{"id":"https://openalex.org/W7138085156","doi":"https://doi.org/10.1609/aaai.v40i39.40650","title":"Beyond Accuracy: A Cognitive Load Framework for Mapping the Capability Boundaries of Tool-use Agents","display_name":"Beyond Accuracy: A Cognitive Load Framework for Mapping the Capability Boundaries of Tool-use Agents","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138085156","doi":"https://doi.org/10.1609/aaai.v40i39.40650"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v40i39.40650","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i39.40650","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v40i39.40650","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Qihao Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qihao Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Yue Hu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yue Hu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Mingzhe Lu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mingzhe Lu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Jiayue Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiayue Wu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Yanbing Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yanbing Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Yuanmin Tang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuanmin Tang","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":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"39","first_page":"33611","last_page":"33619"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.15060000121593475,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.15060000121593475,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.08749999850988388,"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":0.05770000070333481,"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/task","display_name":"Task (project management)","score":0.6675999760627747},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.6498000025749207},{"id":"https://openalex.org/keywords/cognition","display_name":"Cognition","score":0.5734999775886536},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5274999737739563},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5116000175476074},{"id":"https://openalex.org/keywords/cognitive-load","display_name":"Cognitive load","score":0.508400022983551},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.42149999737739563},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.35920000076293945}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.697700023651123},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6675999760627747},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.6498000025749207},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.5734999775886536},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5274999737739563},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5116000175476074},{"id":"https://openalex.org/C61641136","wikidata":"https://www.wikidata.org/wiki/Q1107019","display_name":"Cognitive load","level":3,"score":0.508400022983551},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48010000586509705},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.42149999737739563},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3646000027656555},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.35920000076293945},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.3312999904155731},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.3312000036239624},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.32010000944137573},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.319599986076355},{"id":"https://openalex.org/C170494330","wikidata":"https://www.wikidata.org/wiki/Q1778434","display_name":"Cognitive map","level":3,"score":0.30880001187324524},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.3050000071525574},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2669000029563904},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.26600000262260437},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.2572000026702881},{"id":"https://openalex.org/C161407221","wikidata":"https://www.wikidata.org/wiki/Q4382939","display_name":"Cognitive model","level":3,"score":0.25609999895095825},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.2556000053882599},{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.2526000142097473}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v40i39.40650","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i39.40650","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:ojs.aaai.org:article/40650","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/40650","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i39.40650","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i39.40650","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2563629645","display_name":null,"funder_award_id":"U21B2009","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0],"ability":[1],"of":[2,76],"Large":[3],"Language":[4],"Models":[5],"(LLMs)":[6],"to":[7,53,127],"use":[8],"ex":[9],"ternal":[10],"tools":[11],"unlocks":[12],"powerful":[13],"real-world":[14],"interactions,":[15],"mak":[16],"ing":[17],"rigorous":[18],"evaluation":[19,115],"essential.":[20],"However,":[21],"current":[22],"bench":[23],"marks":[24],"primarily":[25],"report":[26],"final":[27],"accuracy,":[28],"revealing":[29],"what":[30],"mod":[31],"els":[32],"can":[33],"do":[34],"but":[35],"obscuring":[36],"the":[37,72,77,91,105],"cognitive":[38,112,122],"bottlenecks":[39],"that":[40,136],"define":[41],"their":[42],"true":[43],"capability":[44,132],"boundaries.":[45],"To":[46,98],"move":[47],"from":[48,94],"simple":[49],"per":[50,118],"formance":[51,119],"scoring":[52],"a":[54,59,83,147,156],"diagnostic":[55],"tool,":[56],"we":[57,102],"introduce":[58],"frame":[60],"workgroundedinCognitive":[61],"LoadTheory.Ourframeworkde":[62],"constructs":[63],"task":[64,96],"complexity":[65,75],"into":[66],"two":[67],"quantifiable":[68],"components:":[69],"Intrinsic":[70],"Load,":[71,90],"inherent":[73],"structural":[74],"solu":[78],"tion":[79],"path,":[80],"formalized":[81],"with":[82,108,143],"novel":[84],"Tool":[85],"Interaction":[86],"Graph;":[87],"and":[88,155],"Extraneous":[89],"difficulty":[92],"arising":[93],"ambiguous":[95],"presentation.":[97],"enable":[99],"controlled":[100],"experiments,":[101],"construct":[103],"ToolLoad-Bench,":[104],"first":[106],"benchmark":[107],"parametrically":[109],"ad":[110],"justable":[111],"load.":[113],"Our":[114],"reveals":[116],"distinct":[117],"cliffs":[120],"as":[121],"load":[123],"increases,":[124],"allowing":[125],"us":[126],"precisely":[128],"map":[129],"each":[130],"model\u2019s":[131],"boundary.":[133],"We":[134],"validate":[135],"our":[137],"framework\u2019s":[138],"predictions":[139],"are":[140],"highly":[141],"calibrated":[142],"empirical":[144],"results,":[145],"establishing":[146],"principled":[148],"methodology":[149],"for":[150,159],"understanding":[151],"an":[152],"agent\u2019s":[153],"limits":[154],"practical":[157],"foundation":[158],"building":[160],"more":[161],"efficient":[162],"systems.":[163]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-02-02T00:00:00"}