{"id":"https://openalex.org/W7166804145","doi":"https://doi.org/10.18653/v1/2026.findings-acl.86","title":"Do LLMs Catch Their Own Mistakes? A Comprehensive Benchmark for Reflective Tool Use LLMs","display_name":"Do LLMs Catch Their Own Mistakes? A Comprehensive Benchmark for Reflective Tool Use LLMs","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166804145","doi":"https://doi.org/10.18653/v1/2026.findings-acl.86"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.86","doi":"https://doi.org/10.18653/v1/2026.findings-acl.86","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.86","pdf_url":"https://aclanthology.org/2026.findings-acl.86.pdf","source":{"id":"https://openalex.org/S4363605144","display_name":"Findings of the Association for Computational Linguistics: ACL (Findings of ACL)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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"},"volume":null,"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2026.findings-acl.86.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139760761","display_name":"Zheyuan Liu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zheyuan Liu","raw_affiliation_strings":["University of Notre Dame , 2 Amazon ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Notre Dame , 2 Amazon ,","institution_ids":["https://openalex.org/I107639228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139837758","display_name":"Liqiang Xiao","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liqiang Xiao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139744315","display_name":"Yang Li","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061527181","display_name":"Hyokun Yun","orcid":"https://orcid.org/0000-0001-6169-4761","observed_orcids":["https://orcid.org/0000-0001-6169-4761"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hyokun Yun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139791354","display_name":"Lihong Li","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lihong Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139771161","display_name":"Chao Zhang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chao Zhang","raw_affiliation_strings":["Georgia Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5139754113","display_name":"Meng Jiang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Meng Jiang","raw_affiliation_strings":["University of Notre Dame , 2 Amazon ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Notre Dame , 2 Amazon ,","institution_ids":["https://openalex.org/I107639228"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"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":0.43846675,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1748","last_page":"1773"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.8939999938011169,"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/T12031","display_name":"Speech and dialogue systems","score":0.8939999938011169,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.03269999846816063,"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":0.03180000185966492,"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/large-language-models","display_name":"large language models","score":0.925000011920929},{"id":"https://openalex.org/keywords/tool-use","display_name":"tool use","score":0.8080000281333923},{"id":"https://openalex.org/keywords/self-reflection","display_name":"self-reflection","score":0.8429999947547913},{"id":"https://openalex.org/keywords/error-detection","display_name":"error detection","score":0.7110000252723694},{"id":"https://openalex.org/keywords/self-criticism","display_name":"self-criticism","score":0.621999979019165},{"id":"https://openalex.org/keywords/multi-turn-dialogue","display_name":"multi-turn dialogue","score":0.6830000281333923},{"id":"https://openalex.org/keywords/benchmark","display_name":"benchmark","score":0.7059999704360962},{"id":"https://openalex.org/keywords/error-classification","display_name":"error classification","score":0.6299999952316284},{"id":"https://openalex.org/keywords/error-correction","display_name":"error correction","score":0.5989999771118164},{"id":"https://openalex.org/keywords/reflective-thinking","display_name":"reflective thinking","score":0.546999990940094}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4603999853134155},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.41179999709129333},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3797999918460846},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.35350000858306885},{"id":"https://openalex.org/C107826830","wikidata":"https://www.wikidata.org/wiki/Q929380","display_name":"Environmental resource management","level":1,"score":0.31690001487731934},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.31520000100135803},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.30480000376701355},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.2953000068664551},{"id":"https://openalex.org/C32896092","wikidata":"https://www.wikidata.org/wiki/Q189447","display_name":"Risk management","level":2,"score":0.27239999175071716},{"id":"https://openalex.org/C12174686","wikidata":"https://www.wikidata.org/wiki/Q1058438","display_name":"Risk