{"id":"https://openalex.org/W7135235177","doi":"https://doi.org/10.48550/arxiv.2603.11495","title":"Try, Check and Retry: A Divide-and-Conquer Framework for Boosting Long-context Tool-Calling Performance of LLMs","display_name":"Try, Check and Retry: A Divide-and-Conquer Framework for Boosting Long-context Tool-Calling Performance of LLMs","publication_year":2026,"publication_date":"2026-03-12","ids":{"openalex":"https://openalex.org/W7135235177","doi":"https://doi.org/10.48550/arxiv.2603.11495"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.11495","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.11495","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.2603.11495","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5128952707","display_name":"Kunfeng Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Kunfeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053183023","display_name":"Qihuang Zhong","orcid":"https://orcid.org/0009-0001-0118-5217"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhong, Qihuang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111140222","display_name":"Juhua Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Juhua","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129042907","display_name":"Bo Du","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Du, Bo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5129097876","display_name":"Dacheng Tao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tao, Dacheng","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":0.6711999773979187,"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":0.6711999773979187,"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":0.07190000265836716,"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/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.025200000032782555,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.9128000140190125},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.6553999781608582},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.4083000123500824},{"id":"https://openalex.org/keywords/core","display_name":"Core (optical fiber)","score":0.39169999957084656}],"concepts":[{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.9128000140190125},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.6553999781608582},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5913000106811523},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.4754999876022339},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.45680001378059387},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.450300008058548},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.4083000123500824},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.39169999957084656},{"id":"https://openalex.org/C70153297","wikidata":"https://www.wikidata.org/wiki/Q5591907","display_name":"Gradient boosting","level":3,"score":0.28760001063346863},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.23440000414848328}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.11495","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.11495","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.2603.11495","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.11495","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Tool-calling":[0],"empowers":[1],"Large":[2],"Language":[3],"Models":[4],"(LLMs)":[5],"to":[6,16,51,111,128],"interact":[7],"with":[8],"external":[9],"environments.":[10],"However,":[11],"current":[12],"methods":[13,99],"often":[14],"struggle":[15],"handle":[17],"massive":[18],"and":[19,56,82,120,141],"noisy":[20],"candidate":[21],"tools":[22],"in":[23],"long-context":[24],"tool-calling":[25,42],"tasks,":[26],"limiting":[27],"their":[28,101],"real-world":[29],"application.":[30],"To":[31],"this":[32],"end,":[33],"we":[34],"propose":[35],"Tool-DC,":[36],"a":[37,66,104],"Divide-and-Conquer":[38],"framework":[39],"for":[40],"boosting":[41],"performance":[43,134],"of":[44,48,60,63],"LLMs.":[45],"The":[46],"core":[47],"Tool-DC":[49,70,77,87,98,107,124],"is":[50,80,90],"reduce":[52],"the":[53,75,85,116],"reasoning":[54],"difficulty":[55],"make":[57],"full":[58],"use":[59],"self-reflection":[61],"ability":[62],"LLMs":[64],"via":[65],"\"Try-Check-Retry\"":[67],"paradigm.":[68],"Specifically,":[69],"involves":[71],"two":[72],"variants:":[73],"1)":[74],"training-free":[76],"(TF),":[78],"which":[79,89],"plug-and-play":[81],"flexible;":[83],"2)":[84],"training-based":[86],"(TB),":[88],"more":[91],"inference-efficient.":[92],"Extensive":[93],"experiments":[94],"show":[95],"that":[96],"both":[97],"outperform":[100],"counterparts":[102],"by":[103],"clear":[105],"margin.":[106],"(TF)":[108],"brings":[109],"up":[110],"+25.10%":[112],"average":[113],"gains":[114],"against":[115],"baseline":[117],"on":[118],"BFCL":[119],"ACEBench":[121],"benchmarks,":[122],"while":[123],"(TB)":[125],"enables":[126],"Qwen2.5-7B":[127],"achieve":[129],"comparable":[130],"or":[131],"even":[132],"better":[133],"than":[135],"proprietary":[136],"LLMs,":[137],"e.g.,":[138],"OpenAI":[139],"o3":[140],"Claude-Haiku-4.5.":[142]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-03-14T00:00:00"}