{"id":"https://openalex.org/W7161943619","doi":"https://doi.org/10.1145/3786167.3788427","title":"AgentFixer: From Failure Detection to Fix Recommendations in Agentic Systems","display_name":"AgentFixer: From Failure Detection to Fix Recommendations in Agentic Systems","publication_year":2026,"publication_date":"2026-04-12","ids":{"openalex":"https://openalex.org/W7161943619","doi":"https://doi.org/10.1145/3786167.3788427"},"language":null,"primary_location":{"id":"doi:10.1145/3786167.3788427","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3786167.3788427","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Workshop on Agentic Engineering","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3786167.3788427","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5093081414","display_name":"Hadar Mulian","orcid":null},"institutions":[{"id":"https://openalex.org/I4210167297","display_name":"IBM Research - Haifa","ror":"https://ror.org/05rw9t746","country_code":"IL","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210167297"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Hadar Mulian","raw_affiliation_strings":["IBM Research, Haifa, Israel"],"raw_orcid":"https://orcid.org/0009-0008-8614-0739","affiliations":[{"raw_affiliation_string":"IBM Research, Haifa, Israel","institution_ids":["https://openalex.org/I4210167297"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001266138","display_name":"Sergey Zeltyn","orcid":"https://orcid.org/0000-0003-2540-1604"},"institutions":[{"id":"https://openalex.org/I4210167297","display_name":"IBM Research - Haifa","ror":"https://ror.org/05rw9t746","country_code":"IL","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210167297"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Sergey Zeltyn","raw_affiliation_strings":["IBM Research, Haifa, Israel"],"raw_orcid":"https://orcid.org/0000-0003-2540-1604","affiliations":[{"raw_affiliation_string":"IBM Research, Haifa, Israel","institution_ids":["https://openalex.org/I4210167297"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132644891","display_name":"Ido Levy","orcid":null},"institutions":[{"id":"https://openalex.org/I4210167297","display_name":"IBM Research - Haifa","ror":"https://ror.org/05rw9t746","country_code":"IL","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210167297"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Ido Levy","raw_affiliation_strings":["IBM Research, Haifa, Israel"],"raw_orcid":"https://orcid.org/0009-0005-7400-3452","affiliations":[{"raw_affiliation_string":"IBM Research, Haifa, Israel","institution_ids":["https://openalex.org/I4210167297"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132684966","display_name":"Liane Galanti","orcid":null},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Liane Galanti","raw_affiliation_strings":["Princeton University, Princeton, New Jersey, USA"],"raw_orcid":"https://orcid.org/0009-0005-3808-016X","affiliations":[{"raw_affiliation_string":"Princeton University, Princeton, New Jersey, USA","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061821122","display_name":"Avi Yaeli","orcid":null},"institutions":[{"id":"https://openalex.org/I4210167297","display_name":"IBM Research - Haifa","ror":"https://ror.org/05rw9t746","country_code":"IL","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210167297"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Avi Yaeli","raw_affiliation_strings":["IBM Research, Haifa, Israel"],"raw_orcid":"https://orcid.org/0000-0003-4698-1927","affiliations":[{"raw_affiliation_string":"IBM Research, Haifa, Israel","institution_ids":["https://openalex.org/I4210167297"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5132664340","display_name":"Segev Shlomov","orcid":null},"institutions":[{"id":"https://openalex.org/I4210167297","display_name":"IBM Research - Haifa","ror":"https://ror.org/05rw9t746","country_code":"IL","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210167297"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Segev Shlomov","raw_affiliation_strings":["IBM Research, Haifa, Israel"],"raw_orcid":"https://orcid.org/0000-0003-1216-8284","affiliations":[{"raw_affiliation_string":"IBM Research, Haifa, Israel","institution_ids":["https://openalex.org/I4210167297"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"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":0.82612512,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"96","last_page":"103"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10142","display_name":"Formal Methods in Verification","score":0.26019999384880066,"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":0.26019999384880066,"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":0.1590999960899353,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.12370000034570694,"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/ibm","display_name":"IBM","score":0.478300005197525},{"id":"https://openalex.org/keywords/schema","display_name":"Schema (genetic algorithms)","score":0.4767000079154968},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.41449999809265137},{"id":"https://openalex.org/keywords/categorical-variable","display_name":"Categorical variable","score":0.37790000438690186},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.36329999566078186},{"id":"https://openalex.org/keywords/exploratory-analysis","display_name":"Exploratory analysis","score":0.36160001158714294},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.35019999742507935}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6791999936103821},{"id":"https://openalex.org/C70388272","wikidata":"https://www.wikidata.org/wiki/Q5968558","display_name":"IBM","level":2,"score":0.478300005197525},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.4767000079154968},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.41449999809265137},{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.37790000438690186},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.36329999566078186},{"id":"https://openalex.org/C3018260909","wikidata":"https://www.wikidata.org/wiki/Q1322871","display_name":"Exploratory analysis","level":2,"score":0.36160001158714294},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.35019999742507935},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.3172999918460846},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.31700000166893005},{"id":"https://openalex.org/C117447612","wikidata":"https://www.wikidata.org/wiki/Q1412670","display_name":"Software quality","level":4,"score":0.31700000166893005},{"id":"https://openalex.org/C2776999362","wikidata":"https://www.wikidata.org/wiki/Q2349274","display_name":"Planner","level":2,"score":0.2985000014305115},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.2953999936580658},{"id":"https://openalex.org/C63882131","wikidata":"https://www.wikidata.org/wiki/Q17122954","display_name":"Strengths and weaknesses","level":2,"score":0.29089999198913574},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.2858000099658966},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.27619999647140503},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.2718999981880188},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.27000001072883606},{"id":"https://openalex.org/C2777548347","wikidata":"https://www.wikidata.org/wiki/Q5456937","display_name":"Flagging","level":2,"score":0.262800008058548},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.26170000433921814},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.25949999690055847}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3786167.3788427","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3786167.3788427","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Workshop on Agentic Engineering","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3786167.3788427","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3786167.3788427","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 International Workshop on Agentic Engineering","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W2798935874","https://openalex.org/W4403334020","https://openalex.org/W4404783192","https://openalex.org/W4409361510","https://openalex.org/W4412877164","https://openalex.org/W4415427913","https://openalex.org/W7125909867","https://openalex.org/W7133239970"],"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\u2019s":[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\u2019s":[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":"2026-06-11T09:08:48.828518","created_date":"2026-05-22T00:00:00"}