{"id":"https://openalex.org/W7204264693","doi":"https://doi.org/10.48550/arxiv.2608.24473","title":"Ockhamareto: Pareto-Gated Segment-Level Credit Assignment for Concise Unit-Test Generation with Reinforcement Learning","display_name":"Ockhamareto: Pareto-Gated Segment-Level Credit Assignment for Concise Unit-Test Generation with Reinforcement Learning","publication_year":2026,"publication_date":"2026-08-25","ids":{"openalex":"https://openalex.org/W7204264693","doi":"https://doi.org/10.48550/arxiv.2608.24473"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.24473","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.24473","pdf_url":"https://arxiv.org/pdf/2608.24473","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/2608.24473","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5130223872","display_name":"Dong Huang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Huang, Dong","raw_affiliation_strings":["National University of Singapore , Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore , Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000019783","display_name":"Mark Harman","orcid":"https://orcid.org/0000-0002-5864-4488","observed_orcids":["https://orcid.org/0000-0002-5864-4488"]},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Harman, Mark","raw_affiliation_strings":["University College London , London , UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University College London , London , UK","institution_ids":["https://openalex.org/I45129253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088708850","display_name":"Jie M. Zhang","orcid":"https://orcid.org/0000-0003-0481-7264","observed_orcids":["https://orcid.org/0000-0003-0481-7264","https://orcid.org/0000-0001-7733-5392"]},"institutions":[{"id":"https://openalex.org/I183935753","display_name":"King's College London","ror":"https://ror.org/0220mzb33","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I183935753"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Zhang, Jie M.","raw_affiliation_strings":["King's College London , London , UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"King's College London , London , UK","institution_ids":["https://openalex.org/I183935753"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148289188","display_name":"Zhijiang Guo","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guo, Zhijiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133142981","display_name":"Mingzhe Du","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Du, Mingzhe","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5110918847","display_name":"See Kiong Ng","orcid":"https://orcid.org/0000-0001-6565-7511","observed_orcids":["https://orcid.org/0000-0001-6565-7511"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ng, See Kiong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":2,"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.9994999766349792,"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":0.9994999766349792,"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":0.0003000000142492354,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.0,"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/unit-test-generation","display_name":"unit test generation","score":0.9710000157356262},{"id":"https://openalex.org/keywords/test-suite-selection","display_name":"test suite selection","score":0.5770000219345093},{"id":"https://openalex.org/keywords/pareto-optimality","display_name":"Pareto optimality","score":0.7450000047683716},{"id":"https://openalex.org/keywords/occam-s-razor","display_name":"Occam's razor","score":0.890999972820282},{"id":"https://openalex.org/keywords/credit-assignment","display_name":"credit assignment","score":0.8109999895095825},{"id":"https://openalex.org/keywords/mutation-testing","display_name":"mutation testing","score":0.6850000023841858},{"id":"https://openalex.org/keywords/code-coverage","display_name":"code coverage","score":0.3199999928474426}],"concepts":[{"id":"https://openalex.org/C501734568","wikidata":"https://www.wikidata.org/wiki/Q42918","display_name":"Mutation","level":3,"score":0.5860999822616577},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5687000155448914},{"id":"https://openalex.org/C137635306","wikidata":"https://www.wikidata.org/wiki/Q182667","display_name":"Pareto principle","level":2,"score":0.5144000053405762},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.5037000179290771},{"id":"https://openalex.org/C2780148112","wikidata":"https://www.wikidata.org/wiki/Q1432581","display_name":"Proxy (statistics)","level":2,"score":0.49309998750686646},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.49140000343322754},{"id":"https://openalex.org/C68781425","wikidata":"https://www.wikidata.org/wiki/Q2052203","display_name":"Multi-objective