{"id":"https://openalex.org/W4414360467","doi":"https://doi.org/10.24963/ijcai.2025/965","title":"SRA-MCTS: Self-driven Reasoning Augmentation with Monte Carlo Tree Search for Code Generation","display_name":"SRA-MCTS: Self-driven Reasoning Augmentation with Monte Carlo Tree Search for Code Generation","publication_year":2025,"publication_date":"2025-09-01","ids":{"openalex":"https://openalex.org/W4414360467","doi":"https://doi.org/10.24963/ijcai.2025/965"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2025/965","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/965","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101554598","display_name":"Bin Xu","orcid":"https://orcid.org/0000-0001-9518-2940"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Bin Xu","raw_affiliation_strings":["Beijing Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074012827","display_name":"Yu\u2010Kai Lin","orcid":"https://orcid.org/0000-0002-8995-8375"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiguan Lin","raw_affiliation_strings":["Beijing Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100676456","display_name":"Yinghao Li","orcid":"https://orcid.org/0000-0002-8830-4193"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yinghao Li","raw_affiliation_strings":["Beijing Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074250521","display_name":"Yang Gao","orcid":"https://orcid.org/0000-0002-2488-1813"},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Gao","raw_affiliation_strings":["Beijing Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Beijing Institute of Technology","institution_ids":["https://openalex.org/I125839683"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101554598"],"corresponding_institution_ids":["https://openalex.org/I125839683"],"apc_list":null,"apc_paid":null,"fwci":2.5499,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.9049604,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"8678","last_page":"8686"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11450","display_name":"Model-Driven Software Engineering Techniques","score":0.9660000205039978,"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/T11450","display_name":"Model-Driven Software Engineering Techniques","score":0.9660000205039978,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9621999859809875,"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":0.9570000171661377,"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/monte-carlo-tree-search","display_name":"Monte Carlo tree search","score":0.6384999752044678},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.5544000267982483},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.5220999717712402},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5103999972343445},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.476500004529953},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4133000075817108},{"id":"https://openalex.org/keywords/monte-carlo-method","display_name":"Monte Carlo method","score":0.38530001044273376},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.35850000381469727},{"id":"https://openalex.org/keywords/model-based-reasoning","display_name":"Model-based reasoning","score":0.35740000009536743}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7731000185012817},{"id":"https://openalex.org/C46149586","wikidata":"https://www.wikidata.org/wiki/Q11785332","display_name":"Monte Carlo tree search","level":3,"score":0.6384999752044678},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.5544000267982483},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.5220999717712402},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5166000127792358},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.515500009059906},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5103999972343445},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.476500004529953},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4133000075817108},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3882000148296356},{"id":"https://openalex.org/C19499675","wikidata":"https://www.wikidata.org/wiki/Q232207","display_name":"Monte Carlo method","level":2,"score":0.38530001044273376},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.35850000381469727},{"id":"https://openalex.org/C37335422","wikidata":"https://www.wikidata.org/wiki/Q6888134","display_name":"Model-based reasoning","level":3,"score":0.35740000009536743},{"id":"https://openalex.org/C195344581","wikidata":"https://www.wikidata.org/wiki/Q2555318","display_name":"Automated