@inproceedings{acikgoz-etal-2026-speakrl,
title = "{S}peak{RL}: Synergizing Reasoning, Speaking, and Acting in Language Models with Reinforcement Learning",
author = "Acikgoz, Emre Can and
Oh, Jinoh and
Hao, Jie and
Jeon, Joo Hyuk and
Ji, Heng and
Hakkani-Tur, Dilek and
Tur, Gokhan and
Li, Xiang and
Ma, Chengyuan and
Fan, Xing",
editor = "Riccardi, Giuseppe and
Mousavi, Seyed Mahed and
Torres, Maria Ines and
Yoshino, Koichiro and
Callejas, Zoraida and
Chowdhury, Shammur Absar and
Chen, Yun-Nung and
Bechet, Frederic and
Gustafson, Joakim and
Damnati, G{\'e}raldine and
Papangelis, Alex and
D{'}Haro, Luis Fernando and
Mendon{\c{c}}a, John and
Bernardi, Raffaella and
Hakkani-Tur, Dilek and
Di Fabbrizio, Giuseppe {''}Pino{''} and
Kawahara, Tatsuya and
Alam, Firoj and
Tur, Gokhan and
Johnston, Michael",
booktitle = "Proceedings of the 16th International Workshop on Spoken Dialogue System Technology",
month = feb,
year = "2026",
address = "Trento, Italy",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.iwsds-1.32/",
pages = "312--325",
abstract = "Effective human-agent collaboration is increasingly prevalent in real-world applications. Current trends in such collaborations are predominantly unidirectional, with users providing instructions or posing questions to agents, where agents respond directly without seeking necessary clarifications or confirmations. However, the evolving capabilities of these agents require more proactive engagement, where agents should dynamically participate in conversations to clarify user intents, resolve ambiguities, and adapt to changing circumstances. Existing prior work under-utilize the conversational capabilities of language models ({LM}s), thereby optimizing agents as better followers rather than effective speakers. In this work, we introduce {S}peak{RL}, a reinforcement learning ({RL}) method that enhances agents' conversational capabilities by rewarding proactive interactions with users, such as asking right clarification questions when necessary. To support this, we curate {S}peak{ER}, a synthetic dataset that includes diverse scenarios from task-oriented dialogues, where tasks are resolved through interactive clarification questions. We present a systematic analysis of reward design for conversational proactivity and propose a principled reward formulation for teaching agents to balance asking with acting. Empirical evaluations demonstrate that our approach achieves a 20.14{\%} absolute improvement in task completion over base models without increasing conversation turns even surpassing even much larger proprietary models, demonstrating the promise of clarification-centric user-agent interactions."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="acikgoz-etal-2026-speakrl">
<titleInfo>
<title>SpeakRL: Synergizing Reasoning, Speaking, and Acting in Language Models with Reinforcement Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Emre</namePart>
<namePart type="given">Can</namePart>
<namePart type="family">Acikgoz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jinoh</namePart>
<namePart type="family">Oh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jie</namePart>
<namePart type="family">Hao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joo</namePart>
<namePart type="given">Hyuk</namePart>
<namePart type="family">Jeon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heng</namePart>
<namePart type="family">Ji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dilek</namePart>
<namePart type="family">Hakkani-Tur</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gokhan</namePart>
<namePart type="family">Tur</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiang</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chengyuan</namePart>
<namePart type="family">Ma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xing</namePart>
<namePart type="family">Fan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-02</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 16th International Workshop on Spoken Dialogue System Technology</title>
</titleInfo>
<name type="personal">
<namePart type="given">Giuseppe</namePart>
<namePart type="family">Riccardi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seyed</namePart>
<namePart type="given">Mahed</namePart>
<namePart type="family">Mousavi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="given">Ines</namePart>
<namePart type="family">Torres</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Koichiro</namePart>
<namePart type="family">Yoshino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zoraida</namePart>
<namePart type="family">Callejas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shammur</namePart>
<namePart type="given">Absar</namePart>
<namePart type="family">Chowdhury</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yun-Nung</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frederic</namePart>
<namePart type="family">Bechet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joakim</namePart>
<namePart type="family">Gustafson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Géraldine</namePart>
<namePart type="family">Damnati</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alex</namePart>
<namePart type="family">Papangelis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luis</namePart>
<namePart type="given">Fernando</namePart>
<namePart type="family">D’Haro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">John</namePart>
<namePart type="family">Mendonça</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Raffaella</namePart>
<namePart type="family">Bernardi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dilek</namePart>
