发表机构
University of Oxford; National Institute of Information and Communications Technology; National Institute of Informatics（牛津大学; 国立信息与通信技术研究所; 国立信息学研究所）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究针对外语焦虑影响二语习得问题，提出基于欧洲共同语言参考标准的多智能体具身对话系统，通过“生成-评估-再生”循环适配用户水平。小样本试点研究表明该系统生成的对话句子更适配学习者，虽未显著降低焦虑，但提供了相关见解。
AI 中文摘要
外语焦虑是二语习得的主要障碍，尤其是在对话情境中。随着大语言模型在生活各领域的普及，近期研究表明与大语言模型代理交互有助于二语习得和外语教育，特别是降低外语焦虑。相关研究还表明语言要求和任务复杂性是外语焦虑的预测因素。本文提出一种新颖的多智能体具身对话系统，为英语学习者生成水平适配的对话。该系统基于欧洲共同语言参考标准定义的水平，通过“生成-评估-再生”循环和多个大语言模型代理及水平分类器，实现适应用户熟练程度的简单性。我们还分享了一项初步小样本试点研究的结果，该研究用日本大学生测试了该系统，看其是否比未简化的具身对话代理产生更低的外语焦虑水平。对话输出分析表明，所提出的多智能体系统生成的87.4%的对话句子落在学习者自我评估熟练程度预测的欧洲共同语言参考标准水平内，而未简化代理为54.1%。这表明新系统能更好地为学习者生成适当水平的输出。尽管本研究未产生该系统降低日本英语学习者外语焦虑水平的统计学显著证据，但提供了可用性发现和文化相关设计见解，为未来研究提供参考。
英文摘要
Foreign language anxiety (FLA) can be a major barrier to second language acquisition (SLA), especially in conversational contexts. With the proliferation of large language models (LLMs) throughout all areas of life, recent work suggests that interacting with LLM agents can be instrumental within the field of SLA and foreign language education, especially for reducing FLA. Related work also suggests that linguistic demands and task complexity can be predictors of FLA, implying that the use of demanding, complex language could lead to learners experiencing higher FLA. In this paper, we propose a novel multi-agent embodied conversational system that generates level-appropriate dialogue for English language learners. These levels are based on those defined by the Common European Framework of Reference for Languages (CEFR) to describe non-native listener and speaker proficiency. Using a "generate-evaluate-regenerate" loop with multiple LLM agents and a level classifier, it achieves a desired simplicity that is adaptive to the user's proficiency level. We also share the results of a preliminary small-sample pilot study that tested this system with Japanese university students, to see whether it would yield lower FLA levels than an unsimplified embodied conversational agent. Analysis of conversational output showed that 87.4% of dialogue sentences generated by the proposed multi-agent system fell within one predicted CEFR level of the learner's self-assessed proficiency, compared to 54.1% for the unsimplified agent. This suggests that the novel system is better able to produce output at an appropriate level for the learner. Though this study did not yield statistically significant evidence that the system reduces FLA levels in Japanese learners of English, likely due to a small sample size, it provides usability findings and culturally-informed design insights that will inform future study.
Comments8 pages, 6 figures, published in the proceedings of EDULEARN26
Journal refK. Rajaratnam, W. Gan, Y. Sun (2026) TOWARDS REDUCING FOREIGN LANGUAGE ANXIETY USING LEVEL-APPROPRIATE EMBODIED CONVERSATIONAL AGENTS, EDULEARN26 Proceedings, Article 1459
DOI：10.21125/edulearn.2026.1459
