4 citations · 18 across the 22 of their papers we have counts for
4 papers · 1 filter
WitnessGym: Benchmarking Coding Agents on the Construction of Bug Witnesses
Haomin Qi, Xiangzhe Xu, Yiming Huang +2
Bug validation asks a coding agent to produce an executable witness for a reported bug. The witness combines a concrete input with a testing harness and exposes faulty behavior dur…
Natural-Language Workflows Are Not Software Yet: Artifact-Driven Compilation for Reliable Agent Execution
Xiangzhe Xu, Hanxi Guo, Guangyu Shen +2
Natural-language workflows offer a software-like interface for agents: domain experts can write reusable procedures, and agents can execute them as instructions. This promise is no…
The Devil Is in the Interface: Evaluating How Tool Architecture Shapes Coding Agent Behavior
Xiangzhe Xu, Hamidreza Saghir, Qianhui Wu +5
As large language models continue to improve, agentic systems are becoming increasingly important, and tools are a key design dimension because they determine how agents access inf…
Identifying Adversary Tactics and Techniques in Malware Binaries with an LLM Agent
Zhou Xuan, Xiangzhe Xu, Mingwei Zheng +6
Understanding TTPs (Tactics, Techniques, and Procedures) in malware binaries is essential for security analysis and threat intelligence, yet remains challenging in practice. Real-w…