1　Introduction

This section elaborates on the background and significance of generative artificial intelligence (GenAI)-assisted second language (L2) writing research. As a core productive skill, L2 writing faces challenges such as untimely feedback and insufficient personalization, while GenAI offers new pathways to address these difficulties through its multiple functions including instant feedback and content ideation. Although existing research has confirmed its positive effects, most studies focus on effectiveness verification, with limited systematic discussion on embedding mechanisms and instructional structures. International reviews have formed relatively mature knowledge maps, but they are primarily based on English-language journals, making it difficult to present indigenous practices from the Chinese academic community; domestic existing reviews either cover too broad a scope or rely mainly on international journal samples, lacking systematic analysis focused on CSSCI achievements with L2 writing at the core. In view of this, this paper takes CSSCI journal articles as samples and conducts analysis from five dimensions: topic distribution, research design, AI roles, theoretical application, and Chinese context characteristics, aiming to reveal the topic structure and research orientation in the Chinese context, and to answer four research questions regarding publication trends, role positioning, theoretical characteristics, and localization performance, thereby providing structural reflection for subsequent research.

2　Literature Collection and Coding

This section describes the literature collection and coding methods for GenAI-assisted L2 writing research. Literature retrieval used CSSCI source journals from CNKI as the data source, with the time range set from November 30, 2022 to December 31, 2025. A keyword cross-combination strategy was adopted, and after manual verification, 34 valid articles were finally included. The coding framework comprises five layers: topic focus, research design and context, tool and interaction characteristics, theoretical application, and Chinese context, covering 12 coding dimensions and 21 coding variables. Among these, the topic focus layer and Chinese context layer were supplementary additions based on indigenous research characteristics. Coding work was completed jointly by two researchers, with pilot coding consistency reaching 92%; during formal coding, inconsistent items were discussed one by one until consensus was reached.

3　Research Results

This section presents the systematic literature analysis results of domestic generative artificial intelligence-assisted L2 writing research. Publication trends show that from 2023 to 2025, publications in this field rose rapidly, shifting from sporadic exploration to concentrated output, with results distributed across 17 CSSCI source journals, though no systematic review has yet emerged. Research foci can be clustered into three categories: human-computer interaction processes, writing text quality and teaching effects, and learners' individual psychological experiences, with text quality and teaching effects research accounting for over half, while human-computer interaction research comprises less than 20%. In terms of research design, empirical research accounts for 76.5%, with the paradigm shifting from value analysis to empirical verification; research subjects are highly concentrated in college English writing classrooms, with scarce evidence from other educational stages and languages; method selection presents problem-driven characteristics, with text analysis, quasi-experiments, and case studies as mainstream approaches; data levels are shifting from outcome data to process data, but interactive data collection rates remain relatively low. Regarding tool usage, ChatGPT dominates, with domestic large language model application proportions being low and mostly serving as substitutes; AI roles are primarily graders/feedback providers, with intervention concentrated in revision and evaluation stages, while insufficient support exists for front-end ideation and generation. Theoretical application levels show that nearly 60% of studies cite theoretical frameworks, mainly writing pedagogy, sociocultural theory, and learning engagement theory, but there is a lack of systematic integration among theories, and research on revising existing theories remains blank. In terms of localization concerns, studies generally respond to national policy discourse, confront indigenous teaching challenges, and reflect traditional educational concepts such as teacher dominance; some studies utilize Chinese L2 characteristics to form unique contributions, but deep development of domestic tools and research agenda construction still need advancement.

4　Discussion

This section systematically analyzes the core characteristics and deep limitations of domestic generative artificial intelligence-assisted L2 writing research. The study finds that this field has completed the paradigm transformation from value analysis to empirical verification, but there are significant deficiencies in sample structure, evidence form, theoretical application, and localization pathways. At the sample level, research is highly concentrated in college English classrooms, with limited generalizability across educational stages and languages; this pattern stems from the accessibility advantages of higher education settings combined with publication mechanisms, forming common characteristics with international research. Regarding process evidence, interactive data is relatively scarce, with research focusing more on "whether it is effective" rather than "how it works," constraining deep understanding of human-computer collaboration mechanisms; the shift from outcome verification to mechanism explanation becomes an important future direction. In role construction, GenAI is mostly positioned as a feedback tool in post-processing stages, continuing the research tradition of automated writing evaluation systems, with insufficient exploration of its potential as a cognitive partner throughout the entire process; dynamic role switching and strategy regulation mechanisms await exploration. Theoretical application presents a situation of progress and bottlenecks coexisting: although certain theoretical consciousness has been formed, it mostly remains at the stage of introduction and application, without achieving the leap to developing theories; the applicable boundaries of sociocultural theory and other human-computer interaction explanations still need clarification. Localization characteristics are reflected in the multiple embeddings of policy context, educational concepts, Chinese language context, and domestic tool ecology, but these factors currently serve mostly as background descriptions, not yet fully transformed into mechanism variables and theoretical resources; future efforts need to promote indigenous experience from situational description toward mechanism analysis and theoretical construction, to enhance the explanatory power of the Chinese context in academic dialogue.

5　Conclusion

This section summarizes the developmental trajectory and core characteristics of domestic GenAI-assisted L2 writing research: research has shifted from value exploration to empirical testing, with subjects concentrated on college English learners, focusing on feedback comparison, writing quality, and teaching effects, while human-computer interaction process research remains insufficient; GenAI mostly functions in the revision and evaluation stages at the back end of writing, with limited intervention in front-end ideation and middle-stage generation; theoretical application has strengthened but innovative integration remains limited. The research simultaneously demonstrates localization concerns, but factors such as policy context, educational concepts, language characteristics, and domestic tool ecology have not yet fully entered mechanism analysis. The authors note that the field is moving from effectiveness verification toward mechanism explanation, recommending expansion of basic education and non-English language samples, deepening examination of human-computer collaboration mechanisms through process data, and strengthening theoretical integration of indigenous experience to enhance research explanatory power.