arXiv:2602.15854cs.CLcs.AI2026-02

用分层强化学习让对话模型更懂长期任务目标

Decoupling Strategy and Execution in Task-Focused Dialogue via Goal-Oriented Preference Optimization

  • 拆分策略规划与回复生成,分别由专家代理和客服代理负责
  • 在电商对话数据集上,序列级任务完成率提升7.7%至10.3%
  • 适合需要长流程任务执行的商业对话系统研发者

大语言模型在任务导向对话系统中展现出潜力,但现有训练方法多依赖词元级似然或偏好优化,难以对齐长周期任务成功。为此,我们提出面向目标的偏好优化(GOPO),一种分层强化学习框架,通过专家代理与客服代理解耦策略规划与响应生成。专家代理在对话轨迹层面优化多轮目标偏好,客服代理则严格遵循选定策略生成回复。我们在公开基准和电商客服数据集上评估了GOPO,引入基于真实电商交互数据的序列级指标TSE。在Mgshop数据集上,GOPO相较PPO和Memento分别提升TSE 7.7%和10.3%,且在序列级奖励与生成质量上持续领先。此外,使用GOPO训练的14B模型在TSE上分别高于Qwen-235B和GPT-5.2达2.7%和1.5%。消融实验验证了专家代理在长周期优化中的关键作用。GOPO在其他数据集上也表现一致优异。本工作为商业场景下的任务导向对话系统建立了新范式,代码与数据集将公开。

原文摘要 · Abstract (English)

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.

对话系统强化学习任务导向电商对话

Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品;中文卡片由大模型生成,请以原文为准。