{"id":"https://openalex.org/W7225206138","doi":"https://doi.org/10.48550/arxiv.2611.02852","title":"Value-Conditioned Proposal Acquisition for Test-Time Reasoning","display_name":"Value-Conditioned Proposal Acquisition for Test-Time Reasoning","publication_year":2026,"publication_date":"2026-11-02","ids":{"openalex":"https://openalex.org/W7225206138","doi":"https://doi.org/10.48550/arxiv.2611.02852"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2611.02852","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2611.02852","pdf_url":"https://arxiv.org/pdf/2611.02852","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,"listed_in":[],"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"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2611.02852","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5160478211","display_name":"Zeyan Li","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li, Zeyan","raw_affiliation_strings":["Shanghai Jiao Tong University Shanghai , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University Shanghai , China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5160400079","display_name":"Jianfeng Xu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu, Jianfeng","raw_affiliation_strings":["Shanghai Jiao Tong University Shanghai , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University Shanghai , China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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":0.36500000953674316,"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":0.36500000953674316,"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":0.11100000143051147,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.06520000100135803,"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/calibration","display_name":"calibration","score":0.41100001335144043},{"id":"https://openalex.org/keywords/math-500","display_name":"MATH-500","score":0.7570000290870667},{"id":"https://openalex.org/keywords/gsm8k","display_name":"GSM8K","score":0.9729999899864197},{"id":"https://openalex.org/keywords/mbpp","display_name":"MBPP","score":0.9380000233650208},{"id":"https://openalex.org/keywords/token-cost","display_name":"token cost","score":0.4390000104904175},{"id":"https://openalex.org/keywords/qwen3","display_name":"Qwen3","score":0.6959999799728394}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6873000264167786},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.5992000102996826},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5372999906539917},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.5291000008583069},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4932999908924103},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.46709999442100525},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.4586000144481659},{"id":"https://openalex.org/C72169020","wikidata":"https://www.wikidata.org/wiki/Q194404","display_name":"Monotonic function","level":2,"score":0.44350001215934753},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.43320000171661377},{"id":"https://openalex.org/C141513077","wikidata":"https://www.wikidata.org/wiki/Q378542","display_name":"Independent and identically distributed random variables","level":3,"score":0.4043000042438507},{"id":"https://openalex.org/C163985040","wikidata":"https://www.wikidata.org/wiki/Q1172399","display_name":"Data acquisition","level":2,"score":0.3930000066757202},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3885999917984009},{"id":"https://openalex.org/C2777220311","wikidata":"https://www.wikidata.org/wiki/Q6423340","display_name":"Knowledge acquisition","level":2,"score":0.3564000129699707},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3440000116825104},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3131999969482422},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.30799999833106995},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3009999990463257},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2736999988555908},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.27250000834465027},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.2574000060558319},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.25200000405311584}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2611.02852","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2611.02852","pdf_url":"https://arxiv.org/pdf/2611.02852","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,"listed_in":[],"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.2611.02852","doi":"https://doi.org/10.48550/arxiv.2611.02852","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2611.02852","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,"listed_in":[],"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":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2611.02852","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2611.02852","pdf_url":"https://arxiv.org/pdf/2611.02852","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,"listed_in":[],"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"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7225206138.pdf","grobid_xml":"https://content.openalex.org/works/W7225206138.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7201847851","https://openalex.org/W7162567160","https://openalex.org/W7223045142","https://openalex.org/W4415882992","https://openalex.org/W7162495901","https://openalex.org/W7220114287","https://openalex.org/W7166877517","https://openalex.org/W7128067257","https://openalex.org/W7161241618","https://openalex.org/W7223172127"],"abstract_inverted_index":{"Sampling":[0],"and":[1,67,70,107,123,148],"selection":[2],"spend":[3],"test-time":[4,25],"compute":[5],"inside":[6],"a":[7,14,24,43,77,157],"candidate":[8],"pool,":[9],"but":[10],"they":[11],"cannot":[12],"recover":[13],"correct":[15],"answer":[16],"that":[17,27],"never":[18],"enters":[19],"it.":[20],"We":[21],"introduce":[22],"ValueFormation,":[23],"policy":[26],"decides":[28],"after":[29],"each":[30,102],"primary-model":[31],"draw":[32],"whether":[33],"to":[34,110,129],"stop,":[35],"continue":[36],"sampling,":[37],"or":[38],"acquire":[39],"one":[40,53,84],"proposal":[41],"from":[42,58,152],"heterogeneous":[44],"reasoning":[45],"specialist.":[46],"The":[47],"three":[48,104],"actions":[49],"are":[50,73],"compared":[51],"on":[52,143,155],"cost-regularized":[54],"value":[55],"scale":[56],"learned":[57],"vote-state":[59],"features;":[60],"the":[61,89,127,162,166,171],"calibration":[62,86],"is":[63,140,146],"frozen":[64,78],"across":[65],"tasks":[66],"primary":[68,138],"models,":[69],"acquired":[71],"proposals":[72],"accepted":[74],"only":[75],"through":[76],"posterior":[79],"comparison.":[80],"On":[81],"held-out":[82],"MATH-500,":[83],"Llama-fitted":[85],"improves":[87],"over":[88],"strongest":[90],"of":[91,103],"eight":[92],"identically":[93],"evaluated":[94],"baselines":[95],"by":[96,118],"more":[97],"than":[98,133],"fifteen":[99],"points":[100],"for":[101],"8B":[105],"primaries":[106],"transfers":[108],"unchanged":[109],"Qwen3-14B.":[111],"Removing":[112],"acquisition":[113,131,145],"lowers":[114],"Llama":[115],"MATH":[116],"accuracy":[117,164],"20.43":[119],"points,":[120],"while":[121],"same-trace":[122],"same-access":[124],"replays":[125],"attribute":[126],"gain":[128],"state-conditioned":[130],"rather":[132],"specialist":[134],"access":[135],"alone.":[136],"Where":[137],"coverage":[139],"high,":[141],"as":[142],"GSM8K,":[144],"rare":[147],"gains":[149],"mainly":[150],"come":[151],"cheaper":[153],"allocation;":[154],"MBPP,":[156],"fixed":[158],"code":[159],"route":[160],"attains":[161],"top":[163],"at":[165],"lowest":[167],"interaction":[168],"cost.":[169],"Varying":[170],"token":[172],"price":[173],"monotonically":[174],"reduces":[175],"calls":[176],"without":[177],"retraining.":[178]},"counts_by_year":[],"updated_date":"2026-11-06T12:05:46.655746","created_date":"2026-11-04T00:00:00"}