13 papers
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…
When Clear Skies Cloud Trust: Environmental Cues and the Paradox of Confidence in Government
Xiangzhe Xu, Ran Wu
Government trust, as a core concept in political economy and public policy research, serves as a fundamental cornerstone of democratic legitimacy and state capacity. This paper exa…
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…
Nova: Generative Language Models for Assembly Code with Hierarchical Attention and Contrastive Learning
Nan Jiang, Chengxiao Wang, Kevin Liu +4
Binary code analysis is the foundation of crucial tasks in the security domain; thus building effective binary analysis techniques is more important than ever. Large language model…
TAI3: Testing Agent Integrity in Interpreting User Intent
Shiwei Feng, Xiangzhe Xu, Xuan Chen +5
LLM agents are increasingly deployed to automate real-world tasks by invoking APIs through natural language instructions. While powerful, they often suffer from misinterpretation o…
From Poisoned to Aware: Fostering Backdoor Self-Awareness in LLMs
Guangyu Shen, Siyuan Cheng, Xiangzhe Xu +4
Large Language Models (LLMs) can acquire deceptive behaviors through backdoor attacks, where the model executes prohibited actions whenever secret triggers appear in the input. Exi…