2 papers
cs.SE2026
Complex Agents, Shallow Tests: Demystifying and Enhancing Test Adequacy of Agent Harness in the Wild
Yifan Xiong, Jingyi Ge, Zhenpeng Chen +1
LLM-based agentic systems are emerging as a new software paradigm. Modern agents are typically composed of backbone LLMs and a surrounding harness that serves as the operational so…
cs.SE2024
Demystifying and Assessing Code Understandability in Java Decompilation
Ruixin Qin, Yifan Xiong, Yifei Lu +1
Decompilation, the process of converting machine-level code into readable source code, plays a critical role in reverse engineering. Given that the main purpose of decompilation is…