{"id":"https://openalex.org/W7163150380","doi":"https://doi.org/10.48550/arxiv.2606.00135","title":"On Effectiveness and Efficiency of Agentic Tool-calling and RL Training","display_name":"On Effectiveness and Efficiency of Agentic Tool-calling and RL Training","publication_year":2026,"publication_date":"2026-05-28","ids":{"openalex":"https://openalex.org/W7163150380","doi":"https://doi.org/10.48550/arxiv.2606.00135"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.00135","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.00135","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.2606.00135","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5137634096","display_name":"Tong Liu","orcid":"https://orcid.org/0000-0002-4563-167X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Tong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137653085","display_name":"Cheng Qian","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qian, Cheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137661213","display_name":"Matej Cief","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cief, Matej","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137660723","display_name":"Yuan He","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"He, Yuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137636403","display_name":"Daniele Dan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dan, Daniele","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137636853","display_name":"Nikolaos Aletras","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Aletras, Nikolaos","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5078735102","display_name":"Gabriella Kazai","orcid":"https://orcid.org/0009-0002-5158-6630"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kazai, Gabriella","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":0.33980000019073486,"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":0.33980000019073486,"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":0.05950000137090683,"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/T12128","display_name":"AI in Service Interactions","score":0.054099999368190765,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.6847000122070312},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.6230999827384949},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.5192999839782715},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.427700012922287},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.4269999861717224},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.30309998989105225}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7028999924659729},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6847000122070312},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.6230999827384949},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5436999797821045},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.5192999839782715},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5034000277519226},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.427700012922287},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.4269999861717224},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.30309998989105225},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.2865999937057495},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.27309998869895935},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2712000012397766},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.2689000070095062},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2630000114440918},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.257999986410141}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.00135","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.00135","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.2606.00135","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.00135","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Tool-calling":[0],"is":[1,33,40,79],"a":[2],"central":[3],"component":[4],"of":[5,118],"modern":[6],"large":[7],"language":[8],"model":[9],"(LLM)":[10],"agents,":[11],"equipping":[12],"them":[13],"with":[14],"skills":[15],"beyond":[16],"their":[17],"parametric":[18],"knowledge.":[19],"This":[20],"paper":[21],"studies":[22],"tool-calling":[23,47,113,151],"along":[24],"two":[25,116,146],"complementary":[26],"axes:":[27],"effectiveness,":[28,43],"i.e.,":[29,37],"how":[30,38,75],"this":[31],"capability":[32],"measured,":[34],"and":[35,50,74,114,130],"efficiency,":[36,105],"it":[39],"learned.":[41],"On":[42,104],"we":[44,106,144],"systematically":[45],"analyze":[46],"evaluation":[48],"pipelines":[49],"show":[51],"that":[52,148],"results":[53],"can":[54,84],"be":[55],"highly":[56],"sensitive":[57],"to":[58,86],"seemingly":[59],"minor,":[60],"often":[61],"undocumented":[62],"implementation":[63],"choices":[64,83],"including":[65],"the":[66],"random":[67],"seed,":[68],"system":[69],"prompt,":[70],"multi-turn":[71,94],"template":[72],"construction,":[73],"prior":[76],"interaction/reasoning":[77],"history":[78],"carried":[80],"forward.":[81],"These":[82],"lead":[85],"substantial":[87,154],"differences":[88],"in":[89,93],"reported":[90],"performance,":[91],"especially":[92],"settings":[95],"where":[96],"without":[97,157],"rigorous":[98],"standardization,":[99],"leaderboard":[100],"rankings":[101],"are":[102],"unreliable.":[103],"examine":[107],"standard":[108],"reinforcement":[109],"learning":[110,128],"(RL)":[111],"for":[112],"identify":[115],"sources":[117],"computational":[119,138],"waste:":[120],"(i)":[121],"during":[122,132],"rollouts,":[123],"many":[124],"prompts":[125],"produce":[126],"no":[127],"signal,":[129],"(ii)":[131],"policy":[133],"updates,":[134],"optimization":[135],"incurs":[136],"high":[137],"cost.":[139],"Guided":[140],"by":[141],"these":[142],"findings,":[143],"introduce":[145],"techniques":[147],"accelerate":[149],"RL-based":[150],"training,":[152],"achieving":[153],"wall-clock":[155],"speedup":[156],"degrading":[158],"performance.":[159]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-03T00:00:00"}