{"id":"https://openalex.org/W7138427124","doi":"https://doi.org/10.1609/aaai.v40i41.40752","title":"Promoting Efficient Reasoning with Verifiable Stepwise Reward","display_name":"Promoting Efficient Reasoning with Verifiable Stepwise Reward","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138427124","doi":"https://doi.org/10.1609/aaai.v40i41.40752"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i41.40752","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i41.40752","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v40i41.40752","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129705418","display_name":"Chuhuai Yue","orcid":null},"institutions":[{"id":"https://openalex.org/I125839683","display_name":"Beijing Institute of Technology","ror":"https://ror.org/01skt4w74","country_code":"CN","type":"education","lineage":["https://openalex.org/I125839683","https://openalex.org/I890469752"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chuhuai Yue","raw_affiliation_strings":["Meituan\nBeijing Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meituan\nBeijing Institute of Technology","institution_ids":["https://openalex.org/I125839683"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113355125","display_name":"Chengqi Dong","orcid":null},"institutions":[{"id":"https://openalex.org/I4210111784","display_name":"Cell Technology (China)","ror":"https://ror.org/01txhcw25","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210111784"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chengqi Dong","raw_affiliation_strings":["Meituan\nUniversity of Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meituan\nUniversity of Science and Technology of China","institution_ids":["https://openalex.org/I4210111784"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129727885","display_name":"Yinan Gao","orcid":null},"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":"Yinan Gao","raw_affiliation_strings":["Fudan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fudan University","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129678137","display_name":"Hang He","orcid":null},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hang He","raw_affiliation_strings":["Meituan\nEast China Normal University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meituan\nEast China Normal University","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129703550","display_name":"Jiajun Chai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiajun Chai","raw_affiliation_strings":["Meituan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meituan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129650218","display_name":"Wei Lin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei Lin","raw_affiliation_strings":["Meituan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meituan","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129663888","display_name":"Guojun Yin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guojun Yin","raw_affiliation_strings":["Meituan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meituan","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.21305458,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"41","first_page":"34530","last_page":"34538"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.713100016117096,"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":0.713100016117096,"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":0.056299999356269836,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.049400001764297485,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/verifiable-secret-sharing","display_name":"Verifiable secret sharing","score":0.8212000131607056},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.6168000102043152},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5827999711036682},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5611000061035156},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.4544999897480011},{"id":"https://openalex.org/keywords/reasoning-system","display_name":"Reasoning system","score":0.450300008058548},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.42879998683929443},{"id":"https://openalex.org/keywords/analytic-reasoning","display_name":"Analytic reasoning","score":0.42820000648498535},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.3928000032901764}],"concepts":[{"id":"https://openalex.org/C85847156","wikidata":"https://www.wikidata.org/wiki/Q59015987","display_name":"Verifiable secret sharing","level":3,"score":0.8212000131607056},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6941999793052673},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.6168000102043152},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5827999711036682},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5611000061035156},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5572999715805054},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.4544999897480011},{"id":"https://openalex.org/C89288958","wikidata":"https://www.wikidata.org/wiki/Q7301504","display_name":"Reasoning system","level":2,"score":0.450300008058548},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.42879998683929443},{"id":"https://openalex.org/C103057564","wikidata":"https://www.wikidata.org/wiki/Q4751139","display_name":"Analytic