@inproceedings{wang-etal-2025-rethinking-stateful,
title = "Rethinking Stateful Tool Use in Multi-Turn Dialogues: Benchmarks and Challenges",
author = "Wang, Hongru and
Huang, Wenyu and
Wang, Yufei and
Xi, Yuanhao and
Lu, Jianqiao and
Zhang, Huan and
Hu, Nan and
Liu, Zeming and
Pan, Jeff Z. and
Wong, Kam-Fai",
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-acl.284/",
doi = "10.18653/v1/2025.findings-acl.284",
pages = "5433--5453",
ISBN = "979-8-89176-256-5",
abstract = "Existing benchmarks that assess Language Models (LMs) as Language Agents (LAs) for tool use primarily focus on stateless, single-turn interactions or partial evaluations, such as tool selection in a single turn, overlooking the inherent stateful nature of interactions in multi-turn applications. To fulfill this gap, we propose DialogTool, a multi-turn dialogue dataset with stateful tool interactions considering the whole life cycle of tool use, across six key tasks in three stages: 1) \textit{tool creation}; 2) \textit{tool utilization}: tool awareness, tool selection, tool execution; and 3) \textit{role-consistent response}: response generation and role play. Furthermore, we build VirtualMobile {--} an embodied virtual mobile evaluation environment to simulate API calls and assess the robustness of the created APIs. Taking advantage of these artifacts, we conduct comprehensive evaluation on 13 distinct open- and closed-source LLMs and provide detailed analysis at each stage, revealing that the existing state-of-the-art LLMs still cannot perform well to use tools over long horizons ."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2025-rethinking-stateful">
<titleInfo>
<title>Rethinking Stateful Tool Use in Multi-Turn Dialogues: Benchmarks and Challenges</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hongru</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenyu</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yufei</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuanhao</namePart>
<namePart type="family">Xi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jianqiao</namePart>
<namePart type="family">Lu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Huan</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nan</namePart>
<namePart type="family">Hu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zeming</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jeff</namePart>
<namePart type="given">Z</namePart>
<namePart type="family">Pan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kam-Fai</namePart>
<namePart type="family">Wong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2025</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wanxiang</namePart>
<namePart type="family">Che</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joyce</namePart>
<namePart type="family">Nabende</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Shutova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">Taher</namePart>
<namePart type="family">Pilehvar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-256-5</identifier>
</relatedItem>
<abstract>Existing benchmarks that assess Language Models (LMs) as Language Agents (LAs) for tool use primarily focus on stateless, single-turn interactions or partial evaluations, such as tool selection in a single turn, overlooking the inherent stateful nature of interactions in multi-turn applications. To fulfill this gap, we propose DialogTool, a multi-turn dialogue dataset with stateful tool interactions considering the whole life cycle of tool use, across six key tasks in three stages: 1) tool creation; 2) tool utilization: tool awareness, tool selection, tool execution; and 3) role-consistent response: response generation and role play. Furthermore, we build VirtualMobile – an embodied virtual mobile evaluation environment to simulate API calls and assess the robustness of the created APIs. Taking advantage of these artifacts, we conduct comprehensive evaluation on 13 distinct open- and closed-source LLMs and provide detailed analysis at each stage, revealing that the existing state-of-the-art LLMs still cannot perform well to use tools over long horizons .</abstract>
<identifier type="citekey">wang-etal-2025-rethinking-stateful</identifier>
<identifier type="doi">10.18653/v1/2025.findings-acl.284</identifier>
<location>
<url>https://aclanthology.org/2025.findings-acl.284/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>5433</start>
<end>5453</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Rethinking Stateful Tool Use in Multi-Turn Dialogues: Benchmarks and Challenges
%A Wang, Hongru
%A Huang, Wenyu
%A Wang, Yufei
%A Xi, Yuanhao
%A Lu, Jianqiao
%A Zhang, Huan
%A Hu, Nan
%A Liu, Zeming
%A Pan, Jeff Z.
%A Wong, Kam-Fai
%Y Che, Wanxiang
%Y Nabende, Joyce
%Y Shutova, Ekaterina
%Y Pilehvar, Mohammad Taher
%S Findings of the Association for Computational Linguistics: ACL 2025
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-256-5
%F wang-etal-2025-rethinking-stateful
%X Existing benchmarks that assess Language Models (LMs) as Language Agents (LAs) for tool use primarily focus on stateless, single-turn interactions or partial evaluations, such as tool selection in a single turn, overlooking the inherent stateful nature of interactions in multi-turn applications. To fulfill this gap, we propose DialogTool, a multi-turn dialogue dataset with stateful tool interactions considering the whole life cycle of tool use, across six key tasks in three stages: 1) tool creation; 2) tool utilization: tool awareness, tool selection, tool execution; and 3) role-consistent response: response generation and role play. Furthermore, we build VirtualMobile – an embodied virtual mobile evaluation environment to simulate API calls and assess the robustness of the created APIs. Taking advantage of these artifacts, we conduct comprehensive evaluation on 13 distinct open- and closed-source LLMs and provide detailed analysis at each stage, revealing that the existing state-of-the-art LLMs still cannot perform well to use tools over long horizons .
%R 10.18653/v1/2025.findings-acl.284
%U https://aclanthology.org/2025.findings-acl.284/
%U https://doi.org/10.18653/v1/2025.findings-acl.284
%P 5433-5453
Markdown (Informal)
[Rethinking Stateful Tool Use in Multi-Turn Dialogues: Benchmarks and Challenges](https://aclanthology.org/2025.findings-acl.284/) (Wang et al., Findings 2025)
ACL
- Hongru Wang, Wenyu Huang, Yufei Wang, Yuanhao Xi, Jianqiao Lu, Huan Zhang, Nan Hu, Zeming Liu, Jeff Z. Pan, and Kam-Fai Wong. 2025. Rethinking Stateful Tool Use in Multi-Turn Dialogues: Benchmarks and Challenges. In Findings of the Association for Computational Linguistics: ACL 2025, pages 5433–5453, Vienna, Austria. Association for Computational Linguistics.