Ashvin Goel

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...

Don't Trust the Code, Check Its Effects: Runtime Refinement for Regenerated Systems Code Under an Adversarial Generator

Recent work uses large language models to generate systems code from specifications, treating the specification as the durable artifact and the implementation as disposable. Regenerating the implementation specializes it to each workload and device. However, that work lives in a forgiving setting: a component's externa...

Externalization Barriers: An OS Abstraction for Untrusted Agent Exploration