{"id":"https://openalex.org/W7166819471","doi":"https://doi.org/10.18653/v1/2026.findings-acl.98","title":"Towards Self-Improving Error Diagnosis in Multi-Agent Systems","display_name":"Towards Self-Improving Error Diagnosis in Multi-Agent Systems","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166819471","doi":"https://doi.org/10.18653/v1/2026.findings-acl.98"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.98","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.98","pdf_url":"https://aclanthology.org/2026.findings-acl.98.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.findings-acl.98.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139714924","display_name":"Jiazheng Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiazheng Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139769213","display_name":"Emine Yilmaz","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Emine Yilmaz","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139730058","display_name":"Bei Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bei Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139776897","display_name":"Thu Le","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Thu Le","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":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.80920843,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2063","last_page":"2077"},"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":0.7071999907493591,"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":0.7071999907493591,"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/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.03799999877810478,"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/T10876","display_name":"Fault Detection and Control Systems","score":0.031300000846385956,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.2660999894142151},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.25920000672340393},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.23839999735355377},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.22939999401569366},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.22769999504089355}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5242000222206116},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3562000095844269},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.28760001063346863},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.2660999894142151},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.25920000672340393},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.23849999904632568},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.23839999735355377},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.22939999401569366},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.22769999504089355},{"id":"https://openalex.org/C103088060","wikidata":"https://www.wikidata.org/wiki/Q1062839","display_name":"Error detection and correction","level":2,"score":0.2231999933719635}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.98","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.98","pdf_url":"https://aclanthology.org/2026.findings-acl.98.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-acl.98","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.98","pdf_url":"https://aclanthology.org/2026.findings-acl.98.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166819471.pdf","grobid_xml":"https://content.openalex.org/works/W7166819471.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"Language":[1],"Model":[2],"(LLM)-based":[3],"Multi-Agent":[4],"Systems":[5],"(MAS)":[6],"enable":[7],"complex":[8],"problem-solving":[9],"but":[10],"introduce":[11,50],"significant":[12],"debugging":[13],"challenges,":[14],"characterized":[15],"by":[16,123],"long":[17],"interaction":[18],"traces,":[19],"inter-agent":[20],"dependencies,":[21],"and":[22,63,92,134],"delayed":[23],"error":[24,42,66,104,119],"manifestation.Existing":[25],"diagnostic":[26],"approaches":[27],"often":[28],"rely":[29],"on":[30],"expensive":[31],"expert":[32],"annotation":[33],"or":[34],"\"LLM-as-a-judge\"":[35],"paradigms,":[36],"which":[37],"struggle":[38],"to":[39,79,88,102],"pinpoint":[40],"decisive":[41],"steps":[43],"within":[44],"extended":[45],"contexts.In":[46],"this":[47],"paper,":[48],"we":[49],"ERRORPROBE,":[51],"a":[52,71,95,111],"self-improving":[53],"framework":[54,68],"for":[55,129],"semantic":[56],"failure":[57,77],"attribution":[58],"that":[59,115,138],"identifies":[60],"responsible":[61],"agents":[62],"the":[64,75,127,132,148],"originating":[65],"step.The":[67],"operates":[69],"via":[70],"three-stage":[72],"pipeline:(1)":[73],"operationalizing":[74],"MAS":[76],"taxonomy":[78],"detect":[80],"local":[81],"anomalies,":[82],"(2)":[83],"performing":[84],"symptom-driven":[85],"backward":[86],"tracing":[87],"prune":[89],"irrelevant":[90],"context,":[91],"(3)":[93],"employing":[94],"specialized":[96],"multi-agent":[97],"team":[98],"(Strategist,":[99],"Investigator,":[100],"Arbiter)":[101],"validate":[103],"hypotheses":[105],"through":[106],"tool-grounded":[107],"execution.Crucially,":[108],"ERRORPROBE":[109,139],"maintains":[110],"verified":[112,149],"episodic":[113],"memory":[114,150],"updates":[116],"only":[117],"when":[118],"patterns":[120],"are":[121],"confirmed":[122],"executable":[124],"evidence,":[125],"without":[126,155],"need":[128],"annotation.Experiments":[130],"across":[131],"TRACERTRAJ":[133],"WHO&WHEN":[135],"benchmarks":[136],"demonstrate":[137],"significantly":[140],"outperforms":[141],"baselines,":[142],"particularly":[143],"in":[144],"step-level":[145],"localization,":[146],"while":[147],"enables":[151],"robust":[152],"cross-domain":[153],"transfer":[154],"retraining.":[156]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}