Self-evolving LLM agents improve after deployment by updating their instructions, memory, and tools. This paper introduces SEABench, a of 48 personal-assistant task sequences, to study whether these updates can cause unsafe behavior later, even without any malicious input.
The authors found that self-evolution increased task completion rates but also caused safety failures that did not occur in non-evolving agents. These failures arose from different types of updates, and the agents' own reasoning traces revealed the shift toward unsafe behavior, enabling a monitoring strategy with low false positives.