{"id":"https://openalex.org/W7161263753","doi":"https://doi.org/10.48550/arxiv.2605.15177","title":"OpenDeepThink: Parallel Reasoning via Bradley-Terry Aggregation","display_name":"OpenDeepThink: Parallel Reasoning via Bradley-Terry Aggregation","publication_year":2026,"publication_date":"2026-05-14","ids":{"openalex":"https://openalex.org/W7161263753","doi":"https://doi.org/10.48550/arxiv.2605.15177"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.15177","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.15177","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.15177","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5121802796","display_name":"Shang Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Shang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136226811","display_name":"Wenhao Chai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chai, Wenhao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136203067","display_name":"Kaiyuan Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Kaiyuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136237313","display_name":"Huanzhi Mao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mao, Huanzhi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136214194","display_name":"Qiuyang Mang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mang, Qiuyang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5136190360","display_name":"Jingbo Shang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shang, Jingbo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.49630001187324524,"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":0.49630001187324524,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.15289999544620514,"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":0.06210000067949295,"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":0.7024000287055969},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.6740999817848206},{"id":"https://openalex.org/keywords/pointwise","display_name":"Pointwise","score":0.6434000134468079},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6119999885559082},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5641999840736389},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.5454999804496765},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5026999711990356}],"concepts":[{"id":"https://openalex.org/C85847156","wikidata":"https://www.wikidata.org/wiki/Q59015987","display_name":"Verifiable secret sharing","level":3,"score":0.7024000287055969},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.6740999817848206},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6478999853134155},{"id":"https://openalex.org/C2777984123","wikidata":"https://www.wikidata.org/wiki/Q9248237","display_name":"Pointwise","level":2,"score":0.6434000134468079},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6119999885559082},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5641999840736389},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.5454999804496765},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5026999711990356},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4262000024318695},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.39149999618530273},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.373199999332428},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33090001344680786},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3003999888896942},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.29980000853538513},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.28929999470710754},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2851000130176544},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.2703999876976013},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.26420000195503235},{"id":"https://openalex.org/C93959086","wikidata":"https://www.wikidata.org/wiki/Q6888345","display_name":"Model selection","level":2,"score":0.2614000141620636}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.15177","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.15177","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.15177","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.15177","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"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":{"Test-time":[0],"compute":[1,62],"scaling":[2],"is":[3,30,49,109],"a":[4,18,34,42,59,85,161],"primary":[5],"axis":[6],"for":[7],"improving":[8],"LLM":[9,47,73],"reasoning.":[10],"Existing":[11],"methods":[12],"primarily":[13],"scale":[14],"depth":[15],"by":[16,24,119],"extending":[17],"single":[19],"reasoning":[20],"trace.":[21],"Scaling":[22],"breadth":[23],"sampling":[25],"multiple":[26],"candidates":[27,78,89],"in":[28,122,149,155],"parallel":[29],"straightforward,":[31],"but":[32],"introduces":[33],"selection":[35],"bottleneck:":[36],"choosing":[37],"the":[38,72,93,100,106,142,178],"best":[39],"candidate":[40],"without":[41,138],"ground-truth":[43],"verifier,":[44],"since":[45],"pointwise":[46],"judging":[48],"noisy":[50],"and":[51,79,92,135,140,153,173],"biased.":[52],"To":[53],"address":[54],"this,":[55],"we":[56],"introduce":[57],"OpenDeepThink,":[58],"population-based":[60],"test-time":[61],"framework":[63],"that":[64],"selects":[65],"via":[66,82],"pairwise":[67],"Bradley-Terry":[68,83],"comparison.":[69],"Each":[70],"generation,":[71],"judges":[74],"random":[75],"pairs":[76],"of":[77,164],"aggregates":[80],"votes":[81],"into":[84],"global":[86],"ranking;":[87],"top-ranked":[88],"are":[90,97],"preserved":[91],"top":[94],"three":[95],"quarters":[96],"mutated":[98],"using":[99],"natural-language":[101],"critiques":[102],"produced":[103],"during":[104],"comparison;":[105],"bottom":[107],"quarter":[108],"discarded.":[110],"OpenDeepThink":[111],"raises":[112],"Gemini":[113],"3.1":[114],"Pro's":[115],"effective":[116],"Codeforces":[117,167],"Elo":[118],"+405":[120],"points":[121],"eight":[123],"sequential":[124],"LLM-call":[125],"rounds":[126],"(~27":[127],"minutes":[128],"wall-clock).":[129],"The":[130],"pipeline":[131],"transfers":[132],"across":[133],"weaker":[134],"stronger":[136],"models":[137],"retuning,":[139],"on":[141],"multi-domain":[143],"HLE":[144],"benchmark,":[145],"gains":[146],"appear":[147],"concentrated":[148],"objectively":[150],"verifiable":[151],"domains":[152],"reverse":[154],"subjective":[156],"ones.":[157],"We":[158],"release":[159],"CF-73,":[160],"curated":[162],"set":[163],"73":[165],"expert-rated":[166],"problems":[168],"with":[169],"International":[170],"Grandmaster":[171],"annotation":[172],"99%":[174],"local-evaluation":[175],"agreement":[176],"against":[177],"official":[179],"verdict.":[180]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-05-16T00:00:00"}