Showing cs.CLShow all
3 papers · 1 filter
cs.CL2026
SkillHarm: Lifecycle-Aware Skill-Based Attacks via Automated Construction
Yuting Ning, Zhehao Zhang, Yash Kumar Lal +8
Agent skills occupy a privileged position in the agent workflow, as agents are expected to implicitly follow and execute them, rendering third-party skills a vulnerable attack surf…
cs.CL2026
When Actions Go Off-Task: Detecting and Correcting Misaligned Actions in Computer-Use Agents
Yuting Ning, Jaylen Jones, Zhehao Zhang +5
Computer-use agents (CUAs) have made tremendous progress in the past year, yet they still frequently produce misaligned actions that deviate from the user's original intent. Such m…
cs.CL2023
On the steerability of large language models toward data-driven personas
Junyi Li, Ninareh Mehrabi, Charith Peris +5
Large language models (LLMs) are known to generate biased responses where the opinions of certain groups and populations are underrepresented. Here, we present a novel approach to…