9 papers
CodeSpec: Dual Executable Specifications for Agentic Long-Horizon Feature Development
Peiding Wang, Li Zhang, Fang Liu +2
The paper introduces CodeSpec, a method that creates paired architecture and behavior specifications to guide LLM-based code agents in developing new features across existing codeb…
LLM-Driven Collaborative Model for Untangling Commits via Explicit and Implicit Dependency Reasoning
Bo Hou, Xin Tan, Kai Zheng +3
The paper introduces ColaUntangle, a framework that uses multiple LLM-driven agents to identify both explicit and implicit dependencies among code changes in order to separate tang…
ContraFix: Skill-Enhanced Contrastive Runtime Analysis for Vulnerability Repair
Simiao Liu, Fang Liu, Peiding Wang +4
As software systems grow increasingly complex, automated vulnerability repair (AVR) remains difficult because the materials available to a repair system are usually failure artifac…
MemRepair: Hierarchical Memory for Agentic Repository-Level Vulnerability Repair
Simiao Liu, Li Zhang, Fang Liu +3
Modern software ecosystems face a rapidly growing number of disclosed vulnerabilities, increasing the need for automated repair techniques that can operate reliably at repository s…
CodeMEM: AST-Guided Adaptive Memory for Repository-Level Iterative Code Generation
Peiding Wang, Li Zhang, Fang Liu +2
Large language models (LLMs) substantially enhance developer productivity in repository-level code generation through interactive collaboration. However, as interactions progress,…
SecureReviewer: Enhancing Large Language Models for Secure Code Review through Secure-aware Fine-tuning
Fang Liu, Simiao Liu, Yinghao Zhu +2
Identifying and addressing security issues during the early phase of the development lifecycle is critical for mitigating the long-term negative impacts on software systems. Code r…