MAGE introduces the 'shadow memory' abstraction, a novel defensive framework that maintains a safety-focused agentic memory to counter long-horizon threats. It establishes a new paradigm for agentic safety by enabling models to proactively assess risk across extended execution trajectories.
Short on time? Watch the video overview of this paper.
Listen on: Spotify · Apple Podcasts · Amazon Music · YouTube
Follow the show: YouTube · Medium · X · LinkedIn · Bluesky · Threads · Instagram · TikTok · Facebook · Telegram