optimization","level":2,"score":0.42660000920295715},{"id":"https://openalex.org/C2986314615","wikidata":"https://www.wikidata.org/wiki/Q36829","display_name":"Pareto optimal","level":3,"score":0.39430001378059387},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3935999870300293},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.38960000872612},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.37560001015663147},{"id":"https://openalex.org/C144559511","wikidata":"https://www.wikidata.org/wiki/Q2986279","display_name":"Principal (computer security)","level":2,"score":0.34860000014305115},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.33309999108314514},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3082999885082245},{"id":"https://openalex.org/C2778599509","wikidata":"https://www.wikidata.org/wiki/Q36829","display_name":"Pareto efficiency","level":3,"score":0.2904999852180481},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.28299999237060547},{"id":"https://openalex.org/C2777551076","wikidata":"https://www.wikidata.org/wiki/Q842332","display_name":"Front (military)","level":2,"score":0.2502000033855438}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.24473","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.24473","pdf_url":"https://arxiv.org/pdf/2608.24473","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.2608.24473","doi":"https://doi.org/10.48550/arxiv.2608.24473","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.24473","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:2608.24473","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.24473","pdf_url":"https://arxiv.org/pdf/2608.24473","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":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204264693.pdf","grobid_xml":"https://content.openalex.org/works/W7204264693.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7214038137","https://openalex.org/W7171620504","https://openalex.org/W6911399773","https://openalex.org/W7125243911","https://openalex.org/W7205001439","https://openalex.org/W7131249264","https://openalex.org/W7046909943","https://openalex.org/W7212117486","https://openalex.org/W7214937494","https://openalex.org/W7133329644"],"abstract_inverted_index":{"We":[0,147],"introduce":[1],"\\textbf{Ockhamareto},":[2],"a":[3],"single-shot":[4],"GRPO":[5],"framework":[6],"for":[7,196],"unit-test":[8,55],"generation":[9],"and":[10,19,38,73,117,143,160],"selection,":[11],"based":[12],"on":[13,70,93,120,162],"the":[14,51,58,63,98,125,131,151,155,163,183],"principles":[15],"of":[16,53,154],"\\emph{Ockham's":[17],"Razor}":[18],"\\emph{Pareto":[20],"Optimality}.":[21],"Ockhamareto":[22,60,113,128],"has":[23],"two":[24],"principal":[25],"components:":[26],"(i)~a":[27],"\\emph{Pareto-gated":[28],"Bonus}":[29],"that":[30,150],"rewards":[31],"only":[32],"rollouts":[33],"non-dominated":[34],"in~(mutation,":[35],"$-$\\#tests)":[36],"space,":[37],"(ii)~\\emph{Token-level":[39],"Segment":[40],"Credit},":[41],"which":[42],"attributes":[43],"each":[44,72,197],"test's":[45],"marginal":[46],"mutation":[47,83,116,139],"kills":[48],"back":[49],"to":[50,190],"tokens":[52],"its":[54],"block.":[56],"On":[57],"\\emph{UnLeakedTestBench~(ULT)},":[59],"\\emph{strictly":[61],"Pareto-dominates}":[62],"strongest":[64],"RL":[65],"baseline~(\\emph{MIST-RL}).":[66],"Furthermore,":[67],"it":[68,187],"dominates":[69],"{\\em":[71],"all}":[74],"optimization":[75],"objectives,":[76],"catching":[77],"more":[78,171],"bugs":[79],"($49.9\\%$":[80],"vs":[81,91],"$31.3\\%$":[82],"score":[84],"at":[85,133,140],"$N{=}5$),":[86],"using":[87],"\\emph{fewer}":[88],"tests":[89],"($2.60$":[90],"$4.67$":[92],"average),":[94],"thereby":[95],"achieving":[96],"$3.4\\times$":[97],"per-test":[99],"trade-off":[100,157,195],"improvement.":[101],"The":[102],"advantage":[103],"is":[104,166,188],"found":[105],"in":[106],"all":[107,134],"four":[108],"benchmarks~(\\emph{HumanEval+},":[109],"\\emph{MBPP+},":[110],"\\emph{CodeContests},":[111],"\\emph{TestGenEval-Lite}):":[112],"leads":[114],"both":[115],"coverage":[118],"metrics":[119],"every":[121],"one,":[122],"always":[123],"with":[124,169],"smallest":[126],"suite.":[127],"also":[129,148],"outperforms":[130],"state-of-the-art":[132],"model":[135,145],"scales,":[136],"adding":[137],"$+30$--$35$~pp":[138],"4B,":[141],"9B,":[142],"27B":[144],"sizes.":[146],"show":[149],"knee":[152],"point":[153],"optimal":[156],"between":[158],"efficiency":[159],"effectiveness":[161],"Pareto":[164,184],"front":[165,185],"not":[167],"correlated":[168],"obvious":[170],"easily":[172],"computed":[173],"proxy":[174],"metrics,":[175],"such":[176],"as":[177],"function":[178,198],"size.":[179],"This":[180],"finding":[181],"motivates":[182],"computation;":[186],"needed":[189],"identify":[191],"this":[192],"crucial":[193],"engineering":[194],"under":[199],"test.":[200]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-08-27T00:00:00"}