{"id":"https://openalex.org/W7202115341","doi":"https://doi.org/10.1109/isaeece70502.2026.11635708","title":"Reinforcement Learning Approaches for Code Generation: a Comparative Analysis","display_name":"Reinforcement Learning Approaches for Code Generation: a Comparative Analysis","publication_year":2026,"publication_date":"2026-06-01","ids":{"openalex":"https://openalex.org/W7202115341","doi":"https://doi.org/10.1109/isaeece70502.2026.11635708"},"language":"en","primary_location":{"id":"doi:10.1109/isaeece70502.2026.11635708","doi":"https://doi.org/10.1109/isaeece70502.2026.11635708","is_oa":true,"landing_page_url":"https://doi.org/10.1109/isaeece70502.2026.11635708","pdf_url":null,"source":{"id":"https://openalex.org/S4363605363","display_name":"International Symposium on Advances in Electrical, Electronics and Computer Engineering (ISAEECE)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 11th International Symposium on Advances in Electrical, Electronics and Computer Engineering (ISAEECE)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1109/isaeece70502.2026.11635708","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5146430286","display_name":"Ivan Alpatov","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210116741","display_name":"Innopolis University","ror":"https://ror.org/02b7jh107","country_code":"RU","type":"education","lineage":["https://openalex.org/I4210116741"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Ivan Alpatov","raw_affiliation_strings":["Innopolis University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Innopolis University","institution_ids":["https://openalex.org/I4210116741"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091303770","display_name":"Firas Jolha","orcid":"https://orcid.org/0009-0008-0664-8007","observed_orcids":["https://orcid.org/0009-0008-0664-8007"]},"institutions":[{"id":"https://openalex.org/I4210116741","display_name":"Innopolis University","ror":"https://ror.org/02b7jh107","country_code":"RU","type":"education","lineage":["https://openalex.org/I4210116741"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Firas Jolha","raw_affiliation_strings":["Innopolis University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Innopolis University","institution_ids":["https://openalex.org/I4210116741"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021301383","display_name":"Zamira Kholmatova","orcid":"https://orcid.org/0000-0003-1688-1183","observed_orcids":["https://orcid.org/0000-0003-1688-1183"]},"institutions":[{"id":"https://openalex.org/I4210116741","display_name":"Innopolis University","ror":"https://ror.org/02b7jh107","country_code":"RU","type":"education","lineage":["https://openalex.org/I4210116741"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Zamira Kholmatova","raw_affiliation_strings":["Innopolis University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Innopolis University","institution_ids":["https://openalex.org/I4210116741"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5146408153","display_name":"Aizat Murtazin","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210116741","display_name":"Innopolis University","ror":"https://ror.org/02b7jh107","country_code":"RU","type":"education","lineage":["https://openalex.org/I4210116741"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Aizat Murtazin","raw_affiliation_strings":["Innopolis University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Innopolis University","institution_ids":["https://openalex.org/I4210116741"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5146373362","display_name":"Daria Verevkina","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210116741","display_name":"Innopolis University","ror":"https://ror.org/02b7jh107","country_code":"RU","type":"education","lineage":["https://openalex.org/I4210116741"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Daria Verevkina","raw_affiliation_strings":["Innopolis University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Innopolis University","institution_ids":["https://openalex.org/I4210116741"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039583821","display_name":"Giancarlo Succi","orcid":"https://orcid.org/0000-0001-8847-0186","observed_orcids":["https://orcid.org/0000-0001-8847-0186"]},"institutions":[{"id":"https://openalex.org/I9360294","display_name":"University of Bologna","ror":"https://ror.org/01111rn36","country_code":"IT","type":"education","lineage":["https://openalex.org/I9360294"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Giancarlo Succi","raw_affiliation_strings":["Universit\u00e0 di Bologna, Alma Mater Studiorum"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e0 di Bologna, Alma Mater Studiorum","institution_ids":["https://openalex.org/I9360294"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047106210","display_name":"Alexander G. Tormasov","orcid":"https://orcid.org/0000-0001-6887-4327","observed_orcids":["https://orcid.org/0000-0001-6887-4327","https://orcid.org/0009-0009-8739-8747"]},"institutions":[{"id":"https://openalex.org/I193619901","display_name":"Constructor University","ror":"https://ror.org/02yrs2n53","country_code":"DE","type":"education","lineage":["https://openalex.org/I193619901"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Alexander Tormasov","raw_affiliation_strings":["Constructor University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Constructor University","institution_ids":["https://openalex.org/I193619901"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"825","last_page":"828"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9961000084877014,"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":0.9961000084877014,"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/T10533","display_name":"Teaching and Learning Programming","score":0.0007999999797903001,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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":0.0005000000237487257,"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/automatic-code-generation","display_name":"automatic