{"id":"https://openalex.org/W4414900408","doi":"https://doi.org/10.18653/v1/2026.findings-acl.27","title":"Towards Hierarchical Multi-Step Reward Models for Enhanced Reasoning in Large Language Models","display_name":"Towards Hierarchical Multi-Step Reward Models for Enhanced Reasoning in Large Language Models","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W4414900408","doi":"https://doi.org/10.18653/v1/2026.findings-acl.27"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.27","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.27","pdf_url":"https://aclanthology.org/2026.findings-acl.27.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":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.findings-acl.27.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100348937","display_name":"Teng Wang","orcid":"https://orcid.org/0000-0002-2244-4513"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Teng Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Jiang Zhangyi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiang Zhangyi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047567293","display_name":"Zhe He","orcid":"https://orcid.org/0000-0003-3608-0244"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhenqi He","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110313316","display_name":"Shenyang Tong","orcid":"https://orcid.org/0009-0001-8236-2819"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hailei Gong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110313316","display_name":"Shenyang Tong","orcid":"https://orcid.org/0009-0001-8236-2819"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shenyang Tong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012736692","display_name":"Wenhan Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wenhan Yang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047414727","display_name":"Zeyu Li","orcid":"https://orcid.org/0000-0003-3932-9244"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zeyu Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016643106","display_name":"Yanan Zheng","orcid":"https://orcid.org/0000-0002-9823-0191"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yanan Zheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Zifan He","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zifan He","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Zewen Ye","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zewen Ye","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Shengjie Ma","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shengjie Ma","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Jianping Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jianping Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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":0.00952229,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"565","last_page":"576"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.98089998960495,"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/T10028","display_name":"Topic Modeling","score":0.98089998960495,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9472000002861023,"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/robustness","display_name":"Robustness (evolution)","score":0.5831000208854675},{"id":"https://openalex.org/keywords/opportunistic-reasoning","display_name":"Opportunistic reasoning","score":0.5490000247955322},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.44690001010894775},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.43479999899864197},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.38989999890327454},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.3763999938964844},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.3594000041484833},{"id":"https://openalex.org/keywords/reasoning-system","display_name":"Reasoning system","score":0.3547999858856201}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7840999960899353},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6527000069618225},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6050999760627747},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5831000208854675},{"id":"https://openalex.org/C86827895","wikidata":"https://www.wikidata.org/wiki/Q7098582","display_name":"Opportunistic reasoning","level":4,"score":0.5490000247955322},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.44690001010894775},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.43479999899864197},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.38989999890327454},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.3763999938964844},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3594000041484833},{"id":"https://openalex.org/C89288958","wikidata":"https://www.wikidata.org/wiki/Q7301504","display_name":"Reasoning system","level":2,"score":0.3547999858856201},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.3497999906539917},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.33640000224113464},{"id":"https://openalex.org/C37335422","wikidata":"https://www.wikidata.org/wiki/Q6888134","display_name":"Model-based reasoning","level":3,"score":0.33250001072883606},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3310999870300293},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.32120001316070557},{"id":"https://openalex.org/C163797641","wikidata":"https://www.wikidata.org/wiki/Q2067937","display_name":"Tree structure","level":3,"score":0.27469998598098755},{"id":"https://openalex.org/C195344581","wikidata":"https://www.wikidata.org/wiki/Q2555318","display_name":"Automated reasoning","level":2,"score":0.27079999446868896},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.2660999894142151},{"id":"https://openalex.org/C144986985","wikidata":"https://www.wikidata.org/wiki/Q871236","display_name":"Hierarchical database model","level":2,"score":0.2522999942302704}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.27","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.27","pdf_url":"https://aclanthology.org/2026.findings-acl.27.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":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2503.13551","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.13551","pdf_url":"https://arxiv.org/pdf/2503.13551","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2503.13551","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2503.13551","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-acl.27","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.27","pdf_url":"https://aclanthology.org/2026.findings-acl.27.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":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4414900408.pdf","grobid_xml":"https://content.openalex.org/works/W4414900408.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Teng":[0],"Wang,":[1],"Jiang":[2],"Zhangyi,":[3],"Zhenqi":[4],"He,":[5,17],"Hailei":[6],"Gong,":[7],"Shenyang":[8],"Tong,":[9],"Wenhan":[10],"Yang,":[11],"Zeyu":[12],"Li,":[13],"Yanan":[14],"Zheng,":[15],"Zifan":[16],"Zewen":[18],"Ye,":[19],"Shengjie":[20],"Ma,":[21],"Jianping":[22],"Zhang.":[23],"Findings":[24],"of":[25],"the":[26],"Association":[27],"for":[28],"Computational":[29],"Linguistics:":[30],"ACL":[31],"2026.":[32,33]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}