<namePart type="family">Hakkani-Tur</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Giuseppe</namePart>
<namePart type="given">”Pino”</namePart>
<namePart type="family">Di Fabbrizio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tatsuya</namePart>
<namePart type="family">Kawahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Firoj</namePart>
<namePart type="family">Alam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gokhan</namePart>
<namePart type="family">Tur</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Johnston</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Trento, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Effective human-agent collaboration is increasingly prevalent in real-world applications. Current trends in such collaborations are predominantly unidirectional, with users providing instructions or posing questions to agents, where agents respond directly without seeking necessary clarifications or confirmations. However, the evolving capabilities of these agents require more proactive engagement, where agents should dynamically participate in conversations to clarify user intents, resolve ambiguities, and adapt to changing circumstances. Existing prior work under-utilize the conversational capabilities of language models (LMs), thereby optimizing agents as better followers rather than effective speakers. In this work, we introduce SpeakRL, a reinforcement learning (RL) method that enhances agents’ conversational capabilities by rewarding proactive interactions with users, such as asking right clarification questions when necessary. To support this, we curate SpeakER, a synthetic dataset that includes diverse scenarios from task-oriented dialogues, where tasks are resolved through interactive clarification questions. We present a systematic analysis of reward design for conversational proactivity and propose a principled reward formulation for teaching agents to balance asking with acting. Empirical evaluations demonstrate that our approach achieves a 20.14% absolute improvement in task completion over base models without increasing conversation turns even surpassing even much larger proprietary models, demonstrating the promise of clarification-centric user-agent interactions.</abstract>
<identifier type="citekey">acikgoz-etal-2026-speakrl</identifier>
<location>
<url>https://aclanthology.org/2026.iwsds-1.32/</url>
</location>
<part>
<date>2026-02</date>
<extent unit="page">
<start>312</start>
<end>325</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SpeakRL: Synergizing Reasoning, Speaking, and Acting in Language Models with Reinforcement Learning
%A Acikgoz, Emre Can
%A Oh, Jinoh
%A Hao, Jie
%A Jeon, Joo Hyuk
%A Ji, Heng
%A Hakkani-Tur, Dilek
%A Tur, Gokhan
%A Li, Xiang
%A Ma, Chengyuan
%A Fan, Xing
%Y Riccardi, Giuseppe
%Y Mousavi, Seyed Mahed
%Y Torres, Maria Ines
%Y Yoshino, Koichiro
%Y Callejas, Zoraida
%Y Chowdhury, Shammur Absar
%Y Chen, Yun-Nung
%Y Bechet, Frederic
%Y Gustafson, Joakim
%Y Damnati, Géraldine
%Y Papangelis, Alex
%Y D’Haro, Luis Fernando
%Y Mendonça, John
%Y Bernardi, Raffaella
%Y Hakkani-Tur, Dilek
%Y Di Fabbrizio, Giuseppe ”Pino”
%Y Kawahara, Tatsuya
%Y Alam, Firoj
%Y Tur, Gokhan
%Y Johnston, Michael
%S Proceedings of the 16th International Workshop on Spoken Dialogue System Technology
%D 2026
%8 February
%I Association for Computational Linguistics
%C Trento, Italy
%F acikgoz-etal-2026-speakrl
%X Effective human-agent collaboration is increasingly prevalent in real-world applications. Current trends in such collaborations are predominantly unidirectional, with users providing instructions or posing questions to agents, where agents respond directly without seeking necessary clarifications or confirmations. However, the evolving capabilities of these agents require more proactive engagement, where agents should dynamically participate in conversations to clarify user intents, resolve ambiguities, and adapt to changing circumstances. Existing prior work under-utilize the conversational capabilities of language models (LMs), thereby optimizing agents as better followers rather than effective speakers. In this work, we introduce SpeakRL, a reinforcement learning (RL) method that enhances agents’ conversational capabilities by rewarding proactive interactions with users, such as asking right clarification questions when necessary. To support this, we curate SpeakER, a synthetic dataset that includes diverse scenarios from task-oriented dialogues, where tasks are resolved through interactive clarification questions. We present a systematic analysis of reward design for conversational proactivity and propose a principled reward formulation for teaching agents to balance asking with acting. Empirical evaluations demonstrate that our approach achieves a 20.14% absolute improvement in task completion over base models without increasing conversation turns even surpassing even much larger proprietary models, demonstrating the promise of clarification-centric user-agent interactions.
%U https://aclanthology.org/2026.iwsds-1.32/
%P 312-325
Markdown (Informal)
[SpeakRL: Synergizing Reasoning, Speaking, and Acting in Language Models with Reinforcement Learning](https://aclanthology.org/2026.iwsds-1.32/) (Acikgoz et al., IWSDS 2026)
ACL
- Emre Can Acikgoz, Jinoh Oh, Jie Hao, Joo Hyuk Jeon, Heng Ji, Dilek Hakkani-Tur, Gokhan Tur, Xiang Li, Chengyuan Ma, and Xing Fan. 2026. SpeakRL: Synergizing Reasoning, Speaking, and Acting in Language Models with Reinforcement Learning. In Proceedings of the 16th International Workshop on Spoken Dialogue System Technology, pages 312–325, Trento, Italy. Association for Computational Linguistics.