"https://metadata.un.org/sdg/17"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7126045895.pdf","grobid_xml":"https://content.openalex.org/works/W7126045895.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7126273631","https://openalex.org/W7133300551","https://openalex.org/W7167682524","https://openalex.org/W7162114202","https://openalex.org/W7213988564","https://openalex.org/W7139098515","https://openalex.org/W7221514766","https://openalex.org/W7221505366","https://openalex.org/W7139147743","https://openalex.org/W4417295762"],"abstract_inverted_index":{"Open-weight":[0],"coding":[1,51,164,177],"agents":[2,52,61,178],"should":[3],"hold":[4],"a":[5,91],"fundamental":[6],"advantage":[7,35,182],"over":[8],"closed-source":[9],"systems":[10],"because":[11],"they":[12],"can":[13,187],"specialize":[14],"to":[15,63,90,143,151,189,215],"private":[16,64,190],"codebases,":[17,95],"encoding":[18],"repository-specific":[19],"information":[20],"directly":[21],"in":[22,199],"their":[23],"weights.":[24],"Yet":[25],"the":[26,55,119,181,196,217],"cost":[27],"and":[28,57,135,159,179,211],"complexity":[29],"of":[30,60,74,94,121,155,183],"training":[31,50,163],"has":[32],"kept":[33],"this":[34],"theoretical":[36],"until":[37],"now.":[38],"We":[39,147,192],"present":[40],"Soft-Verified":[41],"Efficient":[42],"Repository":[43],"Agents":[44,203],"(SERA),":[45],"an":[46],"efficient":[47],"method":[48],"for":[49,162],"that":[53,186],"enables":[54],"rapid":[56],"cheap":[58],"creation":[59],"specialized":[62],"codebases.":[65,191],"Using":[66,100],"Soft":[67],"Verified":[68],"Generation":[69],"(SVG),":[70],"we":[71,87,167],"generate":[72],"thousands":[73],"trajectories":[75],"from":[76],"any":[77],"code":[78],"repository,":[79],"without":[80],"requiring":[81],"unit":[82],"tests.":[83],"Beyond":[84],"repository":[85],"specialization,":[86],"apply":[88],"SVG":[89],"larger":[92],"corpus":[93],"generating":[96],"200,000+":[97],"synthetic":[98,140],"trajectories.":[99],"only":[101],"supervised":[102],"finetuning":[103],"(SFT),":[104],"SERA":[105,127,194],"achieves":[106],"leading":[107],"results":[108],"among":[109],"fully":[110],"open-source":[111,184],"(open":[112],"data,":[113,210],"method,":[114],"code)":[115],"models":[116,123,128,185],"while":[117],"matching":[118],"performance":[120],"open-weight":[122],"like":[124],"Devstral-Small-2.":[125],"Creating":[126],"is":[129],"26x":[130],"cheaper":[131,137],"than":[132,138],"reinforcement":[133],"learning":[134],"57x":[136],"previous":[139],"data":[141],"methods":[142],"reach":[144],"equivalent":[145],"performance.":[146],"use":[148],"our":[149,169,208],"dataset":[150],"provide":[152],"detailed":[153],"analysis":[154],"scaling":[156],"laws,":[157],"ablations,":[158],"confounding":[160],"factors":[161],"agents.":[165],"Overall,":[166],"believe":[168],"work":[170],"will":[171],"greatly":[172],"accelerate":[173],"research":[174,218],"on":[175],"open":[176],"showcase":[180],"adapt":[188],"release":[193],"as":[195],"first":[197],"model":[198],"Ai2's":[200],"Open":[201],"Coding":[202],"series,":[204],"along":[205],"with":[206],"all":[207],"code,":[209],"Claude":[212],"Code":[213],"integration":[214],"support":[216],"community.":[219]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-01-30T00:00:00"}