Saved in:
Bibliographic Details
Main Authors: Wang, Hui, Zhang, Fafa, Zhang, Xiaoyu, Mu, Chaoxu
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2511.21706
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912731871838208
author Wang, Hui
Zhang, Fafa
Zhang, Xiaoyu
Mu, Chaoxu
author_facet Wang, Hui
Zhang, Fafa
Zhang, Xiaoyu
Mu, Chaoxu
contents In goal-oriented dialogue tasks, the main challenge is to steer the interaction towards a given goal within a limited number of turns. Existing approaches either rely on elaborate prompt engineering, whose effectiveness is heavily dependent on human experience, or integrate policy networks and pre-trained policy models, which are usually difficult to adapt to new dialogue scenarios and costly to train. Therefore, in this paper, we present Nested Rollout Policy Adaptation for Goal-oriented Dialogue (NRPA-GD), a novel dialogue policy planning method that completely avoids specific model training by utilizing a Large Language Model (LLM) to simulate behaviors of user and system at the same time. Specifically, NRPA-GD constructs a complete evaluation mechanism for dialogue trajectories and employs an optimization framework of nested Monte Carlo simulation and policy self-adaptation to dynamically adjust policies during the dialogue process. The experimental results on four typical goal-oriented dialogue datasets show that NRPA-GD outperforms both existing prompt engineering and specifically pre-trained model-based methods. Impressively, NRPA-GD surpasses ChatGPT and pre-trained policy models with only a 0.6-billion-parameter LLM. The proposed approach further demonstrates the advantages and novelty of employing planning methods on LLMs to solve practical planning tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2511_21706
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A General Highly Accurate Online Planning Method Integrating Large Language Models into Nested Rollout Policy Adaptation for Dialogue Tasks
Wang, Hui
Zhang, Fafa
Zhang, Xiaoyu
Mu, Chaoxu
Computation and Language
Artificial Intelligence
In goal-oriented dialogue tasks, the main challenge is to steer the interaction towards a given goal within a limited number of turns. Existing approaches either rely on elaborate prompt engineering, whose effectiveness is heavily dependent on human experience, or integrate policy networks and pre-trained policy models, which are usually difficult to adapt to new dialogue scenarios and costly to train. Therefore, in this paper, we present Nested Rollout Policy Adaptation for Goal-oriented Dialogue (NRPA-GD), a novel dialogue policy planning method that completely avoids specific model training by utilizing a Large Language Model (LLM) to simulate behaviors of user and system at the same time. Specifically, NRPA-GD constructs a complete evaluation mechanism for dialogue trajectories and employs an optimization framework of nested Monte Carlo simulation and policy self-adaptation to dynamically adjust policies during the dialogue process. The experimental results on four typical goal-oriented dialogue datasets show that NRPA-GD outperforms both existing prompt engineering and specifically pre-trained model-based methods. Impressively, NRPA-GD surpasses ChatGPT and pre-trained policy models with only a 0.6-billion-parameter LLM. The proposed approach further demonstrates the advantages and novelty of employing planning methods on LLMs to solve practical planning tasks.
title A General Highly Accurate Online Planning Method Integrating Large Language Models into Nested Rollout Policy Adaptation for Dialogue Tasks
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2511.21706