ClawMMU: Protection-Coherent Virtual Memory for Stateful LLM Agents
AI agents keep long-term memory, much of which comes from web pages and tool results. Agent harnesses, the software that runs the model, do not record who may act on this memory, so an instruction hidden in a fetched page can be treated as the user's own instruction. We propose ClawMMU, a protection layer that labels e...
Jin-Hao Hu, Bardia Mohammadi, Mofasshara Rafique et al.
· 0 citations