{"id":"https://openalex.org/W7166861486","doi":"https://doi.org/10.18653/v1/2026.findings-acl.886","title":"Plug-and-Play Data Module for Code RL: Adaptive Ambiguity Replay","display_name":"Plug-and-Play Data Module for Code RL: Adaptive Ambiguity Replay","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166861486","doi":"https://doi.org/10.18653/v1/2026.findings-acl.886"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.886","doi":"https://doi.org/10.18653/v1/2026.findings-acl.886","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.886","pdf_url":"https://aclanthology.org/2026.findings-acl.886.pdf","source":{"id":"https://openalex.org/S4363605144","display_name":"Findings of the Association for Computational Linguistics: ACL (Findings of ACL)","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":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2026.findings-acl.886.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139845217","display_name":"Jianqing Zhang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]},{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianqing Zhang","raw_affiliation_strings":["Shanghai Jiao Tong University ,","Tencent ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University ,","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Tencent ,","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5159513075","display_name":"Wei Xia","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Xia","raw_affiliation_strings":["Tencent ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent ,","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058931839","display_name":"Zhezheng Hao","orcid":"https://orcid.org/0000-0001-9900-894X","observed_orcids":["https://orcid.org/0000-0001-9900-894X"]},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhezheng Hao","raw_affiliation_strings":["Zhejiang University ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University ,","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139800959","display_name":"Hong Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hong Wang","raw_affiliation_strings":["Tencent ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent ,","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007017628","display_name":"Hande Dong","orcid":"https://orcid.org/0000-0003-0074-2664","observed_orcids":["https://orcid.org/0000-0003-0074-2664"]},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hande Dong","raw_affiliation_strings":["Tencent ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent ,","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139817756","display_name":"Qiang Lin","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiang Lin","raw_affiliation_strings":["Tencent ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent ,","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139815085","display_name":"Yang Janet Liu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yang Liu","raw_affiliation_strings":["Hong Kong Polytechnic University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hong Kong Polytechnic University","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100648774","display_name":"Jian Cao","orcid":"https://orcid.org/0000-0002-0036-9436","observed_orcids":["https://orcid.org/0000-0002-0036-9436"]},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Cao","raw_affiliation_strings":["Shanghai Jiao Tong University ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University ,","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100636286","display_name":"Qiang Yang","orcid":"https://orcid.org/0000-0001-5059-8360","observed_orcids":["https://orcid.org/0000-0001-5059-8360","https://orcid.org/0000-0002-0761-4692","https://orcid.org/0000-0002-6788-8775","https://orcid.org/0000-0002-6570-1516","https://orcid.org/0000-0002-6524-9443","https://orcid.org/0000-0002-0565-2273"]},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Qiang Yang","raw_affiliation_strings":["Hong Kong Polytechnic University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hong Kong Polytechnic University","institution_ids":["https://openalex.org/I14243506"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"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":0.44876699,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"17865","last_page":"17875"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.8086000084877014,"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":0.8086000084877014,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.1582999974489212,"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/T10533","display_name":"Teaching and Learning Programming","score":0.00800000037997961,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/experience-replay","display_name":"experience replay","score":0.9559999704360962},{"id":"https://openalex.org/keywords/code-generation","display_name":"code generation","score":0.7020000219345093},{"id":"https://openalex.org/keywords/source-code-modification","display_name":"code editing","score":0.7329999804496765},{"id":"https://openalex.org/keywords/data-scarcity","display_name":"data scarcity","score":0.5929999947547913},{"id":"https://openalex.org/keywords/policy-divergence","display_name":"policy