{"id":"https://openalex.org/W4414981003","doi":"https://doi.org/10.18653/v1/2026.findings-acl.289","title":"ARISE: An Adaptive Resolution-Aware Metric for Test-Time Scaling Evaluation in Large Reasoning Models","display_name":"ARISE: An Adaptive Resolution-Aware Metric for Test-Time Scaling Evaluation in Large Reasoning Models","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W4414981003","doi":"https://doi.org/10.18653/v1/2026.findings-acl.289"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.289","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.289","pdf_url":"https://aclanthology.org/2026.findings-acl.289.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.289.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5083955516","display_name":"Zhangyue Yin","orcid":"https://orcid.org/0009-0008-0620-8271"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhangyue Yin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102007400","display_name":"Qiushi Sun","orcid":"https://orcid.org/0000-0002-5207-818X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qiushi Sun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075168326","display_name":"Zhiyuan Zeng","orcid":"https://orcid.org/0000-0002-3979-3322"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhiyuan Zeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100762520","display_name":"Zhiyuan Yu","orcid":"https://orcid.org/0000-0003-1746-7144"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhiyuan Yu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030290474","display_name":"Qipeng Guo","orcid":"https://orcid.org/0000-0001-7113-651X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qipeng Guo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088834359","display_name":"Xuanjing Huang","orcid":"https://orcid.org/0000-0001-9197-9426"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xuanjing Huang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5044665993","display_name":"Xipeng Qiu","orcid":"https://orcid.org/0000-0001-7163-5247"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xipeng Qiu","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":0.01045324,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5828","last_page":"5848"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9312000274658203,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9312000274658203,"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/T10028","display_name":"Topic Modeling","score":0.9301999807357788,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9157999753952026,"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/scaling","display_name":"Scaling","score":0.802299976348877},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.7347999811172485},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5597000122070312},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.41110000014305115},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4097000062465668},{"id":"https://openalex.org/keywords/performance-metric","display_name":"Performance metric","score":0.3889999985694885},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.3578999936580658}],"concepts":[{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.802299976348877},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.7347999811172485},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6700000166893005},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5597000122070312},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4408000111579895},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.41110000014305115},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4097000062465668},{"id":"https://openalex.org/C2780898871","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Performance metric","level":2,"score":0.3889999985694885},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.3578999936580658},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.3560999929904938},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3538999855518341},{"id":"https://openalex.org/C83725634","wikidata":"https://www.wikidata.org/wiki/Q7268699","display_name":"Qualitative reasoning","level":2,"score":0.32820001244544983},{"id":"https://openalex.org/C70587473","wikidata":"https://www.wikidata.org/wiki/Q7834111","display_name":"Transformative learning","level":2,"score":0.32690000534057617},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.3122999966144562},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.29109999537467957},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.2759000062942505},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.272599995136261},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2700999975204468},{"id":"https://openalex.org/C195344581","wikidata":"https://www.wikidata.org/wiki/Q2555318","display_name":"Automated reasoning","level":2,"score":0.2574000060558319},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2572000026702881}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.289","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.289","pdf_url":"https://aclanthology.org/2026.findings-acl.289.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:2510.06014","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.06014","pdf_url":"https://arxiv.org/pdf/2510.06014","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.2510.06014","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2510.06014","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.289","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.289","pdf_url":"https://aclanthology.org/2026.findings-acl.289.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":[{"id":"https://openalex.org/G8884928098","display_name":null,"funder_award_id":"U24B20181","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"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4414981003.pdf","grobid_xml":"https://content.openalex.org/works/W4414981003.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Test-time":[0],"scaling":[1,45,69,90,150,156,168],"has":[2],"emerged":[3],"as":[4,24,165],"a":[5,32,60,101,143],"transformative":[6],"paradigm":[7],"for":[8],"enhancing":[9],"the":[10,25,43,67,107,117],"performance":[11,97],"of":[12,19,27,71,109,148],"large":[13,72],"reasoning":[14,28,73,125,174],"models,":[15],"enabling":[16],"dynamic":[17,102],"allocation":[18],"computational":[20],"resources":[21],"during":[22],"inference.However,":[23],"landscape":[26],"models":[29,126],"rapidly":[30],"expands,":[31],"critical":[33],"question":[34],"remains:":[35],"how":[36],"can":[37],"we":[38,52],"systematically":[39],"compare":[40],"and":[41,99,112,135,145],"evaluate":[42],"test-time":[44,68,149],"capabilities":[46],"across":[47,127,158],"different":[48],"models?In":[49],"this":[50],"paper,":[51],"introduce":[53],"ARISE":[54,78,141],"(Adaptive":[55],"Resolution-aware":[56],"Inference":[57],"Scaling":[58],"Evaluation),":[59],"novel":[61],"metric":[62],"specifically":[63],"designed":[64],"to":[65,96,171],"assess":[66],"effectiveness":[70],"models.Unlike":[74],"existing":[75],"evaluation":[76,161],"approaches,":[77],"incorporates":[79],"two":[80],"key":[81],"innovations:":[82],"(1)":[83],"sample-level":[84],"awareness":[85],"that":[86,105,140],"effectively":[87],"penalizes":[88],"negative":[89],"behaviors":[91],"where":[92],"increased":[93],"computation":[94],"leads":[95],"degradation,":[98],"(2)":[100],"sampling":[103],"mechanism":[104],"mitigates":[106],"impact":[108],"accuracy":[110],"fluctuations":[111],"token":[113],"count":[114],"instability":[115],"on":[116],"final":[118],"assessment.We":[119],"conduct":[120],"comprehensive":[121],"experiments":[122],"evaluating":[123],"state-of-the-art":[124],"diverse":[128],"domains":[129],"including":[130],"mathematical":[131],"reasoning,":[132],"code":[133],"generation,":[134],"agentic":[136],"tasks.Our":[137],"results":[138],"demonstrate":[139],"provides":[142],"reliable":[144],"fine-grained":[146],"measurement":[147],"capabilities,":[151],"revealing":[152],"significant":[153],"variations":[154],"in":[155],"efficiency":[157],"models.Notably,":[159],"our":[160],"identifies":[162],"Claude":[163],"Opus":[164],"exhibiting":[166],"superior":[167],"characteristics":[169],"compared":[170],"other":[172],"contemporary":[173],"models.":[175]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}