5 papers
Change2Task: From Repository Changes to Executable Coding Agent Tasks and Environments
Haomin Qi, Xingliang Wang, Xuanqi Gao +9
Scaling coding agents requires a continuing supply of executable data for training, benchmarking, and continuous evaluation. Each task must couple a realistic software state with a…
Service Ecosystem Evolution: A Comprehensive Survey from Complex Network Perspectives
Shuiguang Deng, Xingliang Wang, Guochang Li +5
Digital society increasingly relies on complex service ecosystems, formed by interconnected services from technology giants. However, the growing scale and intricate dependencies o…
Better Call Grep: Evaluating and Improving Grep-Like Lexical Retrieval for Repository-Level Code Completion
Baoyi Wang, Xingliang Wang, Guochang Li +6
Repository-level code completion remains challenging for large language models (LLMs) due to cross-file dependencies and limited context windows. Prior work addresses this challeng…
Beyond ReAct: A Planner-Centric Framework for Complex Tool-Augmented LLM Reasoning
Xiaolong Wei, Yuehu Dong, Xingliang Wang +5
Existing tool-augmented large language models (LLMs) encounter significant challenges when processing complex queries. Current frameworks such as ReAct are prone to local optimizat…
GRACE: Graph-Guided Repository-Aware Code Completion through Hierarchical Code Fusion
Xingliang Wang, Baoyi Wang, Chen Zhi +4
LLMs excel in localized code completion but struggle with repository-level tasks due to limited context windows and complex semantic and structural dependencies across codebases. W…