Designing Large Language Model-Based Agents with the 5E Framework for ESL Learners' Grammar Acquisition

Overview

Yang, Weng, and Yang investigate how LLM-based agents can support English as a Second Language (ESL) learners in acquiring grammar. They designed two AI agents — one acting as a conventional English teacher and another using the 5E framework (engage, explore, explain, elaborate, evaluate) for inquiry-based learning. Thirty-seven ESL students were randomly divided between the two agent conditions, with pre- and post-tests and interviews used to examine intrinsic motivation, cognitive change, and performance.

Key Findings

• High-performing students responded positively to the AI teacher, benefiting from the structured support it provided.
• Low-performing students exhibited mixed attitudes, suggesting that LLM-based grammar agents are not uniformly effective across proficiency levels.
• The study reports differences in intrinsic motivation, cognitive change, and performance transformation between the conventional and 5E-framework agent conditions.
• Findings point to the importance of matching agent design (e.g., 5E inquiry Scaffolding) to learner needs and proficiency.

Implications for Practice

• For language teachers: LLM agents can supplement grammar instruction, but their design (conventional vs. inquiry-based 5E) should be chosen based on learner proficiency and goals.
• For tool designers: Inquiry-based scaffolds such as the 5E framework can shape agent behavior, but low-proficiency learners may need more structured or adaptive support.
• For researchers: The differential response of high- and low-performing learners highlights the need to examine learner-by-design interactions in LLM tutoring.

Connected Concepts

• LLM
• Language Learning
• Inquiry Based Learning
• Conversational AI

Connected Articles

• Tact Pedagogically Adaptive Esl Tutoring — pedagogically adaptive ESL tutoring
• Gpt Item Generation L2 Listening 2026 — LLM item generation for L2 listening assessment (Aryadoust & Wong 2026)
• Isaza Chatgpt Engineering Prompting 2026 — prompt engineering for LLM use in education

Citation

Designing large language model-based agents with 5E framework for ESL learners' grammar acquisition — Yang, X., Weng, X., & Yang, M. (2026). Computers and Education: Artificial Intelligence, 10, 100604.