{"id":"https://openalex.org/W7160957161","doi":"https://doi.org/10.48550/arxiv.2605.08478","title":"When Independent Sampling Outperforms Agentic Reasoning","display_name":"When Independent Sampling Outperforms Agentic Reasoning","publication_year":2026,"publication_date":"2026-05-08","ids":{"openalex":"https://openalex.org/W7160957161","doi":"https://doi.org/10.48550/arxiv.2605.08478"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.08478","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.08478","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":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.2605.08478","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5041835178","display_name":"Yihe Dong","orcid":"https://orcid.org/0000-0002-2390-485X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dong, Yihe","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5135910458","display_name":"Boris Shigida","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shigida, Boris","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/T11596","display_name":"Constraint Satisfaction and Optimization","score":0.3847000002861023,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T11596","display_name":"Constraint Satisfaction and Optimization","score":0.3847000002861023,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10720","display_name":"Complexity and Algorithms in Graphs","score":0.06360000371932983,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.044199999421834946,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/inference","display_name":"Inference","score":0.6347000002861023},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.5688999891281128},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5665000081062317},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.4413999915122986},{"id":"https://openalex.org/keywords/thompson-sampling","display_name":"Thompson sampling","score":0.4277999997138977},{"id":"https://openalex.org/keywords/solver","display_name":"Solver","score":0.3492000102996826}],"concepts":[{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6347000002861023},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6238999962806702},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.5688999891281128},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5665000081062317},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49380001425743103},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.45339998602867126},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.4413999915122986},{"id":"https://openalex.org/C73602740","wikidata":"https://www.wikidata.org/wiki/Q7795822","display_name":"Thompson sampling","level":3,"score":0.4277999997138977},{"id":"https://openalex.org/C2778770139","wikidata":"https://www.wikidata.org/wiki/Q1966904","display_name":"Solver","level":2,"score":0.3492000102996826},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.31630000472068787},{"id":"https://openalex.org/C52740198","wikidata":"https://www.wikidata.org/wiki/Q1539564","display_name":"Importance sampling","level":3,"score":0.28610000014305115},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2809000015258789},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.27790001034736633},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.27379998564720154},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.271699994802475},{"id":"https://openalex.org/C3020493868","wikidata":"https://www.wikidata.org/wiki/Q55631277","display_name":"Real world data","level":2,"score":0.2662000060081482},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.2639999985694885},{"id":"https://openalex.org/C29202148","wikidata":"https://www.wikidata.org/wiki/Q287260","display_name":"Resource allocation","level":2,"score":0.2590999901294708}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.08478","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.08478","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":"doi:10.48550/arxiv.2605.08478","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.08478","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":false,"raw_source_name":null,"raw_type":"Preprint"},"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":{"We":[0,86],"study":[1],"how":[2],"to":[3],"allocate":[4],"inference-time":[5],"compute":[6],"for":[7,71],"competitive":[8],"programming":[9],"under":[10,82],"fixed":[11],"budgets.":[12],"Evaluating":[13],"216":[14],"Codeforces":[15],"problems":[16],"across":[17],"Divisions":[18],"1-3,":[19],"we":[20],"compare":[21],"agent-based":[22],"reasoning":[23,81],"with":[24],"repeated":[25],"independent":[26,75],"sampling":[27],"(k-shot)":[28],"as":[29],"a":[30,48,89,101],"function":[31],"of":[32,37],"both":[33],"cost":[34],"and":[35,42,51,98],"number":[36],"model":[38],"calls.":[39],"Across":[40],"models":[41],"difficulty":[43],"levels,":[44],"k-shot":[45],"consistently":[46],"achieves":[47],"better":[49],"accuracy-cost":[50],"accuracy-query":[52],"tradeoff.":[53],"This":[54],"gap":[55],"persists":[56],"despite":[57],"prompt":[58],"caching":[59],"in":[60],"agent":[61],"frameworks,":[62],"indicating":[63],"lower":[64],"per-call":[65],"effectiveness.":[66],"Our":[67],"results":[68],"show":[69],"that,":[70],"self-contained":[72],"algorithmic":[73],"tasks,":[74],"exploration":[76],"can":[77],"outperform":[78],"deeper":[79],"agentic":[80],"realistic":[83],"resource":[84],"constraints.":[85],"also":[87],"provide":[88],"budget-allocation":[90],"analysis":[91],"when":[92],"the":[93,105],"inference":[94],"budget":[95],"is":[96],"fixed,":[97],"prove":[99],"that":[100],"cost-optimal":[102],"solver":[103],"minimizes":[104],"principled":[106],"metric":[107],"log":[108],"failure":[109],"likelihood":[110],"per":[111],"dollar.":[112]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-05-13T00:00:00"}