{"id":"https://openalex.org/W7166798773","doi":"https://doi.org/10.18653/v1/2026.findings-acl.1523","title":"Good Reasoning Makes Good Demonstrations: Implicit Reasoning Quality Supervision via In-Context Reinforcement Learning","display_name":"Good Reasoning Makes Good Demonstrations: Implicit Reasoning Quality Supervision via In-Context Reinforcement Learning","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166798773","doi":"https://doi.org/10.18653/v1/2026.findings-acl.1523"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.1523","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1523","pdf_url":"https://aclanthology.org/2026.findings-acl.1523.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":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.findings-acl.1523.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139779784","display_name":"Tiehua Mei","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tiehua Mei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139725878","display_name":"Minxuan Lv","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Minxuan Lv","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101391648","display_name":"Leiyu Pan","orcid":"https://orcid.org/0009-0002-5304-0914"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Leiyu Pan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081013230","display_name":"Zhenpeng Su","orcid":"https://orcid.org/0000-0001-5577-4538"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhenpeng Su","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038730121","display_name":"Hongru Hou","orcid":"https://orcid.org/0000-0003-3471-3781"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hongru Hou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008836380","display_name":"Hengrui Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hengrui Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139794898","display_name":"Ao Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ao Xu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139743713","display_name":"Deqing Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Deqing Yang","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":0.78803596,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"30452","last_page":"30469"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.42969998717308044,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.42969998717308044,"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":0.039500001817941666,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.033399999141693115,"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/quality","display_name":"Quality (philosophy)","score":0.5654000043869019},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.46639999747276306},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.3497999906539917},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.3346000015735626},{"id":"https://openalex.org/keywords/case-based-reasoning","display_name":"Case-based reasoning","score":0.334199994802475},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.2906999886035919},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.28859999775886536}],"concepts":[{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5654000043869019},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5480999946594238},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.46639999747276306},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4586000144481659},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.3497999906539917},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3375999927520752},{"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/C20162079","wikidata":"https://www.wikidata.org/wiki/Q1151406","display_name":"Case-based reasoning","level":2,"score":0.334199994802475},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.2906999886035919},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.28859999775886536},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.28679999709129333},{"id":"https://openalex.org/C159032336","wikidata":"https://www.wikidata.org/wiki/Q2488768","display_name":"Non-monotonic logic","level":2,"score":0.2750999927520752},{"id":"https://openalex.org/C2777379011","wikidata":"https://www.wikidata.org/wiki/Q938545","display_name":"Implicit learning","level":3,"score":0.2676999866962433},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.267300009727478},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.2639999985694885},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.2540999948978424},{"id":"https://openalex.org/C195344581","wikidata":"https://www.wikidata.org/wiki/Q2555318","display_name":"Automated reasoning","level":2,"score":0.2502000033855438}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.1523","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1523","pdf_url":"https://aclanthology.org/2026.findings-acl.1523.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"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-acl.1523","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1523","pdf_url":"https://aclanthology.org/2026.findings-acl.1523.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":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166798773.pdf","grobid_xml":"https://content.openalex.org/works/W7166798773.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Reinforcement":[0],"Learning":[1],"with":[2],"Verifiable":[3],"Rewards":[4],"(RLVR)":[5],"improves":[6],"reasoning":[7,32,122,131],"in":[8,127],"large":[9],"language":[10],"models":[11],"but":[12],"treats":[13],"all":[14],"correct":[15,25],"solutions":[16,37],"equally,":[17],"potentially":[18],"reinforcing":[19],"flawed":[20],"traces":[21,115],"that":[22,30,55,94],"arrive":[23],"at":[24,142],"answers":[26],"by":[27,102],"chance.We":[28],"observe":[29],"better":[31,34],"makes":[33],"demonstrations:":[35],"high-quality":[36,114],"serve":[38],"as":[39],"more":[40],"effective":[41],"in-context":[42,60],"examples":[43],"than":[44],"low-quality":[45],"ones.We":[46],"term":[47],"this":[48,78,95],"teaching":[49],"ability":[50,62],"Demonstration":[51],"Utility,":[52],"and":[53,130,138],"show":[54],"the":[56],"policy":[57],"model's":[58],"own":[59],"learning":[61],"provides":[63],"an":[64],"efficient":[65],"way":[66],"to":[67,107,113],"measure":[68],"it,":[69],"yielding":[70],"a":[71,103],"quality":[72,132],"signal":[73,79],"termed":[74],"Evidence":[75,108],"Gain.To":[76],"leverage":[77],"during":[80],"training,":[81],"we":[82,92],"introduce":[83],"In-Context":[84],"RLVR,":[85],"which":[86],"prepends":[87],"demonstrations":[88],"before":[89],"each":[90],"rollout.Theoretically,":[91],"prove":[93],"simple":[96],"input":[97],"modification":[98],"implicitly":[99],"reweights":[100],"rewards":[101],"factor":[104],"approximately":[105],"proportional":[106],"Gain,":[109],"assigning":[110],"higher":[111],"weights":[112],"without":[116],"requiring":[117],"costly":[118],"computation.Experiments":[119],"on":[120],"mathematical":[121],"benchmarks":[123],"demonstrate":[124],"consistent":[125],"improvements":[126],"both":[128],"accuracy":[129],"over":[133],"standard":[134],"RLVR":[135],"baselines.Our":[136],"codes":[137],"datasets":[139],"are":[140],"available":[141],"https://":[143],"github.com/Mithas-114/IC-DAPO.":[144]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}