{"id":"https://openalex.org/W7147399540","doi":"https://doi.org/10.48550/arxiv.2603.29848","title":"AgentFixer: From Failure Detection to Fix Recommendations in LLM Agentic Systems","display_name":"AgentFixer: From Failure Detection to Fix Recommendations in LLM Agentic Systems","publication_year":2026,"publication_date":"2026-02-18","ids":{"openalex":"https://openalex.org/W7147399540","doi":"https://doi.org/10.48550/arxiv.2603.29848"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.29848","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.29848","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.2603.29848","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5093081414","display_name":"Hadar Mulian","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mulian, Hadar","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001266138","display_name":"Sergey Zeltyn","orcid":"https://orcid.org/0000-0003-2540-1604"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zeltyn, Sergey","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132644891","display_name":"Ido Levy","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Levy, Ido","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132684966","display_name":"Liane Galanti","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Galanti, Liane","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061821122","display_name":"Avi Yaeli","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yaeli, Avi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5132664340","display_name":"Segev Shlomov","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shlomov, Segev","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/T10142","display_name":"Formal Methods in Verification","score":0.2159000039100647,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T10142","display_name":"Formal Methods in Verification","score":0.2159000039100647,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T10639","display_name":"Advanced Software Engineering Methodologies","score":0.12559999525547028,"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/T12127","display_name":"Software System Performance and Reliability","score":0.11150000244379044,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/ibm","display_name":"IBM","score":0.4749000072479248},{"id":"https://openalex.org/keywords/schema","display_name":"Schema (genetic algorithms)","score":0.4722999930381775},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.41110000014305115},{"id":"https://openalex.org/keywords/exploratory-analysis","display_name":"Exploratory analysis","score":0.3668000102043152},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.36390000581741333},{"id":"https://openalex.org/keywords/categorical-variable","display_name":"Categorical variable","score":0.35659998655319214},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.3384999930858612},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.3179999887943268}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6671000123023987},{"id":"https://openalex.org/C70388272","wikidata":"https://www.wikidata.org/wiki/Q5968558","display_name":"IBM","level":2,"score":0.4749000072479248},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.4722999930381775},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.41110000014305115},{"id":"https://openalex.org/C3018260909","wikidata":"https://www.wikidata.org/wiki/Q1322871","display_name":"Exploratory analysis","level":2,"score":0.3668000102043152},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.36390000581741333},{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.35659998655319214},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.3384999930858612},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.3179999887943268},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.3147999942302704},{"id":"https://openalex.org/C117447612","wikidata":"https://www.wikidata.org/wiki/Q1412670","display_name":"Software quality","level":4,"score":0.3107999861240387},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.2973000109195709},{"id":"https://openalex.org/C63882131","wikidata":"https://www.wikidata.org/wiki/Q17122954","display_name":"Strengths and weaknesses","level":2,"score":0.2953999936580658},{"id":"https://openalex.org/C2776999362","wikidata":"https://www.wikidata.org/wiki/Q2349274","display_name":"Planner","level":2,"score":0.27889999747276306},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.274399995803833},{"id":"https://openalex.org/C2777548347","wikidata":"https://www.wikidata.org/wiki/Q5456937","display_name":"Flagging","level":2,"score":0.2727000117301941},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.2720000147819519},{"id":"https://openalex.org/C100521375","wikidata":"https://www.wikidata.org/wiki/Q2015382","display_name":"Competence (human resources)","level":2,"score":0.27129998803138733},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.26919999718666077},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.26759999990463257},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.26499998569488525},{"id":"https://openalex.org/C195094911","wikidata":"https://www.wikidata.org/wiki/Q14167904","display_name":"Process management","level":1,"score":0.25529998540878296}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.29848","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.29848","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.2603.29848","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.29848","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":{"We":[0,58],"introduce":[1],"a":[2,178,192],"comprehensive":[3],"validation":[4,166,186],"framework":[5,20,61],"for":[6,145,162,194],"LLM-based":[7],"agentic":[8,189,200],"systems":[9],"that":[10,30,133],"provides":[11],"systematic":[12],"diagnosis":[13],"and":[14,25,39,56,71,85,95,110,139,147,159,184,198],"improvement":[15],"of":[16],"reliability":[17],"failures.":[18],"The":[19,74],"includes":[21],"fifteen":[22],"failure-detection":[23],"tools":[24],"two":[26],"root-cause":[27],"analysis":[28,75,151],"modules":[29],"jointly":[31],"uncover":[32],"weaknesses":[33],"across":[34],"input":[35],"handling,":[36],"prompt":[37,83],"design,":[38],"output":[40],"generation.":[41],"It":[42],"integrates":[43],"lightweight":[44],"rule-based":[45],"checks":[46],"with":[47,122],"LLM-as-a-judge":[48],"assessments":[49],"to":[50,62,113],"support":[51],"structured":[52],"incident":[53],"detection,":[54],"classification,":[55],"repair.":[57],"applied":[59],"the":[60,69,120,135],"IBM":[63],"CUGA,":[64],"evaluating":[65],"its":[66],"performance":[67],"on":[68,88,155],"AppWorld":[70],"WebArena":[72],"benchmarks.":[73],"revealed":[76],"recurrent":[77],"planner":[78],"misalignments,":[79],"schema":[80],"violations,":[81],"brittle":[82],"dependencies,":[84],"more.":[86],"Based":[87],"these":[89],"insights,":[90],"we":[91,128],"refined":[92],"both":[93],"prompting":[94],"coding":[96],"strategies,":[97],"maintaining":[98],"CUGA's":[99],"benchmark":[100],"results":[101,176],"while":[102],"enabling":[103],"mid-sized":[104],"models":[105],"such":[106],"as":[107],"Llama":[108],"4":[109],"Mistral":[111],"Medium":[112],"achieve":[114],"notable":[115],"accuracy":[116],"gains,":[117],"substantially":[118],"narrowing":[119],"gap":[121],"frontier":[123],"models.":[124],"Beyond":[125],"quantitative":[126],"validation,":[127],"conducted":[129],"an":[130,143,171],"exploratory":[131],"study":[132],"fed":[134],"framework's":[136],"diagnostic":[137],"outputs":[138],"agent":[140],"description":[141],"into":[142,170],"LLM":[144],"self-reflection":[146],"prioritization.":[148],"This":[149],"interactive":[150],"produced":[152],"actionable":[153],"insights":[154],"recurring":[156],"failure":[157],"patterns":[158],"focus":[160],"areas":[161],"improvement,":[163],"demonstrating":[164],"how":[165],"itself":[167],"can":[168],"evolve":[169],"agentic,":[172],"dialogue-driven":[173],"process.":[174],"These":[175],"show":[177],"path":[179],"toward":[180],"scalable,":[181],"quality":[182],"assurance,":[183],"adaptive":[185],"in":[187],"production":[188],"systems,":[190],"offering":[191],"foundation":[193],"more":[195],"robust,":[196],"interpretable,":[197],"self-improving":[199],"architectures.":[201]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-04-02T00:00:00"}