@inproceedings{dao-liao-2025-one,
title = "One Planner To Guide Them All ! Learning Adaptive Conversational Planners for Goal-oriented Dialogues",
author = "Dao, Huy Quang and
Liao, Lizi",
editor = "Christodoulopoulos, Christos and
Chakraborty, Tanmoy and
Rose, Carolyn and
Peng, Violet",
booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.emnlp-main.1123/",
pages = "22103--22127",
ISBN = "979-8-89176-332-6",
abstract = "Goal-oriented dialogues, such as recommendation and negotiation, often require balancing multiple, conflicting objectives. Existing methods typically involve training separate models for specific combinations of objectives, leading to computational and scalability issues. In this work, we aim to develop a new dialogue policy method that can adapt to varying objective preferences at inference time without retraining. This raises several challenges in terms of both (1) optimization strategy and (2) knowledge utilization. To address these, we propose a novel learning framework, Preference Adaptive Dialogue Policy Planner (PADPP), for multi-objective goal-oriented dialogues. Specifically, to tackle the former, we introduce a novel policy optimization scheme, which leverages information gained from training the model on previously updated objective weights, accelerating the learning capability on new weight settings. To address the latter, we utilize Generalized Policy Improvement (GPI) to ensure the effectiveness of leveraged knowledge. Experimental results demonstrate that PADPP achieves superior adaptability and performance compared to state-of-the-art approaches, offering a scalable and flexible solution for multi-objective, goal-oriented dialogues. Code and data are available at the anonymous link."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dao-liao-2025-one">
<titleInfo>
<title>One Planner To Guide Them All ! Learning Adaptive Conversational Planners for Goal-oriented Dialogues</title>
</titleInfo>
<name type="personal">
<namePart type="given">Huy</namePart>
<namePart type="given">Quang</namePart>
<namePart type="family">Dao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lizi</namePart>
<namePart type="family">Liao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Christos</namePart>
<namePart type="family">Christodoulopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carolyn</namePart>
<namePart type="family">Rose</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Violet</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-332-6</identifier>
</relatedItem>
<abstract>Goal-oriented dialogues, such as recommendation and negotiation, often require balancing multiple, conflicting objectives. Existing methods typically involve training separate models for specific combinations of objectives, leading to computational and scalability issues. In this work, we aim to develop a new dialogue policy method that can adapt to varying objective preferences at inference time without retraining. This raises several challenges in terms of both (1) optimization strategy and (2) knowledge utilization. To address these, we propose a novel learning framework, Preference Adaptive Dialogue Policy Planner (PADPP), for multi-objective goal-oriented dialogues. Specifically, to tackle the former, we introduce a novel policy optimization scheme, which leverages information gained from training the model on previously updated objective weights, accelerating the learning capability on new weight settings. To address the latter, we utilize Generalized Policy Improvement (GPI) to ensure the effectiveness of leveraged knowledge. Experimental results demonstrate that PADPP achieves superior adaptability and performance compared to state-of-the-art approaches, offering a scalable and flexible solution for multi-objective, goal-oriented dialogues. Code and data are available at the anonymous link.</abstract>
<identifier type="citekey">dao-liao-2025-one</identifier>
<location>
<url>https://aclanthology.org/2025.emnlp-main.1123/</url>
</location>
<part>
<date>2025-11</date>
<extent unit="page">
<start>22103</start>
<end>22127</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T One Planner To Guide Them All ! Learning Adaptive Conversational Planners for Goal-oriented Dialogues
%A Dao, Huy Quang
%A Liao, Lizi
%Y Christodoulopoulos, Christos
%Y Chakraborty, Tanmoy
%Y Rose, Carolyn
%Y Peng, Violet
%S Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing
%D 2025
%8 November
%I Association for Computational Linguistics
%C Suzhou, China
%@ 979-8-89176-332-6
%F dao-liao-2025-one
%X Goal-oriented dialogues, such as recommendation and negotiation, often require balancing multiple, conflicting objectives. Existing methods typically involve training separate models for specific combinations of objectives, leading to computational and scalability issues. In this work, we aim to develop a new dialogue policy method that can adapt to varying objective preferences at inference time without retraining. This raises several challenges in terms of both (1) optimization strategy and (2) knowledge utilization. To address these, we propose a novel learning framework, Preference Adaptive Dialogue Policy Planner (PADPP), for multi-objective goal-oriented dialogues. Specifically, to tackle the former, we introduce a novel policy optimization scheme, which leverages information gained from training the model on previously updated objective weights, accelerating the learning capability on new weight settings. To address the latter, we utilize Generalized Policy Improvement (GPI) to ensure the effectiveness of leveraged knowledge. Experimental results demonstrate that PADPP achieves superior adaptability and performance compared to state-of-the-art approaches, offering a scalable and flexible solution for multi-objective, goal-oriented dialogues. Code and data are available at the anonymous link.
%U https://aclanthology.org/2025.emnlp-main.1123/
%P 22103-22127
Markdown (Informal)
[One Planner To Guide Them All ! Learning Adaptive Conversational Planners for Goal-oriented Dialogues](https://aclanthology.org/2025.emnlp-main.1123/) (Dao & Liao, EMNLP 2025)
ACL