reasoning","level":2,"score":0.35679998993873596},{"id":"https://openalex.org/C89288958","wikidata":"https://www.wikidata.org/wiki/Q7301504","display_name":"Reasoning system","level":2,"score":0.33340001106262207},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.3190000057220459},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.29679998755455017},{"id":"https://openalex.org/C125583679","wikidata":"https://www.wikidata.org/wiki/Q755673","display_name":"Search algorithm","level":2,"score":0.29600000381469727},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.2953000068664551},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2856999933719635},{"id":"https://openalex.org/C86827895","wikidata":"https://www.wikidata.org/wiki/Q7098582","display_name":"Opportunistic reasoning","level":4,"score":0.2840000092983246},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.2766999900341034},{"id":"https://openalex.org/C56289965","wikidata":"https://www.wikidata.org/wiki/Q5249246","display_name":"Decision tree model","level":3,"score":0.2759999930858612},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.27230000495910645},{"id":"https://openalex.org/C83725634","wikidata":"https://www.wikidata.org/wiki/Q7268699","display_name":"Qualitative reasoning","level":2,"score":0.26019999384880066},{"id":"https://openalex.org/C166088908","wikidata":"https://www.wikidata.org/wiki/Q308495","display_name":"Abductive reasoning","level":2,"score":0.2597000002861023},{"id":"https://openalex.org/C93959086","wikidata":"https://www.wikidata.org/wiki/Q6888345","display_name":"Model selection","level":2,"score":0.2565000057220459},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.2563000023365021},{"id":"https://openalex.org/C159032336","wikidata":"https://www.wikidata.org/wiki/Q2488768","display_name":"Non-monotonic logic","level":2,"score":0.2554999887943268},{"id":"https://openalex.org/C20162079","wikidata":"https://www.wikidata.org/wiki/Q1151406","display_name":"Case-based reasoning","level":2,"score":0.2513999938964844}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2025/965","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/965","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":null,"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":{"Large":[0],"language":[1],"models":[2],"exhibit":[3],"remarkable":[4],"performance":[5,126],"in":[6,105],"simple":[7],"code":[8,158],"generation":[9],"tasks.":[10],"However,":[11],"they":[12],"encounter":[13],"significant":[14,152],"challenges":[15],"when":[16],"addressing":[17],"complex":[18],"problems":[19],"that":[20,122],"require":[21],"reasoning":[22,33,45,54,70,94],"and":[23,56,79,109,159],"question":[24],"decomposition.":[25],"To":[26],"tackle":[27],"this,":[28],"we":[29],"propose":[30],"a":[31,77,91],"self-driven":[32],"augmentation":[34],"process,":[35],"SRA-MCTS,":[36],"which":[37],"incorporates":[38],"Monte":[39],"Carlo":[40],"Tree":[41],"Search":[42],"(MCTS)":[43],"for":[44,116,154],"data":[46,115,160],"generation.":[47],"SRA-MCTS":[48,123],"enables":[49],"LLMs":[50],"to":[51,66,82,97,137],"self-generate":[52],"intermediate":[53,69],"steps":[55],"perform":[57],"iterative":[58],"self-evaluation,":[59],"facilitating":[60],"self-improvement.":[61,156],"Specifically,":[62],"it":[63,141],"utilizes":[64],"MCTS":[65,75],"produce":[67],"diverse":[68,93],"steps.":[71],"During":[72],"each":[73],"iteration,":[74],"generates":[76],"step":[78],"employs":[80],"self-evaluation":[81],"guide":[83],"the":[84,103,138,147,151],"selection":[85],"of":[86],"subsequent":[87],"branches,":[88],"ultimately":[89],"forming":[90],"sufficiently":[92],"path":[95],"referred":[96],"as":[98,113],"\u201cthinking\u201d.":[99],"This":[100],"thinking":[101],"guides":[102],"model":[104,130,155],"generating":[106],"corresponding":[107],"code,":[108],"both":[110],"are":[111,161],"combined":[112],"training":[114],"supervised":[117],"fine-tuning.":[118],"Experimental":[119],"results":[120],"demonstrate":[121],"achieves":[124],"consistent":[125],"improvements":[127],"across":[128],"three":[129],"scales":[131],"without":[132],"additional":[133],"supervisory":[134],"assistance.":[135],"Applied":[136],"Meta-Llama-3.1-8B-Instruct":[139],"model,":[140],"delivers":[142],"an":[143],"11-point":[144],"improvement":[145],"on":[146],"MBPP-Complex":[148],"dataset,":[149],"underscoring":[150],"potential":[153],"The":[157],"available":[162],"at":[163],"https://github.com/DIRECT-BIT/SRA-MCTS.":[164]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-10T00:00:00"}