Skip to content
Agents

Appreciation Teaches Unauthorized Execution: Self-Evolution Degrades the Robustness of Personal Agents to Indirect Prompt Injection.

arXiv:2610.39122v1 Announce Type: cross Abstract: Self-evolving personal agents act for users and learn from user feedback. However, if an agent obeys an instruction that an untrusted third party hides in content, the third party gains control of the agent. Su

arXiv cs.AIResearch source·