{"id":"https://openalex.org/W7224436734","doi":"https://doi.org/10.18653/2026.findings-emnlp.1745","title":"RLPgR: Reinforcement Learning from Dependency-Aware Progress Rewards","display_name":"RLPgR: Reinforcement Learning from Dependency-Aware Progress Rewards","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7224436734","doi":"https://doi.org/10.18653/2026.findings-emnlp.1745"},"language":"en","primary_location":{"id":"doi:10.18653/2026.findings-emnlp.1745","doi":"https://doi.org/10.18653/2026.findings-emnlp.1745","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.findings-emnlp.1745","pdf_url":"https://aclanthology.org/2026.findings-emnlp.1745.pdf","source":{"id":"https://openalex.org/S7407096085","display_name":"Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2026","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://aclanthology.org/2026.findings-emnlp.1745.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5160072181","display_name":"Shaofan Liu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaofan Liu","raw_affiliation_strings":["College of Computer Science and Artificial Intelligence , Fudan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Artificial Intelligence , Fudan University","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5152803131","display_name":"Tingyi Yang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tingyi Yang","raw_affiliation_strings":["College of Computer Science and Artificial Intelligence , Fudan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Artificial Intelligence , Fudan University","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083173421","display_name":"Shihan Dou","orcid":"https://orcid.org/0009-0002-6013-3035","observed_orcids":["https://orcid.org/0009-0002-6013-3035"]},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shihan Dou","raw_affiliation_strings":["College of Computer Science and Artificial Intelligence , Fudan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Artificial Intelligence , Fudan University","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127127683","display_name":"Zhiheng Xi","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiheng Xi","raw_affiliation_strings":["College of Computer Science and Artificial Intelligence , Fudan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Artificial Intelligence , Fudan University","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160086910","display_name":"Junjie Ye","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junjie Ye","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160108474","display_name":"Junlin Shang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junlin Shang","raw_affiliation_strings":["College of Computer Science and Artificial Intelligence , Fudan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Artificial Intelligence , Fudan University","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100958962","display_name":"Yuming Yang","orcid":"https://orcid.org/0009-0002-5000-7609","observed_orcids":["https://orcid.org/0009-0002-5000-7609"]},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuming Yang","raw_affiliation_strings":["College of Computer Science and Artificial Intelligence , Fudan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Artificial Intelligence , Fudan University","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160087130","display_name":"Shaowen Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaowen Wang","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114357420","display_name":"Jiayi Chen","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiayi Chen","raw_affiliation_strings":["College of Computer Science and Artificial Intelligence , Fudan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Artificial Intelligence , Fudan University","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160114952","display_name":"Jiazheng Zhang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiazheng Zhang","raw_affiliation_strings":["College of Computer Science and Artificial Intelligence , Fudan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Artificial Intelligence , Fudan University","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160085018","display_name":"Guoqiang Zhang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guoqiang Zhang","raw_affiliation_strings":["College of Computer Science and Artificial Intelligence , Fudan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Artificial Intelligence , Fudan University","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125087202","display_name":"Huaibing Xie","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":"Huaibing Xie","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/A5130595624","display_name":"Pluto Zhou","orcid":"https://orcid.org/0009-0001-1494-2475","observed_orcids":["https://orcid.org/0009-0001-1494-2475"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pluto Zhou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139809977","display_name":"Tao Gui","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Gui","raw_affiliation_strings":["Institute of Trustworthy Embodied AI , Fudan University","Shanghai Key Laboratory of Multimodal Embodied AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Trustworthy Embodied AI , Fudan University","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"Shanghai Key Laboratory of Multimodal Embodied AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160143786","display_name":"Qi Zhang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi Zhang","raw_affiliation_strings":["College of Computer Science and Artificial Intelligence , Fudan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Artificial Intelligence , Fudan University","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5127443454","display_name":"Xuanjing Huang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuanjing Huang","raw_affiliation_strings":["Institute of Trustworthy Embodied AI , Fudan University","Shanghai Key Laboratory of Multimodal