Volume 30 Number 1, 2026 Promoting revision in L2 writing: A mixed-methods study on the role of specialized AI feedback agents

Promoting revision in L2 writing: A mixed-methods study on the role of specialized AI feedback agents

Repository record updated on:
July 29, 2026, 1:02 p.m.
Database record updated on:
July 31, 2026, 5:40 p.m.
Last Harvested on:
July 31, 2026, 5:40 p.m.
access-status:
open.access
bitstream:
[['https://scholarspace.manoa.hawaii.edu/bitstreams/f20d2e89-2d41-41d3-b9d8-3804953591ca/download', '30_01_10125-73705.pdf']]
bitstream_txt:
[['https://scholarspace.manoa.hawaii.edu/bitstreams/dd550c0a-0adc-42da-9249-08322584a8cc/download', 'full_text']]
collection:
Volume 30 Number 1, 2026
contributor.author:
Park, Yujong Ryoo, Jeeho
date.accessioned:
2026-07-29T11:30:34Z
date.available:
2026-07-29T11:30:34Z
date.copyright:
2026
date.issued:
2026-07-30
description.abstract:
Standard generative AI interfaces allow L2 learners to bypass cognitively demanding writing processes by generating complete texts with minimal effort. This study examines whether embedding pedagogical constraints within AI interface design can reshape learner engagement with the revision process in L2 writing. We developed Writing Helper, a multi-agent system that structures iterative revision through four specialized feedback agents (Grammar, Style, Structure, Content) and gamified mastery thresholds. In a quasi-experimental study, 45 Korean university EFL learners completed a creative writing task using either standard AI chatbots (Control, n = 18) or the agentic AI system (Experimental, n = 27). Behavioral analysis revealed that control participants followed largely linear workflows (M = 2.1 iterations), while experimental participants engaged in significantly more revision cycles (M = 6 iterations), producing longer texts (M = 150 vs. 48 words) with higher ratings for narrative elaboration. Qualitative findings indicated that learners valued the structured revision process and expressed willingness to reuse the system, yet reported that higher-order feedback lacked specificity, and inconsistent scoring raised concerns about trust. These findings reveal both the promise and challenges of using constraint-based, agentic AI design in L2 writing classrooms, highlighting the importance of pedagogical interface design.
endingpage:
20
format.extent:
20
identifier.citation:
Park, Y., & Ryoo, J. (2026). Promoting revision in L2 writing: A mixed-methods study on the role of specialized AI feedback agents. Language Learning & Technology, 30(1), 1–20. https://doi.org/10.64152/10125/73705
identifier.doi:
https://doi.org/10.64152/10125/73705
identifier.issn:
1094-3501
identifier.uri:
https://hdl.handle.net/10125/73705
language:
eng
number:
1
publicationname:
Language Learning & Technology
publisher:
University of Hawaii National Foreign Language Resource Center Center for Language & Technology
rights.license:
Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License
rights.uri:
https://creativecommons.org/licenses/by-nc-nd/4.0/
site_url:
/item/10125-73705/
startingpage:
1
subject:
generative AI, L2 writing, constraint-based design, agentic AI, educational technology
title:
Promoting revision in L2 writing: A mixed-methods study on the role of specialized AI feedback agents
type:
Article Text
volume:
30