4 papers
Can Agentic Code Review Catch Vulnerabilities Before They Are Merged?
Yihan Yang, Chenyuan Yang, Zijie Zhao +5
LLM agents have been increasingly adopted for security-focused code review, but existing benchmarks mostly derive the reviewed changes from their later fixes instead of the real-wo…
AnyPoC: Universal Proof-of-Concept Test Generation for Scalable LLM-Based Bug Detection
Zijie Zhao, Chenyuan Yang, Weidong Wang +3
While recent LLM-based agents can identify many candidate bugs in source code, their reports remain static hypotheses that require manual validation, limiting the practicality of a…
SafeAgent: Safeguarding LLM Agents via an Automated Risk Simulator
Xueyang Zhou, Weidong Wang, Lin Lu +7
Large Language Model (LLM)-based agents are increasingly deployed in real-world applications such as "digital assistants, autonomous customer service, and decision-support systems"…
Exploring the Necessity of Reasoning in LLM-based Agent Scenarios
Xueyang Zhou, Guiyao Tie, Guowen Zhang +7
The rise of Large Reasoning Models (LRMs) signifies a paradigm shift toward advanced computational reasoning. Yet, this progress disrupts traditional agent frameworks, traditionall…