Title: MAGE: Safeguarding LLM Agents against Long-Horizon Threats via Shadow Memory

Source: http://arxiv.org/abs/2605.03228v1

Summary:

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.