{"id":"https://openalex.org/W7128355382","doi":"https://doi.org/10.48550/arxiv.2602.06527","title":"HyPER: Bridging Exploration and Exploitation for Scalable LLM Reasoning with Hypothesis Path Expansion and Reduction","display_name":"HyPER: Bridging Exploration and Exploitation for Scalable LLM Reasoning with Hypothesis Path Expansion and Reduction","publication_year":2026,"publication_date":"2026-02-06","ids":{"openalex":"https://openalex.org/W7128355382","doi":"https://doi.org/10.48550/arxiv.2602.06527"},"language":null,"primary_location":{"id":"pmh:doi:10.48550/arxiv.2602.06527","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"type":"article","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":null,"any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101328656","display_name":"Shengxuan Qiu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qiu, Shengxuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079747680","display_name":"Hao\u2010Chen Huang","orcid":"https://orcid.org/0000-0001-6130-5981"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Haochen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081222727","display_name":"Shuzhang Zhong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhong, Shuzhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125393775","display_name":"Pengfei Zuo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zuo, Pengfei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5125384666","display_name":"Meng Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Meng","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":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.1490484,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"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":0.6586999893188477,"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":0.6586999893188477,"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":0.14219999313354492,"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":0.06159999966621399,"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/scalability","display_name":"Scalability","score":0.6503000259399414},{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.5699999928474426},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.5478000044822693},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.544700026512146},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.5268999934196472},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.4514000117778778},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.40290001034736633},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.33309999108314514}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6761999726295471},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6503000259399414},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.5699999928474426},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.5478000044822693},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.544700026512146},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.5268999934196472},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.46000000834465027},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.4514000117778778},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.40290001034736633},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.33309999108314514},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3303000032901764},{"id":"https://openalex.org/C195344581","wikidata":"https://www.wikidata.org/wiki/Q2555318","display_name":"Automated reasoning","level":2,"score":0.3231000006198883},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.32249999046325684},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3174999952316284},{"id":"https://openalex.org/C8505890","wikidata":"https://www.wikidata.org/wiki/Q605095","display_name":"Budget constraint","level":2,"score":0.30880001187324524},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.30869999527931213},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2745000123977661},{"id":"https://openalex.org/C203479927","wikidata":"https://www.wikidata.org/wiki/Q5165939","display_name":"Controller (irrigation)","level":2,"score":0.2711000144481659},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2696000039577484},{"id":"https://openalex.org/C94361409","wikidata":"https://www.wikidata.org/wiki/Q7882500","display_name":"Uncertainty reduction theory","level":2,"score":0.2669999897480011},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.26570001244544983},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.2648000121116638}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:doi:10.48550/arxiv.2602.06527","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"doi:10.48550/arxiv.2602.06527","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.06527","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:doi:10.48550/arxiv.2602.06527","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Scaling":[0],"test-time":[1,77],"compute":[2],"with":[3,36],"multi-path":[4,99],"chain-of-thought":[5],"improves":[6],"reasoning":[7,41,67,163],"accuracy,":[8],"but":[9],"its":[10],"effectiveness":[11],"depends":[12],"critically":[13],"on":[14,48,156],"the":[15,54,57,128],"exploration-exploitation":[16],"trade-off.":[17],"Existing":[18],"approaches":[19],"address":[20],"this":[21],"trade-off":[22],"in":[23,101],"rigid":[24],"ways:":[25],"tree-structured":[26],"search":[27],"hard-codes":[28],"exploration":[29,124],"through":[30],"brittle":[31],"expansion":[32],"rules":[33],"that":[34,56,63,104,121,136,166],"interfere":[35],"post-trained":[37],"reasoning,":[38],"while":[39,181],"parallel":[40],"over-explores":[42],"redundant":[43],"hypothesis":[44,129],"paths":[45,68],"and":[46,62,65,144,147],"relies":[47],"weak":[49],"answer":[50],"selection.":[51],"Motivated":[52],"by":[53,176,185],"observation":[55],"optimal":[58],"balance":[59],"is":[60],"phase-dependent":[61],"correct":[64],"incorrect":[66],"often":[69],"diverge":[70],"only":[71],"at":[72],"late":[73],"stages,":[74],"we":[75],"reformulate":[76],"scaling":[78],"as":[79,127],"a":[80,86,93,108,132,145,170],"dynamic":[81],"expand-reduce":[82],"control":[83,96],"problem":[84],"over":[85],"pool":[87,130],"of":[88,117],"hypotheses.":[89],"We":[90],"propose":[91],"HyPER,":[92],"training-free":[94],"online":[95,119],"policy":[97],"for":[98,151],"decoding":[100],"mixture-of-experts":[102,158],"models":[103,160],"reallocates":[105],"computation":[106],"under":[107],"fixed":[109],"budget":[110],"using":[111],"lightweight":[112],"path":[113],"statistics.":[114],"HyPER":[115,167],"consists":[116],"an":[118],"controller":[120],"transitions":[122],"from":[123],"to":[125,178,187],"exploitation":[126,140],"evolves,":[131],"token-level":[133],"refinement":[134],"mechanism":[135],"enables":[137],"efficient":[138],"generation-time":[139],"without":[141],"full-path":[142],"resampling,":[143],"length-":[146],"confidence-aware":[148],"aggregation":[149],"strategy":[150],"reliable":[152],"answer-time":[153],"exploitation.":[154],"Experiments":[155],"four":[157],"language":[159],"across":[161],"diverse":[162],"benchmarks":[164],"show":[165],"consistently":[168],"achieves":[169],"superior":[171],"accuracy-compute":[172],"trade-off,":[173],"improving":[174],"accuracy":[175],"8":[177],"10":[179],"percent":[180],"reducing":[182],"token":[183],"usage":[184],"25":[186],"40":[188],"percent.":[189]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-02-10T00:00:00"}