训练对话式辅导智能体的逐轮验证器：大语言模型作为编程辅导者的有趣案例
Training Turn-by-Turn Verifiers for Dialogue Tutoring Agents: The Curious Case of LLMs as Your Coding Tutors
AI总结：
针对LLM辅导智能体在复杂任务引导上的不足，提出结合知识追踪与逐轮验证的TRAVER工作流，并通过DICT协议验证其在编程辅导中显著提升成功率，且方法可推广至其他领域。
摘要：
由大语言模型（LLM）驱动的智能辅导智能体在语言学习和科学教育等领域中提供个性化知识方面得到了越来越多的探索。然而，它们在引导用户解决复杂的现实世界任务方面的能力仍未得到充分研究。为了解决这一局限性，在这项工作中，我们聚焦于编程辅导这一具有挑战性的问题，它要求辅导者主动引导学生完成预定义的编程任务。我们提出了一种新颖的智能体工作流，即追踪与验证（TRAVER），它结合了知识追踪来估计学生的知识状态，以及逐轮验证来确保对任务完成的有效引导。我们引入了DICT，一种自动评估协议，它使用受控的学生模拟和代码生成测试来评估辅导智能体。大量实验揭示了编程辅导的挑战，并证明TRAVER实现了显著更高的成功率。尽管本文以编程辅导为例，但我们的方法可以扩展到编程之外，为推进用于人类任务学习的辅导智能体提供有价值的见解。
英文摘要：
Intelligent tutoring agents powered by large language models (LLMs) have been increasingly explored to deliver personalized knowledge in areas such as language learning and science education. However, their capabilities in guiding users to solve complex real-world tasks remain underexplored. To address this limitation, in this work, we focus on coding tutoring, a challenging problem that requires tutors to proactively guide students towards completing predefined coding tasks. We propose a novel agent workflow, Trace-and-Verify (TRAVER), which combines knowledge tracing to estimate a student's knowledge state and turn-by-turn verification to ensure effective guidance toward task completion. We introduce DICT, an automatic evaluation protocol that assesses tutor agents using controlled student simulation and code generation tests. Extensive experiments reveal the challenges of coding tutoring and demonstrate that TRAVER achieves a significantly higher success rate. Although we use code tutoring as an example in this paper, our approach can be extended beyond coding, providing valuable insights into advancing tutoring agents for human task 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。
