ARES: Securing Agents for Computer Use Through Endpoint Resource Mediation and Behavioral Guardrails

Abstract

Large language model (LLM)-based agents are evolving into agents for computer use (ACUs) that read files, invoke applications, communicate over networks, and operate graphical interfaces, moving the effective security boundary from model inputs and outputs to autonomous actions that alter endpoint state. Conventional identity and access controls remain applicable and necessary, but they are authorized based on identity, resource, and network policy rather than on the semantic scope of the active

Categories

@article{kim2026ares,
  title = {{ARES: Securing Agents for Computer Use Through Endpoint Resource Mediation and Behavioral Guardrails}},
  author = {Changhee Kim and Seong-je Cho},
  year = {2026},
  month = sep,
  journal = {Electronics},
  doi = {10.3390/electronics15174007},
  url = {https://www.semanticscholar.org/paper/fd1a22d2baba2df7a0db52925828232b7a69ebb0}
}