assessment","level":2,"score":0.26570001244544983},{"id":"https://openalex.org/C134560507","wikidata":"https://www.wikidata.org/wiki/Q753291","display_name":"Environmental economics","level":1,"score":0.25870001316070557},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.2563000023365021},{"id":"https://openalex.org/C91375879","wikidata":"https://www.wikidata.org/wiki/Q15473274","display_name":"Environmental planning","level":1,"score":0.25529998540878296},{"id":"https://openalex.org/C42475967","wikidata":"https://www.wikidata.org/wiki/Q194292","display_name":"Operations research","level":1,"score":0.2535000145435333}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.86","doi":"https://doi.org/10.18653/v1/2026.findings-acl.86","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.86","pdf_url":"https://aclanthology.org/2026.findings-acl.86.pdf","source":{"id":"https://openalex.org/S4363605144","display_name":"Findings of the Association for Computational Linguistics: ACL (Findings of ACL)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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.86","doi":"https://doi.org/10.18653/v1/2026.findings-acl.86","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.86","pdf_url":"https://aclanthology.org/2026.findings-acl.86.pdf","source":{"id":"https://openalex.org/S4363605144","display_name":"Findings of the Association for Computational Linguistics: ACL (Findings of ACL)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G1319247439","display_name":"RI: Small: Learning to Retrieve Structured Information for Summarization and Translation  of Unstructured Text","funder_award_id":"2137396","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G1709352092","display_name":"CAREER: Synergistic Approaches for Specialized Intelligent Assistance","funder_award_id":"2142827","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5578446656","display_name":"Collaborative Research:  Advancing STEM Online Learning by Augmenting Accessibility with Explanatory Captions and AI","funder_award_id":"2119531","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6436526700","display_name":"III: Small: Intelligent Scientific Text Analytics with Knowledge-Augmented Abductive Reasoning","funder_award_id":"2234058","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166804145.pdf","grobid_xml":"https://content.openalex.org/works/W7166804145.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4415311332","https://openalex.org/W4415961327","https://openalex.org/W4416258681","https://openalex.org/W4416615471","https://openalex.org/W4412875463","https://openalex.org/W4404649838","https://openalex.org/W7160616492","https://openalex.org/W4401042980","https://openalex.org/W7108211030","https://openalex.org/W4400222155"],"abstract_inverted_index":{"Large":[0],"language":[1],"models":[2,92,103,142,149],"(LLMs)":[3],"increasingly":[4],"rely":[5],"on":[6],"external":[7],"tools":[8],"to":[9,16,50,168],"complete":[10],"complex":[11],"tasks,":[12],"yet":[13],"their":[14,20,108],"ability":[15],"recognize":[17],"and":[18,30,66,79,98,106,123,143,160],"correct":[19],"own":[21,109],"tool-use":[22,111],"mistakes":[23],"remains":[24],"underexplored.Existing":[25],"benchmarks":[26],"primarily":[27],"evaluate":[28],"planning":[29],"execution":[31],"success,":[32],"overlooking":[33],"the":[34,46,88,99],"self-reflective":[35,53],"dimension":[36],"of":[37,130],"tool":[38],"use.To":[39],"address":[40],"this":[41],"gap,":[42],"we":[43],"present":[44],"ReflecTool-Bench,":[45],"first":[47],"benchmark":[48,82],"designed":[49],"assess":[51],"LLMs'":[52],"reasoning":[54],"in":[55,95],"toolaugmented":[56],"multi-turn":[57],"dialogues.ReflecTool-Bench":[58],"covers":[59],"10":[60],"domains":[61],"with":[62,157],"88":[63],"distinct":[64],"APIs":[65],"968":[67],"annotated":[68],"dialogues,":[69,97],"systematically":[70],"injecting":[71],"diverse":[72],"error":[73,117,119],"types":[74],"arising":[75],"from":[76,166],"both":[77,138],"user":[78],"assistant":[80],"behavior.The":[81],"defines":[83],"two":[84],"complementary":[85],"evaluation":[86],"setups:":[87],"Critique":[89],"task,":[90],"where":[91,102],"diagnose":[93],"errors":[94],"third-party":[96],"Self-Reflection":[100],"Task,":[101],"must":[104],"detect":[105],"repair":[107],"prior":[110],"mistakes.We":[112],"introduce":[113],"fine-grained":[114],"metrics":[115],"for":[116],"detection,":[118],"classification,":[120],"correction":[121],"accuracy,":[122],"explanation":[124],"quality,":[125],"enabling":[126],"a":[127],"holistic":[128],"assessment":[129],"reflective":[131],"reasoning.Evaluations":[132],"across":[133],"12":[134],"state-of-the-art":[135],"models,":[136,145],"including":[137],"API-based":[139],"closed":[140],"source":[141],"open-source":[144],"reveal":[146],"that":[147],"while":[148],"can":[150],"reliably":[151],"identify":[152],"user-originated":[153],"errors,":[154],"they":[155],"struggle":[156],"assistant-originated":[158],"ones,":[159],"performance":[161],"drops":[162],"sharply":[163],"when":[164],"moving":[165],"critique":[167],"self-reflection.":[169],"2":[170]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-07-02T00:00:00"}