LLM-based multi-agent system (MAS) applications can produce useful intermediate results while leaving task requirements unsatisfied. Repairing such executions requires identifying the work still needed and the completed results that can support it. We present \tool, a contribution-guided runtime repair framework for MA...
Han-Qi Sun, Yu-Chen Shao, Han-Yi Si et al.· 0 citations
Large language model (LLM) agents increasingly complete tasks through live graphical user interfaces (GUIs). Because the model cannot directly operate the GUI, these systems often rely on tools to capture screenshots or UI trees, translate model outputs into GUI actions, and report whether the interface changed. We stu...
Yu-Chen Shao, Wen-Jing Liu, Yu-Heng Huang et al.· 0 citations
Streaming video LLMs must retain evidence before its relevance to future tasks is known and respond when sufficient evidence becomes available. The challenge is to form reusable factual memory without compromising real-time perception. We introduce OneStreamer, which jointly learns query-independent evidence recording...
Static-analysis checker synthesis requires agents to interpret a defect specification, inspect a repository, implement analyzer-specific logic, and refine the checker through repeated compilation and analysis feedback. Existing coding-agent benchmarks focus on tasks such as patch generation or vulnerability detection a...
Hang He, Li-Sheng Wang, Hao Chen et al.· 3 citations
TRACE is introduced, a weights-only auditing method that localizes an unknown checkpoint update relative to frozen harmful and non-harmful reference prototypes and converts this geometry into a continuous harmful-objective score.
Zi-Qun Bao, Xin-Yu Zhang, Yu-Chen Shao et al.· 0 citations
Datura, an automated red teaming testing framework that exposes safety vulnerabilities through chained tool manipulation, is proposed and evaluated across five LLMs and 740 safety-critical tasks under five defense settings, including real-world safety mechanisms.
Yu-Chen Shao, Zi-Qun Bao, Yu-Heng Huang et al.· Proceedings of the ACM on So...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.