Behaviour Change Techniques (BCTs) are central to digital health interventions, yet selecting and delivering effective techniques remains challenging. Contextual bandits enable statistically grounded optimisation of BCT selection, while Large Language Models (LLMs) offer flexible, context-sensitive message generation. We conducted a 4-week study on physical activity motivation (N=54; 9 post-study interviews) that compared five daily messaging approaches: random templates, contextual bandit with templates, LLM generation, hybrid bandit+LLM, and LLM with interaction history. LLM-based approaches were rated substantially more helpful than templates, but no significant differences emerged among LLM conditions. Unexpectedly, bandit optimisation for BCTs selection yielded no additional perceived helpfulness compared with LLM-only approaches. Unconstrained LLMs focused heavily on a single BCT, whereas bandit systems enforced systematic exploration-exploitation across techniques. Quantitative and qualitative findings suggest contextual acknowledgement of user input drove perceived helpfulness. We contribute design suggestions for reflective AI health behaviour change systems that address a trade-off between structured exploration and generative autonomy.

翻译：行为改变技术（BCTs）是数字健康干预的核心，但如何选择并传递有效的技术仍具挑战性。情境化Bandit算法为BCT选择提供了基于统计的优化方法，而大型语言模型（LLMs）则能实现灵活且情境敏感的信息生成。我们开展了一项为期4周的身体活动动机研究（N=54；包含9次研究后访谈），比较了五种每日消息推送方式：随机模板、基于模板的情境化Bandit、LLM生成、Bandit+LLM混合模型，以及结合交互历史的LLM。基于LLM的方法在帮助性评分上显著高于模板方法，但不同LLM条件间未出现显著差异。出乎意料的是，与纯LLM方法相比，采用Bandit优化BCT选择并未带来额外的感知帮助性。无约束的LLM高度集中于单一BCT，而Bandit系统则强制实现了跨技术的系统性探索-利用平衡。定量与定性分析表明，对用户输入的情境化认知是驱动感知帮助性的关键因素。我们提出了反思性AI健康行为改变系统的设计建议，以应对结构化探索与生成自主性之间的权衡。