1　Introduction

The transformative impact of Generative Artificial Intelligence (GAI) on the foreign language education ecosystem, noting that GAI Chatbots provide technical support for teaching through instant interaction, multilingual recognition, and multimodal generation, driving instruction toward personalization, immediacy, and contextualization. On this basis, it is proposed that foreign language education needs to break through monolingual discourse patterns and respect learners' individual needs. Addressing the problem of limited learner agency in traditional teaching, this section clarifies how GAI can expand translanguaging spaces and stimulate learners' subjective agency, pointing out the research gap regarding insufficient attention to learners' translanguaging practices and their agency manifestations, thereby establishing that this study focuses on domestic English Medium Instruction (EMI) classrooms to explore how students engage in translanguaging practices through GAI Chatbots and the characteristics of their agency.

2　Literature Review

Three core themes are reviewed: translanguaging theory has evolved from describing bilingual phenomena to a critical theory, emphasizing language as a dynamic multimodal repertoire that facilitates integrated language and content learning in EMI classrooms, though its application remains controversial in academic circles; learner agency possesses characteristics of sociocultural mediation and situatedness, with diversified mediational resources promoting its development, while research on integration with information technology remains in the exploratory stage; GAI's multilingual and multimodal characteristics are highly compatible with translanguaging, capable of supporting learners' autonomous translanguaging practices, opening up non-teacher-led learning spaces, and promoting personalized learning processes and stimulating agency, yet how to effectively realize its educational potential still requires classroom-based empirical investigation.

3　Research Design

A four-month research design in an EMI course at a certain university, organized around two core questions: the ways of translanguaging practices in learners' interactions with GAI Chatbots, and the forms of learner agency manifested in classroom activities. The research subjects were 50 undergraduate students, with three types of qualitative data collected across four classroom activities—approximately 550,000 words of human-computer interaction records, 40 open-ended feedback responses, and 28 reflective journals. Data analysis employed thematic analysis, using deductive-inductive hybrid coding for research question (1) with "multilingual" and "multimodal" as preset frameworks for translanguaging analysis; for research question (2), inductive coding was conducted to extract agency characteristics from students' expressions of actively setting goals and mobilizing resources.

4　Findings and Discussion

The specific manifestations of translanguaging practices and the multidimensional characteristics of learner agency in English Medium Instruction (EMI) classrooms empowered by Generative Artificial Intelligence (GAI). At the multilingual interaction level, four phenomena were identified: language compensation—students using their native language to replace target language expressions for restricted content to ensure communicative coherence; terminology transfer—directly citing English professional terminology to maintain conceptual accuracy; emphasis highlighting—deliberately embedding foreign language adjectives or adverbs to intensify emotional and informational focus; cognitive simplification—unconsciously switching between languages to reduce cognitive load, aligning with the "cognitive miser" theory. At the multimodal resource utilization level, emojis serve emotional support functions, images carry local cultural elements, while video links and music expand communicative dimensions, with students achieving meaning construction through multimodal collaboration, such as directing GAI to generate bilingual poetry integrating Chaoshan cultural imagery. These translanguaging practices collectively constitute the "GAI translanguaging space," breaking through teacher-dominated models, weakening inequalities brought by language proficiency differences, and providing students with an equal and open autonomous learning environment that promotes integrated language and content learning.

Four dimensions of learner agency are also explored: autonomous planning and regulation—students setting learning plans according to personal goals and preferences and making dynamic adjustments; critical thinking and feedback—students examining and evaluating the applicability of GAI-generated content, questioning scoring deviations and proposing improvement suggestions; resource integration and utilization—students actively mobilizing mediational resources such as music, video, and games, even exploring multiple GAI tools to meet needs; situational awareness and adaptation—students keenly perceiving language and cultural differences and adjusting interaction strategies to adapt to specific communicative situations. These findings indicate that learners in GAI environments have transformed from passive information recipients to subjects of autonomous knowledge construction, providing theoretical expansion and practical reference for understanding agency development in technology-empowered education.

5　Conclusion

This study presents research findings from four activities integrating GAI Chatbots into EMI classrooms, revealing that they construct an open and inclusive GAI translanguaging space. In this space, students autonomously engage in translanguaging practices, demonstrating four types of multilingual interaction phenomena—language compensation, terminology transfer, emphasis highlighting, and cognitive simplification—and utilize multimodal resources for meaning construction; learner agency is manifested in four dimensions: autonomous planning and regulation, critical thinking and feedback, resource integration and utilization, and situational awareness and adaptation. Three pedagogical implications are proposed: utilizing the GAI translanguaging space to mitigate contradictions between EMI monolingual policies and practical needs, stimulating learner agency and establishing interactive archiving feedback mechanisms, and being vigilant against negative technological impacts while emphasizing the irreplaceability of human original capabilities. Finally, limitations are noted regarding the failure to measure subjects' language proficiency and the collection of only four qualitative data sessions, with longitudinal tracking studies recommended for future research.