@inproceedings{garcia-anakabe-etal-2026-adding,
title = "Adding Determinism to a Dialogue Agent for a Robotic Environment",
author = "Garcia Anakabe, Oihana and
Cocola, Riccardo and
Aceta, Cristina",
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-1.26/",
pages = "253--261",
abstract = "Large Language Models ({LLM}s) have strong capabilities in natural dialogue, but their inherent indeterminacy presents challenges in robotic environments where safety and reliability are critical. In this study, we propose a dialogue agent that has been developed to guide and support human operators during robot demonstrations, following the Learning from Demonstration ({L}f{D}) paradigm, where the robot learns tasks from the operator{'}s actions. The agent presented in this work extends the standard prompt-based {LLM} setup by integrating state graphs that explicitly encode dialogue states and transitions. This structure ensures that user interactions follow the intended path, while still allowing users to communicate in a flexible and natural manner. The state graph agent is benchmarked against a monolithic prompt baseline in challenging dialogue scenarios involving ambiguity, incomplete actions, or operator errors. Despite the {LLM} prompt achieving good standalone performance, the state-controlled agent shows greater contextual understanding, reasoning capability, and advisory performance, leading to more intelligent and reliable interactions."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="garcia-anakabe-etal-2026-adding">
<titleInfo>
<title>Adding Determinism to a Dialogue Agent for a Robotic Environment</title>
</titleInfo>
<name type="personal">
<namePart type="given">Oihana</namePart>
<namePart type="family">Garcia Anakabe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Riccardo</namePart>
<namePart type="family">Cocola</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cristina</namePart>
<namePart type="family">Aceta</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>Large Language Models (LLMs) have strong capabilities in natural dialogue, but their inherent indeterminacy presents challenges in robotic environments where safety and reliability are critical. In this study, we propose a dialogue agent that has been developed to guide and support human operators during robot demonstrations, following the Learning from Demonstration (LfD) paradigm, where the robot learns tasks from the operator’s actions. The agent presented in this work extends the standard prompt-based LLM setup by integrating state graphs that explicitly encode dialogue states and transitions. This structure ensures that user interactions follow the intended path, while still allowing users to communicate in a flexible and natural manner. The state graph agent is benchmarked against a monolithic prompt baseline in challenging dialogue scenarios involving ambiguity, incomplete actions, or operator errors. Despite the LLM prompt achieving good standalone performance, the state-controlled agent shows greater contextual understanding, reasoning capability, and advisory performance, leading to more intelligent and reliable interactions.</abstract>
<identifier type="citekey">garcia-anakabe-etal-2026-adding</identifier>
<location>
<url>https://aclanthology.org/2026.iwsds-1.26/</url>
</location>
<part>
<date>2026-02</date>
<extent unit="page">
<start>253</start>
<end>261</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Adding Determinism to a Dialogue Agent for a Robotic Environment
%A Garcia Anakabe, Oihana
%A Cocola, Riccardo
%A Aceta, Cristina
%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 garcia-anakabe-etal-2026-adding
%X Large Language Models (LLMs) have strong capabilities in natural dialogue, but their inherent indeterminacy presents challenges in robotic environments where safety and reliability are critical. In this study, we propose a dialogue agent that has been developed to guide and support human operators during robot demonstrations, following the Learning from Demonstration (LfD) paradigm, where the robot learns tasks from the operator’s actions. The agent presented in this work extends the standard prompt-based LLM setup by integrating state graphs that explicitly encode dialogue states and transitions. This structure ensures that user interactions follow the intended path, while still allowing users to communicate in a flexible and natural manner. The state graph agent is benchmarked against a monolithic prompt baseline in challenging dialogue scenarios involving ambiguity, incomplete actions, or operator errors. Despite the LLM prompt achieving good standalone performance, the state-controlled agent shows greater contextual understanding, reasoning capability, and advisory performance, leading to more intelligent and reliable interactions.
%U https://aclanthology.org/2026.iwsds-1.26/
%P 253-261
Markdown (Informal)
[Adding Determinism to a Dialogue Agent for a Robotic Environment](https://aclanthology.org/2026.iwsds-1.26/) (Garcia Anakabe et al., IWSDS 2026)
ACL