{"id":"https://openalex.org/W7166800456","doi":"https://doi.org/10.18653/v1/2026.acl-long.2122","title":"Thinking-Based Non-Thinking: Solving the Reward Hacking Problem in Training Hybrid Reasoning Models via Reinforcement Learning","display_name":"Thinking-Based Non-Thinking: Solving the Reward Hacking Problem in Training Hybrid Reasoning Models via Reinforcement Learning","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166800456","doi":"https://doi.org/10.18653/v1/2026.acl-long.2122"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.acl-long.2122","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.2122","pdf_url":"https://aclanthology.org/2026.acl-long.2122.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 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.acl-long.2122.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139764479","display_name":"Siyuan Gan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Siyuan Gan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139754567","display_name":"Jiaheng Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiaheng Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139718705","display_name":"Boyan Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Boyan Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139799776","display_name":"Tianpei Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tianpei Yang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039425262","display_name":"Runqing Miao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Runqing Miao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139727250","display_name":"Yuyao Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuyao Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139746987","display_name":"Fanyu Meng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fanyu Meng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139749481","display_name":"Junlan Feng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junlan Feng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049175214","display_name":"Linjian Meng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Linjian Meng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139723805","display_name":"Jing Huo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jing Huo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139729210","display_name":"Yang Gao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang Gao","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":0.78979147,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"45754","last_page":"45771"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.17399999499320984,"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":0.17399999499320984,"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":0.12809999287128448,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.06120000034570694,"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":0.5572999715805054},{"id":"https://openalex.org/keywords/hacker","display_name":"Hacker","score":0.49000000953674316},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.4309999942779541},{"id":"https://openalex.org/keywords/association","display_name":"Association (psychology)","score":0.3666999936103821},{"id":"https://openalex.org/keywords/hybrid-learning","display_name":"Hybrid learning","score":0.2809000015258789},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.27730000019073486}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5893999934196472},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5763000249862671},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5572999715805054},{"id":"https://openalex.org/C86844869","wikidata":"https://www.wikidata.org/wiki/Q2798820","display_name":"Hacker","level":2,"score":0.49000000953674316},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.4309999942779541},{"id":"https://openalex.org/C142853389","wikidata":"https://www.wikidata.org/wiki/Q744778","display_name":"Association (psychology)","level":2,"score":0.3666999936103821},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3046000003814697},{"id":"https://openalex.org/C3018790387","wikidata":"https://www.wikidata.org/wiki/Q869010","display_name":"Hybrid learning","level":2,"score":0.2809000015258789},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.27730000019073486},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.2736000120639801},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.2644999921321869},{"id":"https://openalex.org/C195344581","wikidata":"https://www.wikidata.org/wiki/Q2555318","display_name":"Automated reasoning","level":2,"score":0.26330000162124634},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.26330000162124634},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.26159998774528503},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.2578999996185303}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.2122","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.2122","pdf_url":"https://aclanthology.org/2026.acl-long.2122.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 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.acl-long.2122","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.2122","pdf_url":"https://aclanthology.org/2026.acl-long.2122.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 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2328581383","display_name":null,"funder_award_id":"62276128","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2762746718","display_name":null,"funder_award_id":"62192783","funder_id":"https://openalex.org/F4320324852","funder_display_name":"Nanjing University"},{"id":"https://openalex.org/G2767813700","display_name":null,"funder_award_id":"62192783","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3352331163","display_name":null,"funder_award_id":"62406111","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3352541487","display_name":null,"funder_award_id":"BK20243051","funder_id":"https://openalex.org/F4320322769","funder_display_name":"Natural Science Foundation of Jiangsu Province"},{"id":"https://openalex.org/G5614591551","display_name":null,"funder_award_id":"14380128","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G6491868395","display_name":null,"funder_award_id":"KG202514","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G6794409734","display_name":null,"funder_award_id":"BG2024031","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7957610226","display_name":null,"funder_award_id":"JYB2025XDXM118","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"},{"id":"https://openalex.org/F4320321106","display_name":"Ministry of Education of the People's Republic of China","ror":"https://ror.org/01mv9t934"},{"id":"https://openalex.org/F4320322769","display_name":"Natural Science Foundation of Jiangsu Province","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320324852","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166800456.pdf","grobid_xml":"https://content.openalex.org/works/W7166800456.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Siyuan":[0],"Gan,":[1],"Jiaheng":[2],"Liu,":[3],"Boyan":[4],"Wang,":[5],"Tianpei":[6],"Yang,":[7],"Runqing":[8],"Miao,":[9],"Yuyao":[10],"Zhang,":[11],"Fanyu":[12],"Meng,":[13,17],"Junlan":[14],"Feng,":[15],"Linjian":[16],"Jing":[18],"Huo,":[19],"Yang":[20],"Gao.":[21],"Proceedings":[22],"of":[23,28],"the":[24,29],"64th":[25],"Annual":[26],"Meeting":[27],"Association":[30],"for":[31],"Computational":[32],"Linguistics":[33],"(Volume":[34],"1:":[35],"Long":[36],"Papers).":[37],"2026.":[38]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}