{"id":"https://openalex.org/W7125930392","doi":"https://doi.org/10.1109/tse.2026.3658554","title":"Defining and Detecting the Defects of Large Language Model-Based Autonomous Agents","display_name":"Defining and Detecting the Defects of Large Language Model-Based Autonomous Agents","publication_year":2026,"publication_date":"2026-01-28","ids":{"openalex":"https://openalex.org/W7125930392","doi":"https://doi.org/10.1109/tse.2026.3658554"},"language":null,"primary_location":{"id":"doi:10.1109/tse.2026.3658554","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tse.2026.3658554","pdf_url":null,"source":{"id":"https://openalex.org/S8351582","display_name":"IEEE Transactions on Software Engineering","issn_l":"0098-5589","issn":["0098-5589","1939-3520","2326-3881"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Software Engineering","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5124077108","display_name":"Kaiwen Ning","orcid":null},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kaiwen Ning","raw_affiliation_strings":["School of Software Engineering, Sun Yat-sen University, Zhuhai, China"],"raw_orcid":"https://orcid.org/0009-0009-6009-8285","affiliations":[{"raw_affiliation_string":"School of Software Engineering, Sun Yat-sen University, Zhuhai, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jiachi Chen","orcid":"https://orcid.org/0000-0002-0192-9992"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiachi Chen","raw_affiliation_strings":["State Key Laboratory of Blockchain and Data Security, Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-0192-9992","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Blockchain and Data Security, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jingwen Zhang","orcid":"https://orcid.org/0009-0002-8611-3120"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jingwen Zhang","raw_affiliation_strings":["School of Software Engineering, Sun Yat-sen University, Zhuhai, China"],"raw_orcid":"https://orcid.org/0009-0002-8611-3120","affiliations":[{"raw_affiliation_string":"School of Software Engineering, Sun Yat-sen University, Zhuhai, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124143722","display_name":"Wei Li","orcid":null},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Li","raw_affiliation_strings":["School of Software Engineering, Sun Yat-sen University, Zhuhai, China"],"raw_orcid":"https://orcid.org/0009-0002-1333-4408","affiliations":[{"raw_affiliation_string":"School of Software Engineering, Sun Yat-sen University, Zhuhai, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zexu Wang","orcid":"https://orcid.org/0009-0004-1439-2989"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zexu Wang","raw_affiliation_strings":["School of Software Engineering, Sun Yat-sen University, Zhuhai, China"],"raw_orcid":"https://orcid.org/0009-0004-1439-2989","affiliations":[{"raw_affiliation_string":"School of Software Engineering, Sun Yat-sen University, Zhuhai, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102009762","display_name":"Yuming Feng","orcid":"https://orcid.org/0000-0001-8922-0496"},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuming Feng","raw_affiliation_strings":["Department of New Networks, Peng Cheng Laboratory, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0001-8922-0496","affiliations":[{"raw_affiliation_string":"Department of New Networks, Peng Cheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123005972","display_name":"Weizhe Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weizhe Zhang","raw_affiliation_strings":["School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0003-4783-876X","affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5124118792","display_name":"Zibin Zheng","orcid":null},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zibin Zheng","raw_affiliation_strings":["School of Software Engineering, Sun Yat-sen University, Zhuhai, China"],"raw_orcid":"https://orcid.org/0000-0001-7872-7718","affiliations":[{"raw_affiliation_string":"School of Software Engineering, Sun Yat-sen University, Zhuhai, China","institution_ids":["https://openalex.org/I157773358"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.06856535,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"52","issue":"3","first_page":"1074","last_page":"1093"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.18289999663829803,"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":0.18289999663829803,"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/T10028","display_name":"Topic