{"id":"https://openalex.org/W7161258930","doi":"https://doi.org/10.48550/arxiv.2605.15041","title":"Case-Based Calibration of Adaptive Reasoning and Execution for LLM Tool Use","display_name":"Case-Based Calibration of Adaptive Reasoning and Execution for LLM Tool Use","publication_year":2026,"publication_date":"2026-05-14","ids":{"openalex":"https://openalex.org/W7161258930","doi":"https://doi.org/10.48550/arxiv.2605.15041"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.15041","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.15041","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":null,"license_id":null,"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.2605.15041","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5082716474","display_name":"Renning Pang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pang, Renning","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136251389","display_name":"Tian Lan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lan, Tian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136231172","display_name":"Leyuan Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Leyuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104504009","display_name":"Piao Tong","orcid":"https://orcid.org/0009-0008-7266-6828"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tong, Piao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136189742","display_name":"Sheng Cao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cao, Sheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5136240619","display_name":"Xiaosong Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Xiaosong","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/T10260","display_name":"Software Engineering Research","score":0.2515000104904175,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10260","display_name":"Software Engineering Research","score":0.2515000104904175,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10639","display_name":"Advanced Software Engineering Methodologies","score":0.17389999330043793,"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/T10028","display_name":"Topic Modeling","score":0.050700001418590546,"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/reuse","display_name":"Reuse","score":0.6011999845504761},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5425000190734863},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.539900004863739},{"id":"https://openalex.org/keywords/calibration","display_name":"Calibration","score":0.49880000948905945},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.4334999918937683},{"id":"https://openalex.org/keywords/structured-prediction","display_name":"Structured prediction","score":0.40049999952316284},{"id":"https://openalex.org/keywords/case-based-reasoning","display_name":"Case-based reasoning","score":0.3833000063896179}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7757999897003174},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.6011999845504761},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5425000190734863},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.539900004863739},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.49880000948905945},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4778999984264374},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4361000061035156},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.4334999918937683},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.40049999952316284},{"id":"https://openalex.org/C20162079","wikidata":"https://www.wikidata.org/wiki/Q1151406","display_name":"Case-based reasoning","level":2,"score":0.3833000063896179},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.36550000309944153},{"id":"https://openalex.org/C2989134064","wikidata":"https://www.wikidata.org/wiki/Q288510","display_name":"Execution time","level":2,"score":0.36390000581741333},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.34220001101493835},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.30979999899864197},{"id":"https://openalex.org/C168065819","wikidata":"https://www.wikidata.org/wiki/Q845566","display_name":"Debugging","level":2,"score":0.30169999599456787},{"id":"https://openalex.org/C37335422","wikidata":"https://www.wikidata.org/wiki/Q6888134","display_name":"Model-based reasoning","level":3,"score":0.28369998931884766},{"id":"https://openalex.org/C89288958","wikidata":"https://www.wikidata.org/wiki/Q7301504","display_name":"Reasoning system","level":2,"score":0.2750999927520752},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.26809999346733093},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.2628999948501587},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.25540000200271606}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.15041","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.15041","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.15041","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.15041","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"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":{"Tool":[0],"use":[1],"extends":[2],"large":[3],"language":[4],"models":[5],"beyond":[6],"parametric":[7],"knowledge,":[8],"but":[9],"reliable":[10],"execution":[11,38,105,125,144],"requires":[12],"balancing":[13],"appropriate":[14],"reasoning":[15,60,130],"depth":[16],"with":[17],"strict":[18],"structural":[19,68,137],"validity.":[20],"We":[21],"approach":[22,115],"this":[23,73,140],"problem":[24],"from":[25],"a":[26,32,76],"case-based":[27,89],"perspective":[28],"to":[29,53,65,86,118],"present":[30],"CAST,":[31],"case-driven":[33],"framework":[34,71],"that":[35,100],"treats":[36],"historical":[37,143],"trajectories":[39],"as":[40],"structured":[41],"cases.":[42],"Instead":[43],"of":[44],"reusing":[45],"raw":[46],"exemplar":[47],"outputs,":[48],"CAST":[49,101],"extracts":[50],"case-derived":[51],"signals":[52],"identify":[54],"complexity":[55],"profiles":[56,64],"for":[57,151],"estimating":[58],"optimal":[59],"strategies,":[61],"alongside":[62],"failure":[63],"map":[66],"likely":[67],"breakdowns.":[69],"The":[70,114],"translates":[72],"knowledge":[74,150],"into":[75],"fine-grained":[77],"reward":[78],"design":[79],"and":[80,97,106,127],"adaptive":[81],"reasoning,":[82],"enabling":[83],"the":[84],"model":[85],"autonomously":[87],"internalize":[88],"strategies":[90],"during":[91],"reinforcement":[92],"learning.":[93],"Experiments":[94],"on":[95],"BFCLv2":[96],"ToolBench":[98],"demonstrate":[99],"improves":[102],"both":[103],"schema-faithful":[104],"task-level":[107],"tool-use":[108],"success":[109],"while":[110],"reducing":[111],"unnecessary":[112],"deliberation.":[113],"achieves":[116],"up":[117],"5.85":[119],"percentage":[120],"points":[121],"gain":[122],"in":[123],"overall":[124],"accuracy":[126],"reduces":[128],"average":[129],"length":[131],"by":[132],"26%,":[133],"significantly":[134],"mitigating":[135],"high-impact":[136],"errors.":[138],"Ultimately,":[139],"demonstrates":[141],"how":[142],"cases":[145],"can":[146],"provide":[147],"reusable":[148],"adaptation":[149],"calibrated":[152],"tool":[153],"use.":[154]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-16T00:00:00"}