{"id":"https://openalex.org/W7204260397","doi":"https://doi.org/10.48550/arxiv.2608.24509","title":"PeakBench: Benchmarking Resource-Aware Tool Invocation in LLM Agents","display_name":"PeakBench: Benchmarking Resource-Aware Tool Invocation in LLM Agents","publication_year":2026,"publication_date":"2026-08-25","ids":{"openalex":"https://openalex.org/W7204260397","doi":"https://doi.org/10.48550/arxiv.2608.24509"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.24509","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.24509","pdf_url":"https://arxiv.org/pdf/2608.24509","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.24509","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5137692388","display_name":"Zhi-Kai Chen","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen, Zhi-Kai","raw_affiliation_strings":["National Key Laboratory for Novel Software Technology , Nanjing University , China","School of Artificial Intelligence , Nanjing University , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Key Laboratory for Novel Software Technology , Nanjing University , China","institution_ids":["https://openalex.org/I881766915"]},{"raw_affiliation_string":"School of Artificial Intelligence , Nanjing University , China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148335264","display_name":"Xu-Xiang Zhong","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhong, Xu-Xiang","raw_affiliation_strings":["National Key Laboratory for Novel Software Technology , Nanjing University , China","School of Artificial Intelligence , Nanjing University , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Key Laboratory for Novel Software Technology , Nanjing University , China","institution_ids":["https://openalex.org/I881766915"]},{"raw_affiliation_string":"School of Artificial Intelligence , Nanjing University , China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148210026","display_name":"Song-Yan Li","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li, Song-Yan","raw_affiliation_strings":["Nanjing University , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanjing University , China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073912249","display_name":"De\u2010Chuan Zhan","orcid":"https://orcid.org/0000-0002-3533-2078","observed_orcids":["https://orcid.org/0000-0002-3533-2078"]},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhan, De-Chuan","raw_affiliation_strings":["National Key Laboratory for Novel Software Technology , Nanjing University , China","School of Artificial Intelligence , Nanjing University , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Key Laboratory for Novel Software Technology , Nanjing University , China","institution_ids":["https://openalex.org/I881766915"]},{"raw_affiliation_string":"School of Artificial Intelligence , Nanjing University , China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065180062","display_name":"Han-Jia Ye","orcid":"https://orcid.org/0000-0003-1173-1880","observed_orcids":["https://orcid.org/0000-0003-1173-1880"]},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ye, Han-Jia","raw_affiliation_strings":["National Key Laboratory for Novel Software Technology , Nanjing University , China","School of Artificial Intelligence , Nanjing University , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Key Laboratory for Novel Software Technology , Nanjing University , China","institution_ids":["https://openalex.org/I881766915"]},{"raw_affiliation_string":"School of Artificial Intelligence , Nanjing University , China","institution_ids":["https://openalex.org/I881766915"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I881766915"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":2,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.3158999979496002,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.3158999979496002,"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":0.1842000037431717,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.07819999754428864,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/llm-based-agents","display_name":"LLM agents","score":0.9620000123977661},{"id":"https://openalex.org/keywords/tool-invocation","display_name":"tool invocation","score":0.8830000162124634},{"id":"https://openalex.org/keywords/parallel-execution","display_name":"parallel execution","score":0.8550000190734863},{"id":"https://openalex.org/keywords/resource-constrained-scheduling","display_name":"resource-constrained scheduling","score":0.8840000033378601},{"id":"https://openalex.org/keywords/resource-profiles","display_name":"resource profiles","score":0.5910000205039978},{"id":"https://openalex.org/keywords/agent-benchmarking","display_name":"agent benchmarking","score":0.6480000019073486}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8568999767303467},{"id":"https://openalex.org/C160145156","wikidata":"https://www.wikidata.org/wiki/Q778586","display_name":"Executable","level":2,"score":0.6255000233650208},{"id":"https://openalex.org/C31395832","wikidata":"https://www.wikidata.org/wiki/Q1318674","display_name":"Testbed","level":2,"score":0.5746999979019165},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5638999938964844},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.5034999847412109},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.49149999022483826},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.47029998898506165},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.44859999418258667},{"id":"https://openalex.org/C2779639559","wikidata":"https://www.wikidata.org/wiki/Q7661178","display_name":"Symbolic