[论文解读] Hybrid LLM-Embedded Dialogue Agents for Learner Reflection: Designing Responsive and Theory-Driven Interactions

Paras Sharma, Yueping Sha+7 more|arXiv (Cornell University)|Feb 24, 2026

Intelligent Tutoring Systems and Adaptive Learning被引用 0

一句话总结

论文提出一个混合对话系统，将基于规则的 SRL-为基础框架与大语言模型（LLM）结合，在文化响应性机器人营地中引导学习者反思，取得更丰富的反思，但也存在重复与提示不匹配等问题。

ABSTRACT

Dialogue systems have long supported learner reflections, with theoretically grounded, rule-based designs offering structured scaffolding but often struggling to respond to shifts in engagement. Large Language Models (LLMs), in contrast, can generate context-sensitive responses but are not informed by decades of research on how learning interactions should be structured, raising questions about their alignment with pedagogical theories. This paper presents a hybrid dialogue system that embeds LLM responsiveness within a theory-aligned, rule-based framework to support learner reflections in a culturally responsive robotics summer camp. The rule-based structure grounds dialogue in self-regulated learning theory, while the LLM decides when and how to prompt deeper reflections, responding to evolving conversation context. We analyze themes across dialogues to explore how our hybrid system shaped learner reflections. Our findings indicate that LLM-embedded dialogues supported richer learner reflections on goals and activities, but also introduced challenges due to repetitiveness and misalignment in prompts, reducing engagement.

研究动机与目标

• 将反思以自我调节学习（SRL）理论为基础指导对话设计。
• 开发一个将基于规则的有限状态机与LLM驱动的提示生成器结合的混合对话系统。
• 在确保教学对齐与安全的前提下实现情境感知提示。
• 探讨结构与AI响应性如何影响中学生在机器人营中的反思。

提出的方法

• 设计一个两阶段混合架构：基于SRL的基于规则的有限状态机（FSM）以及促使更深层次反思的LLM。
• 实现一个两阶段的LLM过程：先进行相关性检查以判断学习者的回答是否需要扩展，如需要则进行有针对性的生成。
• 使用少量示例提示和动态字段信息来引导LLM的相关性判断和情境跟进。
• 将LLM参与限制在跟进阶段；保留理论提示以维持教学意图。
• 在一个为期两周、具有文化响应性的机器人夏令营中对中学生学习者进行部署。
• 通过对话的定性分析和互动后访谈进行评估，以识别反思内容与参与问题。

Figure 1 . This diagram depicts our hybrid dialogue system architecture modeled as a Finite State Machine and illustrates how logic flows across the rule-based prompts, learner responses, and conditional transitions at each system-learner turn.

实验结果

研究问题

• RQ1 RQ1：在开放式环境中，我们的方法在哪些方面有效地促发了中学生学习者的反思？
• RQ2 RQ2：促进进一步反思的机会有哪些？
• RQ3 RQ3：学习者对 reflective 对话的感知如何？

主要发现

• 嵌入LLM的对话支持了对学习者目标与活动的更详细的反思。
• 在学习者表达目标/计划时，情境一致的提示提升了反思的深度。
• 重复性提示与情境或情感不匹配导致参与度下降。
• 混合设计在保持理论基础的同时实现了响应性跟进。
• 进行了三轮迭代以调整提示与提示引导以确保情境相关性。
• 学习者欣赏系统的鼓励，且参与度随提示质量的不同而异。

Figure 2 . The two stages of LLM in our dialogue system: (1) Relevance Check, where a dynamic prompt with prompt-specific information and few-shot examples determines binary relevance; and (2) Contextual Generation, where, upon a NO in relevance check, a new prompt incorporating prompt-specific info