Embodied AI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Trustworthy Embodied AI , Fudan University","institution_ids":["https://openalex.org/I24943067"]},{"raw_affiliation_string":"Shanghai Key Laboratory of Multimodal Embodied AI","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"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":0.89876826,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"37334","last_page":"37364"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9452999830245972,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9452999830245972,"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/T10028","display_name":"Topic Modeling","score":0.025699999183416367,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.007699999958276749,"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/reinforcement-learning","display_name":"reinforcement learning","score":0.7820000052452087},{"id":"https://openalex.org/keywords/reward-function-design","display_name":"reward function design","score":0.4480000138282776},{"id":"https://openalex.org/keywords/dependency-parsing","display_name":"dependency parsing","score":0.4230000078678131},{"id":"https://openalex.org/keywords/grammatical-inference","display_name":"grammatical inference","score":0.3409999907016754}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.4154999852180481},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4043999910354614},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.3723999857902527},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.37070000171661377},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3391000032424927},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3346000015735626},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.30219998955726624},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.2782000005245209},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.2475000023841858},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.23839999735355377}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/2026.findings-emnlp.1745","doi":"https://doi.org/10.18653/2026.findings-emnlp.1745","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.findings-emnlp.1745","pdf_url":"https://aclanthology.org/2026.findings-emnlp.1745.pdf","source":{"id":"https://openalex.org/S7407096085","display_name":"Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/2026.findings-emnlp.1745","doi":"https://doi.org/10.18653/2026.findings-emnlp.1745","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.findings-emnlp.1745","pdf_url":"https://aclanthology.org/2026.findings-emnlp.1745.pdf","source":{"id":"https://openalex.org/S7407096085","display_name":"Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G1187148928","display_name":null,"funder_award_id":"62376061","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5542150374","display_name":null,"funder_award_id":"62476061","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7224436734.pdf","grobid_xml":"https://content.openalex.org/works/W7224436734.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2950829674","https://openalex.org/W7224349529","https://openalex.org/W7133196217","https://openalex.org/W3180701530","https://openalex.org/W7215916133","https://openalex.org/W7224313640","https://openalex.org/W7224653526","https://openalex.org/W7103882922","https://openalex.org/W2921772529","https://openalex.org/W6922263630"],"abstract_inverted_index":{"Group-relative":[0],"policy":[1],"optimization":[2],"(GRPO)":[3],"provides":[4],"a":[5,23,50,62,71,77,81,89,105,149],"stable":[6],"recipe":[7],"for":[8],"outcome-based":[9],"RL":[10],"on":[11,157],"language":[12],"model":[13,153],"reasoning,":[14],"but":[15],"its":[16,125],"credit":[17,190],"assignment":[18,191],"is":[19,163],"coarse:":[20],"it":[21,47,94],"broadcasts":[22],"single":[24],"trajectory":[25],"advantage":[26,103],"to":[27,36,91],"every":[28],"token,":[29],"regardless":[30],"of":[31,53,74,132],"how":[32],"individual":[33],"steps":[34,75],"contribute":[35],"the":[37,41,54,92,97,101,111,115,129,182,185],"outcome.We":[38],"call":[39],"this":[40],"uniform-broadcast":[42],"failure":[43],"mode":[44],"and":[45,85,155,168,177],"address":[46],"with":[48,80,165],"RLPgR,":[49],"dependency-aware":[51],"rescaling":[52],"existing":[55],"GRPO":[56],"advantage.RLPgR":[57],"parses":[58],"each":[59,68,120],"rollout":[60,117],"into":[61,76],"Progress":[63],"Dependency":[64],"Graph":[65],"(PDG),":[66],"where":[67],"node":[69,90,112],"groups":[70],"contiguous":[72],"span":[73],"milestone-level":[78],"unit":[79],"locally":[82],"validatable":[83],"artifact,":[84],"directed":[86],"edges":[87],"connect":[88],"artifacts":[93],"depends":[95],"on.Using":[96],"PDG,":[98],"RLPgR":[99,162],"rescales":[100],"grouprelative":[102],"by":[104],"small,":[106],"bounded,":[107],"signpreserving":[108],"factor":[109],"at":[110],"level.This":[113],"preserves":[114],"outcome-governed":[116],"direction":[118],"while":[119],"step's":[121],"update":[122],"better":[123],"reflects":[124],"dependency":[126],"role,":[127],"avoiding":[128],"reward-hacking":[130],"drift":[131],"densely":[133],"shaped":[134],"process":[135],"rewards.To":[136],"reduce":[137],"PDG":[138,178],"construction":[139],"cost,":[140],"we":[141],"train":[142],"an":[143],"open":[144],"Qwen3-8B":[145],"progress":[146],"annotator":[147],"amortizing":[148],"one-time":[150],"proprietary":[151],"bootstrap.Across":[152],"families":[154],"sizes":[156],"five":[158],"math":[159],"reasoning":[160],"benchmarks,":[161],"competitive":[164],"strong":[166],"outcome-RL":[167],"process-RL":[169],"baselines.Three":[170],"controlled":[171],"studies":[172],"(scaling-strength":[173],"sensitivity,":[174],"segment-level":[175],"baselines,":[176],"label":[179],"perturbation)":[180],"support":[181],"view":[183],"that":[184],"gain":[186],"comes":[187],"from":[188],"structured":[189],"rather":[192],"than":[193],"incidental":[194],"tuning.":[195]},"counts_by_year":[],"updated_date":"2026-11-01T11:40:01.658920","created_date":"2026-10-30T00:00:00"}