{"id":"https://openalex.org/W7161953125","doi":"https://doi.org/10.48550/arxiv.2605.20473","title":"Code Generation by Differential Test Time Scaling","display_name":"Code Generation by Differential Test Time Scaling","publication_year":2026,"publication_date":"2026-05-19","ids":{"openalex":"https://openalex.org/W7161953125","doi":"https://doi.org/10.48550/arxiv.2605.20473"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.20473","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.20473","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":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.20473","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5136645571","display_name":"Yifeng He","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"He, Yifeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104166491","display_name":"Ethan Wang","orcid":"https://orcid.org/0009-0003-7478-7993"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Ethan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100644806","display_name":"Jicheng Wang","orcid":"https://orcid.org/0000-0003-2744-7059"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Jicheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136700909","display_name":"Xuanxin Ouyang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ouyang, Xuanxin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5136669107","display_name":"Hao Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Hao","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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.7791000008583069,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.7791000008583069,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/T10260","display_name":"Software Engineering Research","score":0.03590000048279762,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.03519999980926514,"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/inference","display_name":"Inference","score":0.6424999833106995},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.6223000288009644},{"id":"https://openalex.org/keywords/fuzz-testing","display_name":"Fuzz testing","score":0.6051999926567078},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.529699981212616},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.4724000096321106},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4244999885559082},{"id":"https://openalex.org/keywords/code-generation","display_name":"Code generation","score":0.4153999984264374},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.41530001163482666}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7289000153541565},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6424999833106995},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.6223000288009644},{"id":"https://openalex.org/C111065885","wikidata":"https://www.wikidata.org/wiki/Q1189053","display_name":"Fuzz testing","level":3,"score":0.6051999926567078},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.529699981212616},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.4724000096321106},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4244999885559082},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.4153999984264374},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.41530001163482666},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.3898000121116638},{"id":"https://openalex.org/C93226319","wikidata":"https://www.wikidata.org/wiki/Q193137","display_name":"Differential (mechanical device)","level":2,"score":0.3659000098705292},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.36230000853538513},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.3034999966621399},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.296099990606308},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2881999909877777},{"id":"https://openalex.org/C149629883","wikidata":"https://www.wikidata.org/wiki/Q660926","display_name":"Fraction (chemistry)","level":2,"score":0.28769999742507935},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.28439998626708984},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.28380000591278076},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.27410000562667847},{"id":"https://openalex.org/C128942645","wikidata":"https://www.wikidata.org/wiki/Q1568346","display_name":"Test case","level":3,"score":0.25450000166893005},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.25279998779296875}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.20473","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.20473","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":"doi:10.48550/arxiv.2605.20473","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.20473","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":false,"raw_source_name":null,"raw_type":"Preprint"},"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":{"Test-time":[0],"scaling":[1,56,127,189],"has":[2],"emerged":[3],"as":[4,120],"a":[5,53,200],"promising":[6],"approach":[7],"for":[8,39,58,134],"improving":[9],"code":[10,59,69],"generation":[11,60],"by":[12],"exploring":[13],"large":[14,90,177],"solution":[15],"spaces":[16],"at":[17],"inference":[18,38,133],"time.":[19],"However,":[20],"existing":[21,87],"methods":[22,128],"often":[23],"rely":[24],"on":[25,62,97,109],"public":[26],"test":[27],"cases":[28],"that":[29,129],"are":[30],"unavailable":[31],"in":[32],"practice,":[33],"or":[34,89,194],"require":[35],"extensive":[36],"LLM":[37,132],"candidate":[40,135],"selection,":[41,136],"leading":[42],"to":[43,81,147,158,186,216],"significant":[44],"token":[45,150],"consumption":[46],"and":[47,74,105,165,169,204,209],"time":[48,203],"overhead.":[49],"We":[50,172],"present":[51],"DiffCodeGen,":[52],"novel":[54],"test-time":[55,126,188],"method":[57],"based":[61,108],"coverage-guided":[63,79],"differential":[64],"analysis.":[65],"DiffCodeGen":[66,100,112,137,152,174,191,206],"generates":[67],"diverse":[68],"candidates":[70,96,107],"using":[71,198],"various":[72],"sampling":[73],"prompting":[75],"strategies,":[76],"then":[77],"applies":[78],"fuzzing":[80],"synthesize":[82],"inputs":[83],"without":[84,140],"requiring":[85],"any":[86,141],"tests":[88],"language":[91,178],"models.":[92],"By":[93],"executing":[94],"all":[95],"these":[98],"inputs,":[99],"captures":[101],"their":[102],"dynamic":[103],"behavior":[104],"clusters":[106],"behavioral":[110],"similarity.":[111],"selects":[113],"the":[114,117,121,159],"medoid":[115],"of":[116,162,202],"largest":[118],"cluster":[119],"final":[122],"output.":[123],"Unlike":[124],"prior":[125],"invoke":[130],"additional":[131,149],"performs":[138],"selection":[139],"extra":[142],"model":[143],"calls,":[144],"incurring":[145],"little":[146],"no":[148],"consumption.":[151],"is":[153,166,207],"fully":[154],"asynchronous,":[155],"naturally":[156],"suited":[157],"current":[160],"trend":[161],"agentic":[163],"coding,":[164],"thus":[167],"efficient":[168],"highly":[170],"scalable.":[171],"evaluate":[173],"across":[175],"4":[176],"models,":[179],"demonstrating":[180],"consistent":[181],"improvements":[182],"over":[183],"baselines.":[184],"Compared":[185],"state-of-the-art":[187],"methods,":[190],"achieves":[192],"competitive":[193],"superior":[195],"performance":[196],"while":[197],"only":[199],"fraction":[201],"tokens.":[205],"model-agnostic":[208],"can":[210],"be":[211],"combined":[212],"with":[213],"reasoning":[214],"models":[215],"further":[217],"boost":[218],"performance.":[219]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-22T00:00:00"}