{"id":"https://openalex.org/W4412889385","doi":"https://doi.org/10.18653/v1/2025.acl-srw.8","title":"Can Multi-turn Self-refined Single Agent LMs with Retrieval Solve Hard Coding Problems?","display_name":"Can Multi-turn Self-refined Single Agent LMs with Retrieval Solve Hard Coding Problems?","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412889385","doi":"https://doi.org/10.18653/v1/2025.acl-srw.8"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.acl-srw.8","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-srw.8","pdf_url":"https://aclanthology.org/2025.acl-srw.8.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":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.acl-srw.8.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5092162513","display_name":"Md. Tanzib Hosain","orcid":"https://orcid.org/0009-0007-8723-7922"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Md Tanzib Hosain","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5021919229","display_name":"Md. Kishor Morol","orcid":"https://orcid.org/0000-0002-4468-8260"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Md Kishor Morol","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5092162513"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.1026,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.95288116,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"129","last_page":"142"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10100","display_name":"Metaheuristic Optimization Algorithms Research","score":0.9609000086784363,"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/T10100","display_name":"Metaheuristic Optimization Algorithms Research","score":0.9609000086784363,"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/T10320","display_name":"Neural Networks and Applications","score":0.9455999732017517,"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/computer-science","display_name":"Computer science","score":0.722461462020874},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.6072060465812683},{"id":"https://openalex.org/keywords/turn","display_name":"Turn (biochemistry)","score":0.4828341603279114},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3512771725654602},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3385905921459198},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15675625205039978},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.07295173406600952}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.722461462020874},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.6072060465812683},{"id":"https://openalex.org/C85641259","wikidata":"https://www.wikidata.org/wiki/Q290042","display_name":"Turn (biochemistry)","level":2,"score":0.4828341603279114},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3512771725654602},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3385905921459198},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15675625205039978},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.07295173406600952},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.acl-srw.8","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-srw.8","pdf_url":"https://aclanthology.org/2025.acl-srw.8.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":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.acl-srw.8","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-srw.8","pdf_url":"https://aclanthology.org/2025.acl-srw.8.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":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412889385.pdf","grobid_xml":"https://content.openalex.org/works/W4412889385.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W4412839308","https://openalex.org/W4231070408","https://openalex.org/W943151747","https://openalex.org/W2048981943","https://openalex.org/W2051487156","https://openalex.org/W2753901553","https://openalex.org/W2804368879"],"abstract_inverted_index":{"Among":[0],"the":[1,21,42,131],"hardest":[2],"tasks":[3],"for":[4,80],"humans":[5],"are":[6,68],"those":[7],"found":[8],"in":[9],"competitive":[10,81],"programming":[11,51,82],"where":[12],"problems":[13,144],"require":[14],"sophisticated":[15],"algorithmic":[16,167],"thinking,":[17],"puzzle":[18],"solving,":[19],"and":[20,61,65,72,110,166,175],"creation":[22],"of":[23,47,76,130,142],"effective":[24],"code.As":[25],"a":[26,74,95,121,127,156],"domain":[27],"to":[28,70,117,125],"assess":[29],"language":[30],"models":[31],"(LMs),":[32],"it":[33],"has":[34],"not":[35],"received":[36],"enough":[37],"attention,":[38],"though.This":[39],"study":[40],"presents":[41],"ICPC":[43],"benchmark,":[44],"which":[45,104],"consists":[46],"254":[48],"international":[49],"collegiate":[50],"contest":[52],"(ICPC)":[53],"tasks.Each":[54],"problem":[55],"includes":[56],"official":[57],"analysis,":[58],"reference":[59],"code,":[60],"sample,":[62],"high-quality":[63],"unit,":[64],"hidden":[66],"tests.We":[67],"able":[69],"develop":[71],"evaluate":[73],"variety":[75],"LM":[77],"inference":[78,102],"techniques":[79],"with":[83,108,154,163],"these":[84],"resources.With":[85],"zero-shot":[86],"chain-of-thought":[87],"prompting,":[88],"we":[89,119,134],"find":[90],"that":[91,136,145],"o1":[92,137],"only":[93],"achieves":[94],"19.1%":[96],"pass@1":[97],"solve":[98,139],"rate.With":[99],"our":[100,172,179],"best":[101],"technique,":[103],"combines":[105],"multi-turn":[106],"self-judge":[107],"reflection":[109],"retrieval":[111],"over":[112],"episodic":[113],"information,":[114],"raises":[115],"this":[116],"42.2%.Furthermore,":[118],"conduct":[120],"new":[122],"human-in-the-loop":[123],"investigation":[124],"gain":[126],"deeper":[128],"understanding":[129],"remaining":[132],"difficulties.Surprisingly,":[133],"discover":[135],"can":[138],"17":[140],"out":[141],"18":[143],"were":[146],"previously":[147],"unsolvable":[148],"by":[149,171],"any":[150],"model":[151],"or":[152],"technique":[153],"just":[155],"few":[157],"specific":[158],"instructions.A":[159],"footstep":[160],"toward":[161],"LMs":[162],"grounded,":[164],"imaginative,":[165],"thinking":[168],"is":[169],"provided":[170],"quantitative":[173],"findings":[174],"qualitative":[176],"research.We":[177],"open-source":[178],"code":[180],"at":[181],"https://github.com/kraritt/zolve.":[182]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-03-25T14:56:36.534964","created_date":"2025-10-10T00:00:00"}