Large language models (LLMs) produce responses rated as highly empathic in single-turn settings (Ayers et al., 2023; Lee et al., 2024), yet they are also known to be formulaic generators that reuse the same lexical patterns, syntactic templates, and discourse structures across tasks (Jiang et al., 2025; Shaib et al., 2024; Namuduri et al., 2025). Less attention has been paid to whether this formulaicity extends to the level of discourse moves, i.e., what a response does for the person it is addressing. This question is especially consequential for empathic dialogue, where effective support demands not just a kind response at one moment but varied strategies as a conversation unfolds (Stiles et al., 1998). Indeed, prior work shows that LLMs reuse the same tactic sequences more than human supporters in single-turn settings (Gueorguieva et al., 2026). We extend this analysis to multi-turn conversations and find that the rigidity compounds: once a tactic appears in a supporter turn, LLMs reuse it in the next at nearly double the rate of humans (0.50-0.56 vs. 0.27). This pattern holds across LLMs serving as supporters in real emotional support conversations, and is invisible to standard similarity metrics. To address this gap, we introduce MINT (Multi-turn Inter-tactic Novelty Training), the first reinforcement learning framework to optimize discourse move diversity across multi-turn empathic dialogue. The best MINT variant combines an empathy quality reward with a cross-turn tactic novelty signal, improving aggregate empathy by 25.3% over vanilla across 1.7B and 4B models while reducing cross-turn discourse move repetition by 26.3% on the 4B model, surpassing all baselines including quality-only and token-level diversity methods on both measures. These results suggest that what current models lack is not empathy itself, but the ability to vary their discourse moves across a conversation.

翻译：大型语言模型（LLMs）在单轮对话中生成被认为高度共情的回应（Ayers等，2023；Lee等，2024），但已知它们也是公式化生成器，跨任务重复使用相同的词汇模式、句法模板和话语结构（Jiang等，2025；Shaib等，2024；Namuduri等，2025）。然而，这种公式化是否延伸至话语行为层面（即回应为对话对象所执行的功能）尚未得到充分关注。这一问题对于共情对话尤为关键，因为有效的支持不仅要求在某一时刻给予友善回应，更需要在对话展开过程中采用多样化的策略（Stiles等，1998）。事实上，先前研究表明，在单轮对话中，LLMs比人类支持者更频繁地重复使用相同策略序列（Gueorguieva等，2026）。我们将此分析扩展至多轮对话，并发现其僵化性会加剧：一旦某种策略出现在支持者的对话轮次中，LLMs在下一轮重复使用该策略的频率几乎是人类的两倍（0.50-0.56对0.27）。这一模式在真实情感支持对话中由LLMs担任支持者时普遍存在，且对标准相似度指标不可见。为填补这一空白，我们提出MINT（多轮跨策略新颖性训练），这是首个旨在优化多轮共情对话中话语行为多样性的强化学习框架。最佳MINT变体将共情质量奖励与跨轮策略新颖性信号相结合，在1.7B和4B参数规模模型上将整体共情质量较原始模型提升25.3%，同时将4B模型的跨轮话语行为重复率降低26.3%，在两项指标上均超越了包括仅考虑质量方法和词级多样性方法在内的所有基线。这些结果表明，当前模型所欠缺的并非共情本身，而是在对话中变化其话语行为的能力。