3 papers
cs.SE2026
Reusing Past Repairs Through Hierarchical Trajectory Abstraction for Coding Agents
Yisen Xu, Jiayuan Zhou, Ruiqi Pan +1
Although LLM-driven repair agents can tackle complex, repository-level issues, they treat every issue independently and discard the procedural knowledge accumulated from previous r…
cs.SE2025
Lingxi: Repository-Level Issue Resolution Framework Enhanced by Procedural Knowledge Guided Scaling
Xu Yang, Jiayuan Zhou, Michael Pacheco +5
Driven by the advancements of Large Language Models (LLMs), LLM-powered agents are making significant improvements in software engineering tasks, yet struggle with complex, reposit…
cs.SE2025
One-for-All Does Not Work! Enhancing Vulnerability Detection by Mixture-of-Experts (MoE)
Xu Yang, Shaowei Wang, Jiayuan Zhou +1
Deep Learning-based Vulnerability Detection (DLVD) techniques have garnered significant interest due to their ability to automatically learn vulnerability patterns from previously…