Saved in:
Bibliographic Details
Main Authors: Xu, Jingyi, Ren, Xingyu, Shou, Zhoupeng, Zhang, Yumeng, You, Zhiqiang
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2602.15854
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918347021484032
author Xu, Jingyi
Ren, Xingyu
Shou, Zhoupeng
Zhang, Yumeng
You, Zhiqiang
author_facet Xu, Jingyi
Ren, Xingyu
Shou, Zhoupeng
Zhang, Yumeng
You, Zhiqiang
contents Large language models show potential in task-oriented dialogue systems, yet existing training methods often rely on token-level likelihood or preference optimization, which poorly align with long-horizon task success. To address this, we propose Goal-Oriented Preference Optimization (GOPO), a hierarchical reinforcement learning framework that decouples strategy planning from response generation via an Expert Agent and a Customer Service Agent. The Expert Agent optimizes multi-turn goal preferences at the dialogue-trajectory level, while the Customer Service Agent generates responses strictly aligned with the selected strategy. We evaluate GOPO on public benchmarks and e-commerce customer service datasets, and introduce Task-focused Sequential Engagement (TSE), a sequence-level metric derived from real e-commerce interaction data. On the Mgshop dataset, GOPO improves TSE by 7.7% and 10.3% over PPO and Memento, with consistent gains in sequence-level reward and generation quality. Furthermore, a 14B model trained with GOPO achieves 2.7% and 1.5% higher TSE than Qwen-235B and GPT-5.2, respectively. Ablation studies confirm the Expert Agent's critical role in long-horizon optimization. GOPO demonstrates consistent improvements across other datasets as well. This work establishes a new paradigm for task-oriented dialogue systems in commercial scenarios, with code and datasets to be made public.
format Preprint
id arxiv_https___arxiv_org_abs_2602_15854
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Decoupling Strategy and Execution in Task-Focused Dialogue via Goal-Oriented Preference Optimization
Xu, Jingyi
Ren, Xingyu
Shou, Zhoupeng
Zhang, Yumeng
You, Zhiqiang
Computation and Language
Artificial Intelligence
Large language models show potential in task-oriented dialogue systems, yet existing training methods often rely on token-level likelihood or preference optimization, which poorly align with long-horizon task success. To address this, we propose Goal-Oriented Preference Optimization (GOPO), a hierarchical reinforcement learning framework that decouples strategy planning from response generation via an Expert Agent and a Customer Service Agent. The Expert Agent optimizes multi-turn goal preferences at the dialogue-trajectory level, while the Customer Service Agent generates responses strictly aligned with the selected strategy. We evaluate GOPO on public benchmarks and e-commerce customer service datasets, and introduce Task-focused Sequential Engagement (TSE), a sequence-level metric derived from real e-commerce interaction data. On the Mgshop dataset, GOPO improves TSE by 7.7% and 10.3% over PPO and Memento, with consistent gains in sequence-level reward and generation quality. Furthermore, a 14B model trained with GOPO achieves 2.7% and 1.5% higher TSE than Qwen-235B and GPT-5.2, respectively. Ablation studies confirm the Expert Agent's critical role in long-horizon optimization. GOPO demonstrates consistent improvements across other datasets as well. This work establishes a new paradigm for task-oriented dialogue systems in commercial scenarios, with code and datasets to be made public.
title Decoupling Strategy and Execution in Task-Focused Dialogue via Goal-Oriented Preference Optimization
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2602.15854