{"id":"https://openalex.org/W7166829378","doi":"https://doi.org/10.18653/v1/2026.findings-acl.2150","title":"CodeRM-NT: Reward Model for Code RL without Unit Tests","display_name":"CodeRM-NT: Reward Model for Code RL without Unit Tests","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166829378","doi":"https://doi.org/10.18653/v1/2026.findings-acl.2150"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.2150","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.2150","pdf_url":"https://aclanthology.org/2026.findings-acl.2150.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.findings-acl.2150.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139767285","display_name":"Xiao Xia","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiao Xia","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139765891","display_name":"Dan Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dan Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139797610","display_name":"Tianrui Sun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tianrui Sun","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":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.81915629,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"43316","last_page":"43333"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12072","display_name":"Machine Learning and Algorithms","score":0.14030000567436218,"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":0.14030000567436218,"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/T10260","display_name":"Software Engineering Research","score":0.1339000016450882,"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.06679999828338623,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5220999717712402},{"id":"https://openalex.org/keywords/unit","display_name":"Unit (ring theory)","score":0.36980000138282776},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.30379998683929443},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.25760000944137573},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.23639999330043793}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6177999973297119},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5220999717712402},{"id":"https://openalex.org/C122637931","wikidata":"https://www.wikidata.org/wiki/Q118084","display_name":"Unit (ring theory)","level":2,"score":0.36980000138282776},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3562999963760376},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.30379998683929443},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.25760000944137573},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.25360000133514404},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.2379000037908554},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.23639999330043793},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.23160000145435333}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.2150","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.2150","pdf_url":"https://aclanthology.org/2026.findings-acl.2150.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-acl.2150","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.2150","pdf_url":"https://aclanthology.org/2026.findings-acl.2150.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320322392","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166829378.pdf","grobid_xml":"https://content.openalex.org/works/W7166829378.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Providing":[0],"accurate":[1],"reward":[2,58,87],"signals":[3],"for":[4,101],"code":[5,22,31,57,77,85,102,136],"generated":[6],"by":[7,39,73,109],"large":[8],"language":[9],"models":[10],"(LLMs)":[11],"is":[12,96],"a":[13,56],"significant":[14],"challenge":[15],"in":[16],"applying":[17],"reinforcement":[18],"learning":[19,108,140],"(RL)":[20],"to":[21,29,75,83,92],"generation.Existing":[23],"methods":[24],"rely":[25],"on":[26,63,116,134,142],"unit":[27,47,64,128],"tests":[28,48],"evaluate":[30],"correctness":[32],"and":[33,44,79,111],"provide":[34],"rewards,":[35,130],"which":[36],"are":[37],"hindered":[38],"the":[40,90],"difficulty":[41],"of":[42,98],"acquiring":[43],"verifying":[45],"reliable":[46],"at":[49],"scale.In":[50],"this":[51],"work,":[52],"we":[53],"propose":[54],"CODERM-NT,":[55],"model":[59,146],"with":[60,86,123],"no":[61],"reliance":[62],"tests.Our":[65],"method":[66],"leverages":[67],"Monte":[68],"Carlo":[69],"Tree":[70],"Search":[71],"guided":[72],"LLMs":[74],"generate":[76],"snippets":[78],"judges":[80],"execution":[81],"traces":[82],"annotate":[84],"signals.We":[88],"use":[89],"rewards":[91,100],"train":[93],"CODERM-NT":[94,124,143],"that":[95,121],"capable":[97],"providing":[99],"during":[103],"RL.CODERM-NT":[104],"also":[105],"facilitates":[106],"curriculum":[107,139],"scoring":[110],"sorting":[112],"training":[113,122],"samples":[114],"based":[115,141],"their":[117],"difficulty.Experimental":[118],"results":[119],"demonstrate":[120],"consistently":[125],"outperforms":[126],"synthetic":[127],"test-based":[129],"yielding":[131],"superior":[132],"performance":[133],"multiple":[135],"generation":[137],"benchmarks.Additionally,":[138],"further":[144],"enhances":[145],"performance.":[147]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}