{"id":"https://openalex.org/W7155504515","doi":"https://doi.org/10.48550/arxiv.2604.21018","title":"Adaptive Test-Time Compute Allocation with Evolving In-Context Demonstrations","display_name":"Adaptive Test-Time Compute Allocation with Evolving In-Context Demonstrations","publication_year":2026,"publication_date":"2026-04-22","ids":{"openalex":"https://openalex.org/W7155504515","doi":"https://doi.org/10.48550/arxiv.2604.21018"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.21018","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.21018","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":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2604.21018","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5097984509","display_name":"Bowen Zuo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zuo, Bowen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103212607","display_name":"Dongruo Zhou","orcid":"https://orcid.org/0000-0001-8094-9918"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Dongruo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5044159962","display_name":"Yinglun Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhu, Yinglun","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":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":0.5903000235557556,"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":0.5903000235557556,"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":0.1145000010728836,"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"}},{"id":"https://openalex.org/T11273","display_name":"Advanced Graph Neural Networks","score":0.05079999938607216,"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/resampling","display_name":"Resampling","score":0.6959999799728394},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.6783999800682068},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6128000020980835},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.4745999872684479},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.446399986743927},{"id":"https://openalex.org/keywords/adaptive-sampling","display_name":"Adaptive sampling","score":0.33160001039505005}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7551000118255615},{"id":"https://openalex.org/C150921843","wikidata":"https://www.wikidata.org/wiki/Q1170431","display_name":"Resampling","level":2,"score":0.6959999799728394},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.6783999800682068},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6128000020980835},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.4745999872684479},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.446399986743927},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.41019999980926514},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.40450000762939453},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3594000041484833},{"id":"https://openalex.org/C2781395549","wikidata":"https://www.wikidata.org/wiki/Q4680762","display_name":"Adaptive sampling","level":3,"score":0.33160001039505005},{"id":"https://openalex.org/C44280652","wikidata":"https://www.wikidata.org/wiki/Q104837","display_name":"Phase (matter)","level":2,"score":0.3287000060081482},{"id":"https://openalex.org/C2781020372","wikidata":"https://www.wikidata.org/wiki/Q533093","display_name":"On the fly","level":2,"score":0.2964000105857849},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2782000005245209},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.27140000462532043},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.26190000772476196},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.26159998774528503},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.2605000138282776}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.21018","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.21018","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":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2604.21018","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.21018","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":"Preprint"},"sustainable_development_goals":[{"score":0.5317984819412231,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"While":[0],"scaling":[1],"test-time":[2,29],"compute":[3,15,30],"can":[4],"substantially":[5,123],"improve":[6],"model":[7],"performance,":[8],"existing":[9,119],"approaches":[10],"either":[11],"rely":[12],"on":[13,76,92],"static":[14],"allocation":[16,31],"or":[17],"sample":[18],"from":[19,64,95,102],"fixed":[20,104],"generation":[21,42,82,91],"distributions.":[22],"In":[23],"this":[24],"work,":[25],"we":[26],"introduce":[27],"a":[28,49,103],"framework":[32],"that":[33,52,114],"jointly":[34],"adapts":[35],"where":[36],"computation":[37,75],"is":[38,43],"spent":[39],"and":[40,56,110],"how":[41],"performed.":[44],"Our":[45],"method":[46],"begins":[47],"with":[48],"warm-up":[50],"phase":[51,71],"identifies":[53],"easy":[54],"queries":[55,78,98],"assembles":[57],"an":[58],"initial":[59],"pool":[60],"of":[61],"question-response":[62],"pairs":[63],"the":[65],"test":[66],"set":[67],"itself.":[68],"An":[69],"adaptive":[70],"then":[72],"concentrates":[73],"further":[74],"unresolved":[77],"while":[79,121],"reshaping":[80],"their":[81],"distributions":[83],"through":[84],"evolving":[85],"in-context":[86],"demonstrations":[87],"--":[88],"conditioning":[89],"each":[90],"successful":[93],"responses":[94],"semantically":[96],"related":[97],"rather":[99],"than":[100],"resampling":[101],"distribution.":[105],"Experiments":[106],"across":[107],"math,":[108],"coding,":[109],"reasoning":[111],"benchmarks":[112],"demonstrate":[113],"our":[115],"approach":[116],"consistently":[117],"outperforms":[118],"baselines":[120],"consuming":[122],"less":[124],"inference-time":[125],"compute.":[126]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-04-25T00:00:00"}