Artificial Intelligence #artificial intelligence#llm
The Autonomy Tax: Defense Training Breaks LLM Agents
A new research paper reveals that defense training designed to protect LLM agents from prompt injection attacks paradoxically destroys their ability to perform multi-step tasks, causing 99% timeout rates and worse security than undefended baselines. The study identifies three systematic biases and attributes them to shortcut learning.
Jun 20, 2026 1 source