code generation","score":0.8050000071525574},{"id":"https://openalex.org/keywords/group-relative-policy-optimization","display_name":"Group Relative Policy Optimization","score":0.9929999709129333},{"id":"https://openalex.org/keywords/preference-learning","display_name":"preference learning","score":0.578000009059906},{"id":"https://openalex.org/keywords/cyclomatic-complexity","display_name":"cyclomatic complexity","score":0.9829999804496765},{"id":"https://openalex.org/keywords/code-readability","display_name":"code readability","score":0.8790000081062317},{"id":"https://openalex.org/keywords/functional-correctness","display_name":"functional correctness","score":0.7039999961853027},{"id":"https://openalex.org/keywords/llm-fine-tuning","display_name":"LLM fine-tuning","score":0.7419999837875366}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6352999806404114},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.49160000681877136},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48579999804496765},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.4708000123500824},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3449000120162964},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3278000056743622},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.28200000524520874},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.2773999869823456},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2773999869823456},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.26409998536109924},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.2578999996185303}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/isaeece70502.2026.11635708","doi":"https://doi.org/10.1109/isaeece70502.2026.11635708","is_oa":true,"landing_page_url":"https://doi.org/10.1109/isaeece70502.2026.11635708","pdf_url":null,"source":{"id":"https://openalex.org/S4363605363","display_name":"International Symposium on Advances in Electrical, Electronics and Computer Engineering (ISAEECE)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 11th International Symposium on Advances in Electrical, Electronics and Computer Engineering (ISAEECE)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1109/isaeece70502.2026.11635708","doi":"https://doi.org/10.1109/isaeece70502.2026.11635708","is_oa":true,"landing_page_url":"https://doi.org/10.1109/isaeece70502.2026.11635708","pdf_url":null,"source":{"id":"https://openalex.org/S4363605363","display_name":"International Symposium on Advances in Electrical, Electronics and Computer Engineering (ISAEECE)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 11th International Symposium on Advances in Electrical, Electronics and Computer Engineering (ISAEECE)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W4385572634","https://openalex.org/W4400582872","https://openalex.org/W4404782360","https://openalex.org/W4414742445","https://openalex.org/W4415502377","https://openalex.org/W4416036282","https://openalex.org/W7133243119"],"related_works":["https://openalex.org/W4411950364","https://openalex.org/W7162326866","https://openalex.org/W4415798241","https://openalex.org/W7213283227","https://openalex.org/W125013037","https://openalex.org/W4402672108","https://openalex.org/W7166737528","https://openalex.org/W4403742539","https://openalex.org/W7167734468","https://openalex.org/W7204275870"],"abstract_inverted_index":{"The":[0],"rapid":[1],"advancement":[2],"of":[3,81,154],"Large":[4],"Language":[5],"Models":[6],"(LLMs)":[7],"has":[8],"transformed":[9],"automated":[10],"code":[11,20,47,91,140,169],"generation.":[12],"However,":[13],"generating":[14],"functionally":[15],"correct,":[16],"efficient,":[17],"and":[18,56,98,146,156],"maintainable":[19],"remains":[21],"a":[22,77,89,119,151],"challenging":[23],"task.":[24],"Traditional":[25],"supervised":[26],"fine-tuning":[27,46],"often":[28],"fails":[29],"to":[30],"optimize":[31],"multiple":[32],"software":[33],"quality":[34,92],"attributes":[35],"simultaneously.":[36],"This":[37],"study":[38],"investigates":[39],"two":[40],"reinforcement":[41],"learning":[42,65],"(RL)":[43],"approaches":[44],"for":[45,166],"generation":[48,170],"models:":[49],"Pairwise":[50],"Filtering":[51],"Proximal":[52],"Policy":[53,59],"Optimization":[54,60],"(PF-PPO)":[55],"Group":[57],"Relative":[58],"(GRPO).":[61],"PF-PPO":[62],"employs":[63],"prefer-ence":[64],"through":[66],"noisy":[67],"pairwise":[68],"comparisons,":[69],"while":[70],"GRPO":[71,117],"utilizes":[72],"group-wise":[73],"relative":[74],"ranking":[75],"with":[76],"median":[78],"baseline.":[79],"Instead":[80],"using":[82,108],"unstable":[83],"LLM-judge":[84],"rewards,":[85],"we":[86],"have":[87],"employed":[88],"static":[90,139],"metric,":[93],"which":[94],"combines":[95],"cyclomatic":[96],"complex-ity":[97],"readability":[99],"scores.":[100],"Experiments":[101],"were":[102],"conducted":[103],"on":[104],"the":[105,109],"DeepSeekCoder-1.3B-Instruct":[106],"model":[107],"highly":[110],"recognized":[111],"MBPP":[112],"benchmark.":[113],"Results":[114],"show":[115,135],"that":[116],"achieves":[118],"31%":[120],"improvement":[121],"in":[122,138],"functional":[123],"correctness":[124,145],"$\\left(R_{\\text":[125],"{UT":[126],"}}\\right)$,":[127],"outperforming":[128],"PF":[129],"\u2013PPO":[130],"(21%":[131],"improvement).":[132],"Both":[133],"methods":[134],"limited":[136],"gains":[137],"quality,":[141],"highlighting":[142],"trade-offs":[143],"between":[144],"maintainability.":[147],"Our":[148],"work":[149],"provides":[150],"comparative":[152],"analysis":[153],"preference-based":[155],"group-relative":[157],"RL":[158],"strategies":[159],"under":[160],"constrained":[161],"computational":[162],"settings,":[163],"offering":[164],"insights":[165],"future":[167],"RL-based":[168],"research.":[171]},"counts_by_year":[],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2026-08-11T00:00:00"}
