@inproceedings{liu-etal-2026-llms,
title = "Do {LLM}s Catch Their Own Mistakes? A Comprehensive Benchmark for Reflective Tool Use {LLM}s",
author = "Liu, Zheyuan and
Xiao, Liqiang and
Li, Yang and
Yun, Hyokun and
Li, Lihong and
Zhang, Chao and
Jiang, Meng",
editor = "Liakata, Maria and
Moreira, Viviane P. and
Zhang, Jiajun and
Jurgens, David",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-acl.86/",
pages = "1748--1773",
ISBN = "979-8-89176-395-1",
abstract = "Large language models (LLMs) increasingly rely on external tools to complete complex tasks, yet their ability to recognize and correct their own tool-use mistakes remains underexplored. Existing benchmarks primarily evaluate planning and execution success, overlooking the self-reflective dimension of tool use. To address this gap, we present ReflecTool-Bench, the first benchmark designed to assess LLMs' self-reflective reasoning in tool-augmented multi-turn dialogues. ReflecTool-Bench covers 10 domains with 88 distinct APIs and 968 annotated dialogues, systematically injecting diverse error types arising from both user and assistant behavior. The benchmark defines two complementary evaluation setups: the Critique task, where models diagnose errors in third-party dialogues, and the Self-Reflection Task, where models must detect and repair their own prior tool-use mistakes. We introduce fine-grained metrics for error detection, error classification, correction accuracy, and explanation quality, enabling a holistic assessment of reflective reasoning. Evaluations across 12 state-of-the-art models, including both API-based closed source models and open source models, reveal that while models can reliably identify user-originated errors, they struggle with assistant-originated ones, and performance drops sharply when moving from critique to self-reflection."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liu-etal-2026-llms">
<titleInfo>
<title>Do LLMs Catch Their Own Mistakes? A Comprehensive Benchmark for Reflective Tool Use LLMs</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zheyuan</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Liqiang</namePart>
<namePart type="family">Xiao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hyokun</namePart>
<namePart type="family">Yun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lihong</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chao</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Meng</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Liakata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Viviane</namePart>
<namePart type="given">P</namePart>
<namePart type="family">Moreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiajun</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Jurgens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-395-1</identifier>
</relatedItem>
<abstract>Large language models (LLMs) increasingly rely on external tools to complete complex tasks, yet their ability to recognize and correct their own tool-use mistakes remains underexplored. Existing benchmarks primarily evaluate planning and execution success, overlooking the self-reflective dimension of tool use. To address this gap, we present ReflecTool-Bench, the first benchmark designed to assess LLMs’ self-reflective reasoning in tool-augmented multi-turn dialogues. ReflecTool-Bench covers 10 domains with 88 distinct APIs and 968 annotated dialogues, systematically injecting diverse error types arising from both user and assistant behavior. The benchmark defines two complementary evaluation setups: the Critique task, where models diagnose errors in third-party dialogues, and the Self-Reflection Task, where models must detect and repair their own prior tool-use mistakes. We introduce fine-grained metrics for error detection, error classification, correction accuracy, and explanation quality, enabling a holistic assessment of reflective reasoning. Evaluations across 12 state-of-the-art models, including both API-based closed source models and open source models, reveal that while models can reliably identify user-originated errors, they struggle with assistant-originated ones, and performance drops sharply when moving from critique to self-reflection.</abstract>
<identifier type="citekey">liu-etal-2026-llms</identifier>
<location>
<url>https://aclanthology.org/2026.findings-acl.86/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>1748</start>
<end>1773</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Do LLMs Catch Their Own Mistakes? A Comprehensive Benchmark for Reflective Tool Use LLMs
%A Liu, Zheyuan
%A Xiao, Liqiang
%A Li, Yang
%A Yun, Hyokun
%A Li, Lihong
%A Zhang, Chao
%A Jiang, Meng
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Findings of the Association for Computational Linguistics: ACL 2026
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-395-1
%F liu-etal-2026-llms
%X Large language models (LLMs) increasingly rely on external tools to complete complex tasks, yet their ability to recognize and correct their own tool-use mistakes remains underexplored. Existing benchmarks primarily evaluate planning and execution success, overlooking the self-reflective dimension of tool use. To address this gap, we present ReflecTool-Bench, the first benchmark designed to assess LLMs’ self-reflective reasoning in tool-augmented multi-turn dialogues. ReflecTool-Bench covers 10 domains with 88 distinct APIs and 968 annotated dialogues, systematically injecting diverse error types arising from both user and assistant behavior. The benchmark defines two complementary evaluation setups: the Critique task, where models diagnose errors in third-party dialogues, and the Self-Reflection Task, where models must detect and repair their own prior tool-use mistakes. We introduce fine-grained metrics for error detection, error classification, correction accuracy, and explanation quality, enabling a holistic assessment of reflective reasoning. Evaluations across 12 state-of-the-art models, including both API-based closed source models and open source models, reveal that while models can reliably identify user-originated errors, they struggle with assistant-originated ones, and performance drops sharply when moving from critique to self-reflection.
%U https://aclanthology.org/2026.findings-acl.86/
%P 1748-1773
Markdown (Informal)
[Do LLMs Catch Their Own Mistakes? A Comprehensive Benchmark for Reflective Tool Use LLMs](https://aclanthology.org/2026.findings-acl.86/) (Liu et al., Findings 2026)
ACL
- Zheyuan Liu, Liqiang Xiao, Yang Li, Hyokun Yun, Lihong Li, Chao Zhang, and Meng Jiang. 2026. Do LLMs Catch Their Own Mistakes? A Comprehensive Benchmark for Reflective Tool Use LLMs. In Findings of the Association for Computational Linguistics: ACL 2026, pages 1748–1773, San Diego, California, United States. Association for Computational Linguistics.