Publications
Also on Google Scholar.
Preprints
Workshop Papers
- ClawMMU: Protection-Coherent Virtual Memory for Stateful LLM Agents
Jinhao Hu, Bardia Mohammadi, Mofasshara Binte Rafique, Lars Henning Klein, Akhil Arora, Ashvin Goel, Laurent Bindschaedler.
Workshop on Co-designing Systems and ML Foundations of an OS Layer for Agentic AI (AgenticOS @ NeurIPS'26).
arXiv:2610.28093
- Don’t Trust the Code, Check Its Effects: Runtime Refinement for Regenerated Systems Code Under an Adversarial Generator
Jinhao Hu, Ashvin Goel, Laurent Bindschaedler.
Workshop on Practical Adoption Challenges of ML for Systems (PACMI'26), co-located with SOSP 2026.
arXiv:2609.00430
- Externalization Barriers: An OS Abstraction for Untrusted Agent Exploration
Jinhao Hu, Bardia Mohammadi, Ashvin Goel, Laurent Bindschaedler.
Workshop on Operating Systems Design for AI Agents (AgenticOS'26), co-located with SOSP 2026.
PDF