divergence","score":0.7749999761581421},{"id":"https://openalex.org/keywords/importance-weighting","display_name":"importance weighting","score":0.5329999923706055},{"id":"https://openalex.org/keywords/training-dynamics","display_name":"training dynamics","score":0.4779999852180481},{"id":"https://openalex.org/keywords/plug-and-play-module","display_name":"plug-and-play module","score":0.6309999823570251}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6820999979972839},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5249999761581421},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.4287000000476837},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.367000013589859},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.35670000314712524},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.33399999141693115},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.33180001378059387},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.2799000144004822},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.25110000371932983},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.24869999289512634}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.886","doi":"https://doi.org/10.18653/v1/2026.findings-acl.886","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.886","pdf_url":"https://aclanthology.org/2026.findings-acl.886.pdf","source":{"id":"https://openalex.org/S4363605144","display_name":"Findings of the Association for Computational Linguistics: ACL (Findings of ACL)","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":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-acl.886","doi":"https://doi.org/10.18653/v1/2026.findings-acl.886","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.886","pdf_url":"https://aclanthology.org/2026.findings-acl.886.pdf","source":{"id":"https://openalex.org/S4363605144","display_name":"Findings of the Association for Computational Linguistics: ACL (Findings of ACL)","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":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G5847459458","display_name":null,"funder_award_id":"YG2024QNB05","funder_id":"https://openalex.org/F4320322999","funder_display_name":"Shanghai Jiao Tong University"},{"id":"https://openalex.org/G6188036497","display_name":null,"funder_award_id":"2025ZHYL003","funder_id":"https://openalex.org/F4320317789","funder_display_name":"Shanghai Municipal Health Commission"}],"funders":[{"id":"https://openalex.org/F4320316083","display_name":"Tencent","ror":"https://ror.org/00hhjss72"},{"id":"https://openalex.org/F4320317789","display_name":"Shanghai Municipal Health Commission","ror":null},{"id":"https://openalex.org/F4320322598","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98"},{"id":"https://openalex.org/F4320322999","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04"},{"id":"https://openalex.org/F4320335227","display_name":"Bijzonder Onderzoeksfonds UGent","ror":"https://ror.org/00cv9y106"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166861486.pdf","grobid_xml":"https://content.openalex.org/works/W7166861486.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4416549768","https://openalex.org/W7166853295","https://openalex.org/W4416157468","https://openalex.org/W4416245618","https://openalex.org/W4389524303","https://openalex.org/W7166829378","https://openalex.org/W7162655027","https://openalex.org/W7140530547","https://openalex.org/W4415798241","https://openalex.org/W7138852248"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1],"(RL)":[2],"is":[3],"effective":[4,129],"for":[5,48,68,128],"improving":[6],"code":[7,111],"generation":[8],"but":[9],"suffers":[10],"from":[11,81],"data":[12],"scarcity.While":[13],"experience":[14],"replay":[15,130],"mitigates":[16],"this,":[17,61],"existing":[18],"approaches":[19],"rely":[20],"on":[21,91,99,109],"static,":[22],"in-epoch":[23],"metrics":[24],"that":[25,42,73,104],"overlook":[26],"training":[27,58],"dynamics,":[28],"often":[29],"introducing":[30],"low-utility":[31],"or":[32],"outdated":[33],"data.Analyzing":[34],"RL":[35],"dynamics":[36],"via":[37],"dataset":[38],"cartography,":[39],"we":[40,62],"observe":[41],"\"ambiguous\"":[43],"samples,":[44],"which":[45],"are":[46],"vital":[47],"model":[49],"generalization,":[50],"rapidly":[51],"migrate":[52],"to":[53,94],"\"easy-to-learn\"":[54],"regions,":[55],"diminishing":[56],"their":[57],"value.To":[59],"address":[60],"propose":[63],"Adaptive":[64],"Ambiguity":[65],"Replay":[66],"(A2R)":[67],"RL,":[69],"a":[70,125],"plug-and-play":[71],"module":[72],"prioritizes":[74],"cross-epoch":[75,122],"ambiguous":[76],"samples.To":[77],"neutralize":[78],"the":[79],"noise":[80],"stale":[82],"experiences,":[83],"A2R":[84,105],"incorporates":[85],"an":[86],"adaptive":[87],"importance":[88],"mechanism":[89],"based":[90],"policy":[92],"divergence":[93],"weigh":[95],"replayed":[96],"rollouts.Extensive":[97],"experiments":[98],"nine":[100],"LLMs":[101],"(3B-14B)":[102],"demonstrate":[103],"outperforms":[106],"state-of-the-art":[107],"baselines":[108],"real-world":[110],"editing":[112],"tasks":[113],"across":[114],"both":[115],"unseen":[116],"and":[117],"learned":[118],"domains.Our":[119],"results":[120],"highlight":[121],"ambiguity":[123],"as":[124],"key":[126],"factor":[127],"in":[131],"RL.Code":[132]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-07-02T00:00:00"}
