📖 Research interests: Software Evolution, LLM-based Agent, and GUI Code Gen & Testing.
More info can be found in itaowe.com
📖 Research interests: Software Evolution, LLM-based Agent, and GUI Code Gen & Testing.
More info can be found in itaowe.com
[FSE'2026] SWE-Factory: Your Automated Factory for Issue Resolution Training Data and Evaluation Benchmarks
[FSE'2026] PlayCoder: Making LLM-Generated GUI Code Playable
[EMNLP 2025 main] C3 Benchmark: A Bilingual Benchmark for Spoken Dialogue Models Exploring Challenges in Complex Conversations
Python 30
A GitHub issue resolution benchmark with multi-aspect diversity in programming languages, repository domains and modality of input information. (ISSTA'25)
MAGIS: LLM-Based Multi-Agent Framework for GitHub Issue Resolution. [NeurIPS 2024]
CSS 11