通过交互学习用户偏好以实现长期协同

Learning User Preferences Through Interaction for Long-Term Collaboration

January 6, 2026

作者: Shuhaib Mehri, Priyanka Kargupta, Tal August, Dilek Hakkani-Tür

cs.AI

摘要

随着对话智能体在与用户协作过程中不断积累经验，适应不同用户偏好对于建立长期关系、持续提升协作质量至关重要。本文提出MultiSessionCollab基准测试，用于评估智能体在多轮会话中学习用户偏好并利用这些偏好提升协作质量的能力。为构建适用于该场景的智能体，我们开发了具备长期协作能力的智能体架构，其通过持续积累交互经验来维护并优化用户偏好记忆库。此外，我们证明可从MultiSessionCollab中的用户模拟器行为提取学习信号，用以训练智能体生成更全面的反思并更有效地更新记忆。大量实验表明，配备记忆模块的智能体能够显著提升长期协作效果，具体表现为任务成功率提高、交互效率提升以及用户操作负担减轻。最后，我们开展的人类用户研究证实，记忆机制在实际应用场景中能有效改善用户体验。

English

As conversational agents accumulate experience collaborating with users, adapting to user preferences is essential for fostering long-term relationships and improving collaboration quality over time. We introduce MultiSessionCollab, a benchmark that evaluates how well agents can learn user preferences and leverage them to improve collaboration quality throughout multiple sessions. To develop agents that succeed in this setting, we present long-term collaborative agents equipped with a memory that persists and refines user preference as interaction experience accumulates. Moreover, we demonstrate that learning signals can be derived from user simulator behavior in MultiSessionCollab to train agents to generate more comprehensive reflections and update their memory more effectively. Extensive experiments show that equipping agents with memory improves long-term collaboration, yielding higher task success rates, more efficient interactions, and reduced user effort. Finally, we conduct a human user study that demonstrates that memory helps improve user experience in real-world settings.