reasoning","level":3,"score":0.42820000648498535},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.3928000032901764},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.3815999925136566},{"id":"https://openalex.org/C83725634","wikidata":"https://www.wikidata.org/wiki/Q7268699","display_name":"Qualitative reasoning","level":2,"score":0.3779999911785126},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.37720000743865967},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37119999527931213},{"id":"https://openalex.org/C115086926","wikidata":"https://www.wikidata.org/wiki/Q17004651","display_name":"Causal reasoning","level":3,"score":0.3587000072002411},{"id":"https://openalex.org/C193221554","wikidata":"https://www.wikidata.org/wiki/Q5153664","display_name":"Commonsense reasoning","level":2,"score":0.35850000381469727},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.3546999990940094},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.3433000147342682},{"id":"https://openalex.org/C20162079","wikidata":"https://www.wikidata.org/wiki/Q1151406","display_name":"Case-based reasoning","level":2,"score":0.3431999981403351},{"id":"https://openalex.org/C86827895","wikidata":"https://www.wikidata.org/wiki/Q7098582","display_name":"Opportunistic reasoning","level":4,"score":0.3395000100135803},{"id":"https://openalex.org/C195344581","wikidata":"https://www.wikidata.org/wiki/Q2555318","display_name":"Automated reasoning","level":2,"score":0.32899999618530273},{"id":"https://openalex.org/C37335422","wikidata":"https://www.wikidata.org/wiki/Q6888134","display_name":"Model-based reasoning","level":3,"score":0.3093999922275543},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.28279998898506165},{"id":"https://openalex.org/C159032336","wikidata":"https://www.wikidata.org/wiki/Q2488768","display_name":"Non-monotonic logic","level":2,"score":0.2791000008583069},{"id":"https://openalex.org/C107848011","wikidata":"https://www.wikidata.org/wiki/Q4680756","display_name":"Adaptive reasoning","level":4,"score":0.2728999853134155},{"id":"https://openalex.org/C2776325391","wikidata":"https://www.wikidata.org/wiki/Q6917865","display_name":"Motivated reasoning","level":3,"score":0.2644999921321869},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.2563000023365021}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i41.40752","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i41.40752","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i41.40752","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i41.40752","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"reasoning":[1,11,37,50,107,120,129,155],"models":[2],"(LRMs)":[3],"have":[4],"recently":[5],"achieved":[6],"significant":[7],"progress":[8],"in":[9,105],"complex":[10],"tasks,":[12],"aided":[13],"by":[14,135],"reinforcement":[15],"learning":[16],"with":[17,138],"verifiable":[18,90],"rewards.":[19],"However,":[20],"LRMs":[21],"often":[22],"suffer":[23],"from":[24],"overthinking,":[25],"expending":[26],"excessive":[27],"computation":[28],"on":[29,99,126],"simple":[30],"problems":[31],"and":[32,56,67,113,133,140,163,170,174,186],"reducing":[33],"efficiency.":[34],"Existing":[35],"efficient":[36],"methods":[38],"typically":[39],"require":[40],"accurate":[41],"task":[42],"assessment":[43],"to":[44,79],"preset":[45],"token":[46],"budgets":[47],"or":[48],"select":[49],"modes,":[51],"which":[52,95],"limits":[53],"their":[54],"flexibility":[55],"reliability.":[57],"In":[58],"this":[59,83],"work,":[60],"we":[61,85],"revisit":[62],"the":[63,100,106,116,192],"essence":[64],"of":[65,102,119,167],"overthinking":[66,168,193],"identify":[68],"that":[69,144,178],"encouraging":[70],"effective":[71,188],"steps":[72,185],"while":[73,152],"penalizing":[74],"ineffective":[75,184],"ones":[76],"is":[77,111],"key":[78],"its":[80],"solution.":[81],"To":[82],"end,":[84],"propose":[86],"a":[87],"novel":[88],"rule-based":[89],"stepwise":[91],"reward":[92],"mechanism":[93],"(VSRM),":[94],"assigns":[96],"rewards":[97],"based":[98],"performance":[101],"intermediate":[103],"states":[104],"trajectory.":[108],"This":[109],"approach":[110,180],"intuitive":[112],"naturally":[114],"fits":[115],"step-by-step":[117],"nature":[118],"tasks.":[121],"We":[122],"conduct":[123],"extensive":[124],"experiments":[125],"standard":[127],"mathematical":[128],"benchmarks,":[130],"including":[131],"AIME24":[132],"AIME25,":[134],"integrating":[136],"VSRM":[137],"PPO":[139],"Reinforce++.":[141],"Results":[142],"show":[143],"our":[145,179],"method":[146],"achieves":[147],"substantial":[148],"output":[149],"length":[150],"reduction":[151],"maintaining":[153],"original":[154],"performance,":[156],"striking":[157],"an":[158],"optimal":[159],"balance":[160],"between":[161],"efficiency":[162],"accuracy.":[164],"Further":[165],"analysis":[166],"frequency":[169],"pass@k":[171],"score":[172],"before":[173],"after":[175],"training":[176],"demonstrates":[177],"indeed":[181],"effectively":[182],"suppresses":[183],"encourages":[187],"reasoning,":[189],"fundamentally":[190],"alleviating":[191],"problem.":[194]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-03-18T00:00:00"}