{"id":"https://openalex.org/W4417300512","doi":"https://doi.org/10.18653/v1/2026.findings-acl.626","title":"Shorten After You\u2019re Right: Lazy Length Penalties for Reasoning RL","display_name":"Shorten After You\u2019re Right: Lazy Length Penalties for Reasoning RL","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W4417300512","doi":"https://doi.org/10.18653/v1/2026.findings-acl.626"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.626","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.626","pdf_url":"https://aclanthology.org/2026.findings-acl.626.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.626.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5113407753","display_name":"Danlong Yuan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Danlong Yuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101903884","display_name":"Tian Xie","orcid":"https://orcid.org/0000-0003-0871-0229"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tian Xie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061624006","display_name":"Shaohan Huang","orcid":"https://orcid.org/0000-0003-4324-6337"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shaohan Huang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066928490","display_name":"Huishuai Zhang","orcid":"https://orcid.org/0000-0003-2711-7295"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huishuai Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113034676","display_name":"Zhuocheng Gong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhuocheng Gong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101437627","display_name":"Chong Luo","orcid":"https://orcid.org/0000-0003-0939-474X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chong Luo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014662947","display_name":"Furu Wei","orcid":"https://orcid.org/0000-0002-7810-5852"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Furu Wei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5037132097","display_name":"Dongyan Zhao","orcid":"https://orcid.org/0000-0002-0396-6703"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dongyan Zhao","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":0.03683449,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"12864","last_page":"12877"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.19509999454021454,"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":0.19509999454021454,"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":0.18729999661445618,"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":0.16580000519752502,"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/process","display_name":"Process (computing)","score":0.6151999831199646},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.5504000186920166},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5184000134468079},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.47749999165534973},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.3732999861240387},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.366100013256073},{"id":"https://openalex.org/keywords/reasoning-system","display_name":"Reasoning system","score":0.35569998621940613}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.670799970626831},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.6151999831199646},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5867999792098999},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.5504000186920166},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5184000134468079},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.47749999165534973},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43650001287460327},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3732999861240387},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.366100013256073},{"id":"https://openalex.org/C89288958","wikidata":"https://www.wikidata.org/wiki/Q7301504","display_name":"Reasoning system","level":2,"score":0.35569998621940613},{"id":"https://openalex.org/C83725634","wikidata":"https://www.wikidata.org/wiki/Q7268699","display_name":"Qualitative reasoning","level":2,"score":0.35530000925064087},{"id":"https://openalex.org/C19012869","wikidata":"https://www.wikidata.org/wiki/Q578372","display_name":"Response time","level":2,"score":0.3476000130176544},{"id":"https://openalex.org/C159032336","wikidata":"https://www.wikidata.org/wiki/Q2488768","display_name":"Non-monotonic logic","level":2,"score":0.33340001106262207},{"id":"https://openalex.org/C195344581","wikidata":"https://www.wikidata.org/wiki/Q2555318","display_name":"Automated reasoning","level":2,"score":0.3240000009536743},{"id":"https://openalex.org/C20162079","wikidata":"https://www.wikidata.org/wiki/Q1151406","display_name":"Case-based reasoning","level":2,"score":0.3190999925136566},{"id":"https://openalex.org/C86827895","wikidata":"https://www.wikidata.org/wiki/Q7098582","display_name":"Opportunistic reasoning","level":4,"score":0.2985000014305115},{"id":"https://openalex.org/C37335422","wikidata":"https://www.wikidata.org/wiki/Q6888134","display_name":"Model-based reasoning","level":3,"score":0.2727999985218048}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.626","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.626","pdf_url":"https://aclanthology.org/2026.findings-acl.626.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:2505.12284","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.12284","pdf_url":"https://arxiv.org/pdf/2505.12284","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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.2505.12284","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2505.12284","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.626","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.626","pdf_url":"https://aclanthology.org/2026.findings-acl.626.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":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4417300512.pdf","grobid_xml":"https://content.openalex.org/works/W4417300512.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Long-reasoning":[0],"models":[1],"achieve":[2,144],"strong":[3],"accuracy":[4,103],"on":[5,24,97],"complex":[6],"reasoning":[7,12,141],"tasks,":[8],"but":[9],"their":[10],"extended":[11],"trajectories":[13],"incur":[14],"substantial":[15],"memory":[16],"and":[17,35,58,75,109],"latency":[18],"costs.Several":[19],"existing":[20],"shortening":[21],"methods":[22],"rely":[23],"additional":[25],"supervision":[26],"or":[27,136],"multi-stage":[28],"post-training,":[29],"which":[30],"primarily":[31],"reduces":[32,127],"inference":[33,56],"length":[34,71,79,86,129,151,164],"does":[36],"not":[37],"reduce":[38,161],"the":[39,90,118],"rollout":[40],"tokens":[41],"during":[42],"on-policy":[43,63],"reinforcement":[44],"learning":[45],"(RL).We":[46],"instead":[47],"target":[48],"onpolicy":[49],"response":[50,128,150,163],"shortening,":[51],"aiming":[52],"to":[53],"improve":[54],"both":[55],"efficiency":[57],"RL":[59,64,92],"training":[60,74,102,132],"throughput.However,":[61],"because":[62],"couples":[65],"optimization":[66],"with":[67],"exploration,":[68],"naively":[69],"penalizing":[70],"can":[72],"destabilize":[73],"suppress":[76],"exploration.To":[77],"impose":[78],"pressure":[80],"safely,":[81],"we":[82,143,160],"propose":[83],"a":[84,105,114,139,145,153],"lazy":[85],"penalty":[87],"integrated":[88],"into":[89],"rule-based":[91],"pipeline:":[93],"it":[94],"activates":[95],"only":[96,100,110],"correct":[98,120],"trajectories,":[99],"after":[101],"enters":[104],"stably":[106],"improving":[107,137],"regime,":[108],"when":[111],"responses":[112],"exceed":[113],"tolerance":[115],"band":[116],"beyond":[117],"minimal":[119],"length.Across":[121],"four":[122],"settings,":[123],"our":[124],"method":[125],"significantly":[126],"without":[130],"extra":[131],"stages":[133],"while":[134,167],"maintaining":[135],"performance.In":[138],"logic":[140],"setting,":[142],"40%":[146],"reduction":[147],"in":[148,156],"stepaveraged":[149],"alongside":[152],"14-point":[154],"gain":[155],"performance.For":[157],"math":[158],"problems,":[159],"step-averaged":[162],"by":[165],"33%":[166],"preserving":[168],"performance.":[169]},"counts_by_year":[],"updated_date":"2026-08-08T07:41:36.138363","created_date":"2025-10-10T00:00:00"}