Safety of Latent Communication in Multi-Agent Systems
Benign latent links between agents raise harmful compliance, and an RL attack lifts the mean score from 27.9 to 76.9.
1 stories, newest first · one card per story
Benign latent links between agents raise harmful compliance, and an RL attack lifts the mean score from 27.9 to 76.9.
Today 1.6K readers · 2.5K views · 779 reads · all time 189K views