@inproceedings{ionov-etal-2026-call,
title = "Call, Reward, Repeat: Advancing Dialog State Tracking with {GRPO} and Function Calling",
author = "Ionov, Timur and
Marshalova, Anna and
Malykh, Valentin",
editor = "Baez Santamaria, Selene and
Somayajula, Sai Ashish and
Yamaguchi, Atsuki",
booktitle = "Proceedings of the 19th Conference of the {E}uropean Chapter of the {A}ssociation for {C}omputational {L}inguistics (Volume 4: Student Research Workshop)",
month = mar,
year = "2026",
address = "Rabat, Morocco",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.eacl-srw.21/",
pages = "292--303",
ISBN = "979-8-89176-383-8",
abstract = "Recent advancements in Large Language Models (LLMs) have notably enhanced task-oriented dialogue systems, particularly in Dialogue State Tracking (DST), owing to their generative capabilities and strong generalization. Although recent approaches such as LDST and FnCTOD significantly improved cross-domain DST performance via supervised fine-tuning (SFT), these methods typically require substantial amounts of domain-specific data. In this paper, we address this limitation by employing Group Relative Policy Optimization (GRPO) - a critic-free reinforcement learning method that efficiently guides LLMs toward improved DST accuracy even under low-resource conditions. Our results on established DST benchmarks, including MultiWOZ 2.1 and 2.4, demonstrate that the RL approach achieves superior performance to existing methods while using significantly reduced out-of-domain training data. In addition, we found out that models pretrained specifically for tool-use tasks can be a better starting point, especially on small scales."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ionov-etal-2026-call">
<titleInfo>
<title>Call, Reward, Repeat: Advancing Dialog State Tracking with GRPO and Function Calling</title>
</titleInfo>
<name type="personal">
<namePart type="given">Timur</namePart>
<namePart type="family">Ionov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Marshalova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Valentin</namePart>
<namePart type="family">Malykh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 4: Student Research Workshop)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Selene</namePart>
<namePart type="family">Baez Santamaria</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sai</namePart>
<namePart type="given">Ashish</namePart>
<namePart type="family">Somayajula</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Atsuki</namePart>
<namePart type="family">Yamaguchi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Rabat, Morocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-383-8</identifier>
</relatedItem>
<abstract>Recent advancements in Large Language Models (LLMs) have notably enhanced task-oriented dialogue systems, particularly in Dialogue State Tracking (DST), owing to their generative capabilities and strong generalization. Although recent approaches such as LDST and FnCTOD significantly improved cross-domain DST performance via supervised fine-tuning (SFT), these methods typically require substantial amounts of domain-specific data. In this paper, we address this limitation by employing Group Relative Policy Optimization (GRPO) - a critic-free reinforcement learning method that efficiently guides LLMs toward improved DST accuracy even under low-resource conditions. Our results on established DST benchmarks, including MultiWOZ 2.1 and 2.4, demonstrate that the RL approach achieves superior performance to existing methods while using significantly reduced out-of-domain training data. In addition, we found out that models pretrained specifically for tool-use tasks can be a better starting point, especially on small scales.</abstract>
<identifier type="citekey">ionov-etal-2026-call</identifier>
<location>
<url>https://aclanthology.org/2026.eacl-srw.21/</url>
</location>
<part>
<date>2026-03</date>
<extent unit="page">
<start>292</start>
<end>303</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Call, Reward, Repeat: Advancing Dialog State Tracking with GRPO and Function Calling
%A Ionov, Timur
%A Marshalova, Anna
%A Malykh, Valentin
%Y Baez Santamaria, Selene
%Y Somayajula, Sai Ashish
%Y Yamaguchi, Atsuki
%S Proceedings of the 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 4: Student Research Workshop)
%D 2026
%8 March
%I Association for Computational Linguistics
%C Rabat, Morocco
%@ 979-8-89176-383-8
%F ionov-etal-2026-call
%X Recent advancements in Large Language Models (LLMs) have notably enhanced task-oriented dialogue systems, particularly in Dialogue State Tracking (DST), owing to their generative capabilities and strong generalization. Although recent approaches such as LDST and FnCTOD significantly improved cross-domain DST performance via supervised fine-tuning (SFT), these methods typically require substantial amounts of domain-specific data. In this paper, we address this limitation by employing Group Relative Policy Optimization (GRPO) - a critic-free reinforcement learning method that efficiently guides LLMs toward improved DST accuracy even under low-resource conditions. Our results on established DST benchmarks, including MultiWOZ 2.1 and 2.4, demonstrate that the RL approach achieves superior performance to existing methods while using significantly reduced out-of-domain training data. In addition, we found out that models pretrained specifically for tool-use tasks can be a better starting point, especially on small scales.
%U https://aclanthology.org/2026.eacl-srw.21/
%P 292-303
Markdown (Informal)
[Call, Reward, Repeat: Advancing Dialog State Tracking with GRPO and Function Calling](https://aclanthology.org/2026.eacl-srw.21/) (Ionov et al., EACL 2026)
ACL