Modeling","score":0.08299999684095383,"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/T11986","display_name":"Scientific Computing and Data Management","score":0.060600001364946365,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/workflow","display_name":"Workflow","score":0.711899995803833},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5016000270843506},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4805000126361847},{"id":"https://openalex.org/keywords/property","display_name":"Property (philosophy)","score":0.4052000045776367},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.39899998903274536},{"id":"https://openalex.org/keywords/transformative-learning","display_name":"Transformative learning","score":0.3946000039577484},{"id":"https://openalex.org/keywords/multi-agent-system","display_name":"Multi-agent system","score":0.3790999948978424}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8733999729156494},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.711899995803833},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5016000270843506},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4805000126361847},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.46549999713897705},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.451200008392334},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.4052000045776367},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.39899998903274536},{"id":"https://openalex.org/C70587473","wikidata":"https://www.wikidata.org/wiki/Q7834111","display_name":"Transformative learning","level":2,"score":0.3946000039577484},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.3790999948978424},{"id":"https://openalex.org/C74072328","wikidata":"https://www.wikidata.org/wiki/Q1142726","display_name":"Intelligent agent","level":2,"score":0.35989999771118164},{"id":"https://openalex.org/C2780378061","wikidata":"https://www.wikidata.org/wiki/Q25351891","display_name":"Service (business)","level":2,"score":0.3467000126838684},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3384999930858612},{"id":"https://openalex.org/C5894958","wikidata":"https://www.wikidata.org/wiki/Q2297769","display_name":"Software agent","level":2,"score":0.33660000562667847},{"id":"https://openalex.org/C13687954","wikidata":"https://www.wikidata.org/wiki/Q4826847","display_name":"Autonomous agent","level":2,"score":0.3140999972820282},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3070000112056732},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.27649998664855957},{"id":"https://openalex.org/C2778956278","wikidata":"https://www.wikidata.org/wiki/Q392813","display_name":"Agent-oriented software engineering","level":4,"score":0.2702000141143799},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.2669999897480011},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.26269999146461487},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.26109999418258667},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.25270000100135803}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tse.2026.3658554","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tse.2026.3658554","pdf_url":null,"source":{"id":"https://openalex.org/S8351582","display_name":"IEEE Transactions on Software Engineering","issn_l":"0098-5589","issn":["0098-5589","1939-3520","2326-3881"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Software Engineering","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6051054000854492,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[{"id":"https://openalex.org/G4425133490","display_name":null,"funder_award_id":"62302534","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1992114977","https://openalex.org/W2784876765","https://openalex.org/W2903328789","https://openalex.org/W3007045600","https://openalex.org/W3096688843","https://openalex.org/W3185244049","https://openalex.org/W4226496236","https://openalex.org/W4376606589","https://openalex.org/W4384154512","https://openalex.org/W4385080397","https://openalex.org/W4385287322","https://openalex.org/W4388483049","https://openalex.org/W4388483716","https://openalex.org/W4388858951","https://openalex.org/W4390812405","https://openalex.org/W4392449489","https://openalex.org/W4392873030","https://openalex.org/W4393105641","https://openalex.org/W4394