Skip to main content
QUICK REVIEW

[论文解读] Exploring Learners' Expectations and Engagement When Collaborating with Constructively Controversial Peer Agents

Thitaree Tanprasert, Young‐Ho Kim|arXiv (Cornell University)|Jan 20, 2026
Innovative Teaching and Learning Methods被引用 0
一句话总结

本文研究在异步协作中,受监管与非受监管的基于 CC 的行为以及对代理设计透明度的影响,如何影响学习者参与度、自主感知与在与基于 LLM 的同伴代理协作时的感知。

ABSTRACT

Peer agents can supplement real-time collaborative learning in asynchronous online courses. Constructive Controversy (CC) theory suggests that humans deepen their understanding of a topic by confronting and resolving controversies. This study explores whether CC's benefits apply to LLM-based peer agents, focusing on the impact of agents' disputatious behaviors and disclosure of agents' behavior designs on the learning process. In our mixed-method study (n=144), we compare LLMs that follow detailed CC guidelines (regulated) to those guided by broader goals (unregulated) and examine the effects of disclosing the agents' design to users (transparent vs. opaque). Findings show that learners' values influence their agent interaction: those valuing control appreciate unregulated agents' willingness to cease push-back upon request, while those valuing intellectual challenges favor regulated agents for stimulating creativity. Additionally, design transparency lowers learners' perception of agents' abilities. Our findings lay the foundation for designing effective collaborative peer agents in isolated educational settings.

研究动机与目标

  • 检查基于 CC 的行为是否能在异步协作中提升学习效果。
  • 研究受监管与非受监管的 CC 行为对参与度、自主感知和协作动力学的影响。
  • 评估是否披露代理行为设计(透明 vs 不透明)对这些影响的调节作用。
  • 识别学习者在应对基于 CC 的同伴代理时的价值取向与策略。
  • 为在孤立教育情境中实现高效的基于 LLM 的协同同伴代理提供设计见解。

提出的方法

  • 进行一个 2 x 2 混合因子实验,144 名本科生在论证任务轮次中与基于 CC 的同伴代理互动。
  • 比较非受监管(高层 CC 指南,可由 LLM 灵活适应)与受监管(严格 CC 指南,受管控)行为。
  • 将代理设计透明度(透明 vs 不透明)作为一个 between-subject 因子进行操控。
  • 结合对话分析、任务指标(回合数、字数、完成时间、论证质量)以及对参与度和自主感知的自我报告。
  • 收集开放式调查以捕捉关于学习者价值观与期望的定性见解(子研究问题1)。
Figure 1. A summary diagram of the study procedure. After watching the experiment demo video, each participant completes two rounds of the task for the two behavior mechanisms (regulated and unregulated) with a 5-minute break in between. The dashed-border box shows the steps within each round. Note
Figure 1. A summary diagram of the study procedure. After watching the experiment demo video, each participant completes two rounds of the task for the two behavior mechanisms (regulated and unregulated) with a 5-minute break in between. The dashed-border box shows the steps within each round. Note

实验结果

研究问题

  • RQ1Sub-RQ1: 学习者的价值观与期望有哪些,会影响他们对基于 CC 的同伴代理的感知与互动?
  • RQ2Sub-RQ2: 受监管与非受监管的 CC 行为如何影响参与度、自主感知与协作动力学?
  • RQ3Sub-RQ3: 是否披露或不披露代理的行为设计会如何调节这些影响?

主要发现

  • 学习者可分为以效率驱动(Efficiency-Driven)和好奇心驱动(Curiosity-Driven)两类,分别对应不同的协作策略和对 CC 行为的偏好。
  • 披露代理的行为设计会显著降低学习者对代理能力的整体感知。
  • 受监管的 CC 行为往往激发创造力并提供更具挑战性的参与,而非受监管的行为则提供与学习者控制相一致的灵活性。
  • 学习者的价值观会影响他们在代理互动中的合作与矛盾之间的偏好平衡。
  • 两种代理设计模式(受监管 vs 非受监管)以不同方式影响参与度、自主感知与协作动力学。
Figure 2. This figure shows the experiment interface (a). The screen is divided into three columns. The leftmost column is the activity instruction, including the task scenario, the activity steps, and the argument grading rubrics. The middle column is the chat window, where the participant has a co
Figure 2. This figure shows the experiment interface (a). The screen is divided into three columns. The leftmost column is the activity instruction, including the task scenario, the activity steps, and the argument grading rubrics. The middle column is the chat window, where the participant has a co

更好的研究,从现在开始

从阅读论文到最终审阅,大幅缩短您的研究时间。

无需绑定信用卡

本解读由 AI 生成,并经人工编辑审核。