Skip to content
Agents

JANUS: Foreseeing Latent Risk for Long-Horizon Agent Safety.

arXiv:2607.19913v2 Announce Type: replace Abstract: Agent safety is moving from content moderation toward preventing operational failures before tool-using agents act. We propose Janus, a foresight-oriented framework for long-horizon agent safety that trains g

arXiv cs.AIResearch source·