arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2602.19303cs.HC
收藏

对话式AI助教的路径:整合辅导最佳实践和定向技术以产生可扩展的AI代理

The Path to Conversational AI Tutors: Integrating Tutoring Best Practices and Targeted Technologies to Produce Scalable AI Agents

Cornell University(康奈尔大学);University of Adelaide(阿德莱德大学);University of Florida(佛罗里达大学);Digital Promise(数字承诺)

Kirk Vanacore, Ryan S. Baker, Avery H. Closser, Jeremy Roschelle

AI总结:

本文探讨了通过整合辅导最佳实践和生成式AI技术,开发可扩展且有效的对话式AI助教的研究路径。

摘要:

生成式AI的出现加速了能够通过自然语言对话与学生互动的对话式辅导系统的发展。与以往的智能辅导系统(ITS)不同,后者主要作为具有反馈和提示的自适应和互动问题集,对话式助教有潜力通过实时与学生的思维、问题和误解互动来模拟高质量的人类辅导。虽然一些先前的ITS,如AutoTutor,能够进行对话式回应,但其作者成本高且缺乏全面的对话能力。生成式AI改变了ITS进行对话的能力。然而,实现对话式助教的全部潜力需要仔细考虑已有的人类辅导和ITS研究,同时也要分解出新的研究需求。本文综合了成功的辅导方法、从传统ITS中获得的经验教训以及对话式AI助教的新研究。我们使用一个“保持、改变、聚焦、研究”的框架来指导对话式辅导的设计。我们主张系统应保留来自先前ITS的已证明方法,如知识追踪和情感检测;通过利用生成式AI进行动态内容生成和对话支架改变辅导的交付方式;并聚焦意义建构、学生自主性和推理的细粒度诊断的机会。最后,我们确定了需要进一步研究的领域,包括有效性测试、学生体验以及与人类教学的整合。通过综合人类辅导、传统ITS和新兴生成式AI技术的洞察,本文概述了开发可扩展、教学有效的且能响应学习的社会和动机维度的对话式助教的研究议程。

英文摘要:

The emergence of generative AI has accelerated the development of conversational tutoring systems that interact with students through natural language dialogue. Unlike prior intelligent tutoring systems (ITS), which largely function as adaptive and interactive problem sets with feedback and hints, conversational tutors hold the potential to simulate high-quality human tutoring by engaging with students' thoughts, questions, and misconceptions in real time. While some previous ITS, such as AutoTutor, could respond conversationally, they were expensive to author and lacked a full range of conversational ability. Generative AI has changed the capacity of ITS to engage conversationally. However, realizing the full potential of conversational tutors requires careful consideration of what research on human tutoring and ITS has already established, while also unpacking what new research will be needed. This paper synthesizes tenets of successful human tutoring, lessons learned from legacy ITS, and emerging work on conversational AI tutors. We use a keep, change, center, study framework for guiding the design of conversational tutoring. We argue that systems should keep proven methods from prior ITS, such as knowledge tracing and affect detection; change how tutoring is delivered by leveraging generative AI for dynamic content generation and dialogic scaffolding; and center opportunities for meaning-making, student agency, and granular diagnosis of reasoning. Finally, we identify areas requiring further study, including efficacy testing, student experience, and integration with human instruction. By synthesizing insights from human tutoring, legacy ITS, and emerging generative AI technologies, this paper outlines a research agenda for developing conversational tutors that are scalable, pedagogically effective, and responsive to the social and motivational dimensions of learning.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