execution","level":3,"score":0.43459999561309814},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4018999934196472},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.37599998712539673},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.3720000088214874},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.35749998688697815},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.3091000020503998},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.28700000047683716},{"id":"https://openalex.org/C40842320","wikidata":"https://www.wikidata.org/wiki/Q19423","display_name":"Buffer overflow","level":2,"score":0.2854999899864197},{"id":"https://openalex.org/C29202148","wikidata":"https://www.wikidata.org/wiki/Q287260","display_name":"Resource allocation","level":2,"score":0.2842999994754791},{"id":"https://openalex.org/C2776834041","wikidata":"https://www.wikidata.org/wiki/Q25346349","display_name":"Execution model","level":2,"score":0.2808000147342682},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.2718999981880188},{"id":"https://openalex.org/C35525427","wikidata":"https://www.wikidata.org/wiki/Q745881","display_name":"Intrusion detection system","level":2,"score":0.2680000066757202},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.26440000534057617},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.2630000114440918},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.2558000087738037}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.24509","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.24509","pdf_url":"https://arxiv.org/pdf/2608.24509","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2608.24509","doi":"https://doi.org/10.48550/arxiv.2608.24509","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.24509","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,"listed_in":[],"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2608.24509","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.24509","pdf_url":"https://arxiv.org/pdf/2608.24509","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204260397.pdf","grobid_xml":"https://content.openalex.org/works/W7204260397.grobid-xml"},"referenced_works_count":17,"referenced_works":["https://openalex.org/W4304195432","https://openalex.org/W4366999541","https://openalex.org/W4378505261","https://openalex.org/W4393247776","https://openalex.org/W4414448307","https://openalex.org/W4415240829","https://openalex.org/W4415317974","https://openalex.org/W4415335901","https://openalex.org/W4416050733","https://openalex.org/W4416242557","https://openalex.org/W4417100884","https://openalex.org/W7119523234","https://openalex.org/W7127367462","https://openalex.org/W7127380112","https://openalex.org/W7130402983","https://openalex.org/W7137905904","https://openalex.org/W7165385035"],"related_works":["https://openalex.org/W7166836923","https://openalex.org/W7137899878","https://openalex.org/W7221044954","https://openalex.org/W7162690279","https://openalex.org/W7223060390","https://openalex.org/W7162682022","https://openalex.org/W7213580510","https://openalex.org/W7139942924","https://openalex.org/W7154397947","https://openalex.org/W7214714701"],"abstract_inverted_index":{"LLM":[0],"agents":[1],"increasingly":[2],"solve":[3],"tasks":[4],"by":[5],"invoking":[6],"multiple":[7],"tools,":[8],"where":[9],"parallel":[10,62],"execution":[11,55,63,155],"is":[12,56,64,100,185],"essential":[13],"for":[14,135,179],"low":[15],"latency":[16],"but":[17,58,66],"difficult":[18],"to":[19,68],"manage":[20],"safely.":[21],"Existing":[22],"agent":[23,182],"benchmarks":[24],"primarily":[25],"evaluate":[26],"tool":[27],"selection,":[28],"argument":[29],"generation,":[30],"and":[31,42,89,103,170],"end-to-end":[32],"success":[33],"under":[34,156],"mostly":[35],"serial":[36,54],"execution,":[37],"largely":[38],"overlooking":[39],"valid":[40],"parallelization":[41],"resource-constrained":[43,112],"scheduling.":[44],"This":[45],"missing":[46],"scheduling":[47],"dimension":[48],"creates":[49],"a":[50,79,121,176],"practical":[51],"failure":[52],"mode:":[53],"safe":[57,152],"slow,":[59],"while":[60],"resource-agnostic":[61],"fast":[65],"prone":[67],"avoidable":[69,168],"resource":[70,91,157,164,172],"overflows.":[71],"To":[72],"address":[73],"this":[74,118,139],"gap,":[75],"we":[76,141],"introduce":[77],"PeakBench,":[78],"benchmark":[80],"of":[81],"executable":[82],"multi-tool":[83],"workflows":[84,99],"with":[85,120,132],"execution-grounded":[86],"dependency":[87,109],"annotations":[88],"measured":[90],"profiles.":[92],"A":[93],"central":[94],"challenge":[95,119],"in":[96],"evaluating":[97],"such":[98],"attribution:":[101],"failures":[102],"inefficiencies":[104],"may":[105],"arise":[106],"from":[107,129],"incorrect":[108],"planning,":[110],"poor":[111],"scheduling,":[113,131],"or":[114,153],"both.":[115],"PeakBench":[116,175],"addresses":[117],"two-part":[122],"evaluation":[123],"framework":[124],"that":[125,143,162],"disentangles":[126],"logical":[127,145],"planning":[128,146],"physical":[130],"dedicated":[133],"metrics":[134],"each":[136],"dimension.":[137],"Using":[138],"framework,":[140],"show":[142,161],"strong":[144],"does":[147],"not":[148],"reliably":[149],"translate":[150],"into":[151],"efficient":[154],"constraints.":[158],"We":[159],"further":[160],"exposing":[163],"information":[165],"can":[166],"reduce":[167],"overflows":[169],"improve":[171],"utilization,":[173],"making":[174],"useful":[177],"testbed":[178],"diagnosing":[180],"resource-aware":[181],"behavior.":[183],"Code":[184],"available":[186],"at":[187],"https://github.com/Czzzk/Staggering-the-Peaks.":[188]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-08-27T00:00:00"}
