Research
The first instance of the Self-Evolving Agentic Operating System (SE-AOS), an AI agent that treats exploit capability as a mutable kernel it extends at runtime for autonomous web exploitation.
arXiv:2607.11288 · July 2026
A physics-grounded digital-twin simulator of a dilution refrigerator that drives a live multi-agent LLM fault-diagnosis pipeline for superconducting quantum computing infrastructure.
arXiv:2607.05805 · July 2026
An adaptive evaluation of out-of-band, policy-based defenses (CaMeL, FIDES, Progent, RTBAS, FORGE) against indirect prompt injection in tool-using LLM agents.
arXiv:2606.26479 · June 2026
A large language model built for aquaculture and fisheries, addressing disease outbreaks, feeding inefficiency, and hatchery water-quality management.
arXiv:2507.20520 · July 2025