595621","https://openalex.org/W4396832466","https://openalex.org/W4398160938","https://openalex.org/W4400484660","https://openalex.org/W4401113745","https://openalex.org/W4401863345","https://openalex.org/W4402442227","https://openalex.org/W4402671722","https://openalex.org/W4403209970","https://openalex.org/W4404952885","https://openalex.org/W4405181589","https://openalex.org/W4406858164","https://openalex.org/W4410226837","https://openalex.org/W4410637025","https://openalex.org/W4410985905","https://openalex.org/W4411113092","https://openalex.org/W4411552283","https://openalex.org/W4411552367","https://openalex.org/W4412505619","https://openalex.org/W4415800619","https://openalex.org/W7133199409"],"related_works":[],"abstract_inverted_index":{"Artificial":[0],"intelligence":[1],"(AI)":[2],"agents":[3],"are":[4],"systems":[5],"capable":[6],"of":[7,50,125,132,190,240,259,269,279,300],"perceiving":[8],"their":[9,146],"environment,":[10],"autonomously":[11],"planning":[12],"and":[13,38,73,84,91,119,160,168,176,186,213,225,246,276],"executing":[14],"tasks.":[15],"Recent":[16],"advancements":[17],"in":[18,112,145,163,293,303],"Large":[19],"Language":[20],"Models":[21],"(LLMs)":[22],"have":[23],"introduced":[24],"a":[25,130,197,267,277],"transformative":[26],"paradigm":[27],"for":[28],"AI":[29,54,114,140],"agents,":[30,63],"enabling":[31],"them":[32],"to":[33,96,109,142,184,203,215,255],"interact":[34],"with":[35,76],"external":[36],"resources":[37],"tools":[39],"through":[40],"prompt":[41],"techniques.":[42],"This":[43],"advancement":[44],"has":[45],"significantly":[46],"extended":[47],"the":[48,64,123,154,272,282,298],"capabilities":[49],"LLMs,":[51],"positioning":[52],"LLM-based":[53,113,139],"Agents":[55,141],"as":[56,99],"an":[57],"important":[58],"research":[59],"area.":[60],"In":[61],"such":[62,98],"workflow":[65],"integrates":[66],"developer-written":[67],"code,":[68],"which":[69,238,248],"manages":[70],"framework":[71],"construction":[72],"logic":[74,93],"control,":[75],"LLM-generated":[77],"natural":[78,227],"language":[79,228],"that":[80,135,264],"enhances":[81],"dynamic":[82],"decision-making":[83],"interaction.":[85],"However,":[86],"inconsistencies":[87],"between":[88],"LLM":[89,164],"outputs":[90],"developer":[92,172],"can":[94],"lead":[95],"defects,":[97],"tool":[100],"invocation":[101],"failures.":[102],"These":[103],"issues":[104,302],"introduce":[105],"specific":[106,222],"risks,":[107],"leading":[108],"various":[110,257],"defects":[111,144,162,292],"Agents,":[115],"including":[116],"service":[117],"interruptions":[118],"incorrect":[120],"output.":[121],"Despite":[122],"importance":[124],"these":[126,205,301],"issues,":[127],"there":[128],"is":[129],"lack":[131],"systematic":[133],"work":[134],"focuses":[136],"on":[137,158,271,281],"analyzing":[138,226],"uncover":[143],"code.":[147],"To":[148,230],"address":[149],"this":[150],"gap,":[151],"we":[152,195,233],"present":[153],"first":[155],"study":[156],"focused":[157],"identifying":[159,221],"detecting":[161],"Agents.":[165],"We":[166,178],"collected":[167],"analyzed":[169],"14,754":[170],"relevant":[171],"reports":[173],"from":[174],"StackOverflow":[175],"GitHub.":[177],"further":[179],"filtered":[180],"2,604":[181],"valid":[182],"posts":[183],"define":[185],"classify":[187],"eight":[188],"types":[189,258],"agent":[191,274,295],"code":[192,223],"defects.":[193,206,260],"Then,":[194],"designed":[196,254],"static":[198],"analysis":[199,289],"tool,":[200],"named":[201],"Agentable,":[202,232],"detect":[204],"Agentable":[207,265],"leverages":[208],"Code":[209],"Property":[210],"Graphs":[211],"(CPGs)":[212],"LLMs":[214],"analyze":[216],"Agent":[217,244,251],"workflows":[218],"by":[219],"efficiently":[220],"patterns":[224],"descriptions.":[229],"evaluate":[231],"constructed":[234],"two":[235],"datasets:":[236],"AgentSet,":[237],"consists":[239],"84":[241],"real":[242],"world":[243],"projects,":[245,296],"AgentTest,":[247],"contains":[249],"78":[250],"projects":[252],"specifically":[253],"include":[256],"Our":[261],"evaluation":[262],"shows":[263],"achieves":[266],"precision":[268],"88.79%":[270],"real-world":[273,294],"dataset":[275],"recall":[278],"91.03%":[280],"manually":[283],"labeled":[284],"defect":[285],"dataset.":[286],"Furthermore,":[287],"our":[288],"identifies":[290],"889":[291],"highlighting":[297],"prevalence":[299],"practice.":[304]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2026-01-29T00:00:00"}