Towards Reducing Foreign Language Anxiety Using Level-Appropriate Embodied Conversational Agents

arXiv cs.CL Papers
foreign-language-anxiety second-language-acquisition embodied-conversational-agents large-language-models cefr multi-agent-system education

Summary

This paper proposes a multi-agent embodied conversational system that generates level-appropriate dialogue for English learners using a generate-evaluate-regenerate loop with LLMs and a CEFR classifier. A pilot study with Japanese university students showed improved level appropriateness but no statistically significant reduction in foreign language anxiety.

arXiv:2607.21887v1 Announce Type: cross Abstract: 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.
Original Article
View Cached Full Text

Cached at: 07/27/26, 07:42 AM 

# Towards Reducing Foreign Language Anxiety Using Level-Appropriate Embodied Conversational Agents
Source: [https://arxiv.org/abs/2607.21887](https://arxiv.org/abs/2607.21887)
[View PDF](https://arxiv.org/pdf/2607.21887)

> Abstract: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\.

## Submission history

From: Krishan Rajaratnam \[[view email](https://arxiv.org/show-email/d3b4d86a/2607.21887)\] **\[v1\]**Fri, 24 Jul 2026 01:31:13 UTC \(423 KB\)

Similar Articles

LectūraAgents: A Multi-Agent Framework for Adaptive Personalized AI-Assisted Learning and Embodied Teaching

Hugging Face Daily Papers

LectūraAgents is a multi-agent framework for adaptive personalized learning that mimics professor-student interactions and generates embodied teaching actions aligned with learner profiles. It introduces a hierarchical architecture, an adaptive embodied teaching mechanism, and a Teaching Action-Speech Alignment algorithm, showing consistent improvements over existing approaches.

Adversarial Stress Testing of Role-Playing Language Agents using Multi-Agent Evaluation

arXiv cs.AI

This paper presents a modular multi-agent platform for adversarially stress-testing role-playing language agents, using a strategy-driven Interrogator Agent and automated Judging Agent to reveal cumulative behavioral failures across multi-turn dialogues. Experiments across three personas and LLM families show multi-strategy adversarial evaluation reduces robustness scores by 0.17-0.20 and identifies common failure patterns, with strong human alignment.

Evaluating multimodal emotion recognition in proactive conversational agents: A user study

arXiv cs.AI

This paper presents a multimodal emotion recognition module for proactive conversational agents, using facial recognition and linguistic analysis. A user study with 20 participants reveals a 'poker face' effect where visual cues are unreliable, while linguistic analysis proves more accurate; the study also shows agents can elicit emotions through conversational adaptation.