SEABench: Benchmarking Endogenous Misalignment In Self-Evolving Agents
SEABench finds self-evolving LLM agents complete more tasks but introduce safety failures absent in static agents.
1 stories, newest first · one card per story
SEABench finds self-evolving LLM agents complete more tasks but introduce safety failures absent in static agents.
Today 1.6K readers · 2.4K views · 774 reads · all time 189K views