AI RESEARCH
Agent-Sentry: Bounding LLM Agents via Execution Provenance
arXiv CS.AI
•
ArXi:2603.22868v1 Announce Type: cross Agentic computing systems, which autonomously spawn new functionalities based on natural language instructions, are becoming increasingly prevalent. While immensely capable, these systems raise serious security, privacy, and safety concerns. Fundamentally, the full set of functionalities offered by these systems, combined with their probabilistic execution flows, is not known beforehand.