Preprint
May 2026
Restricting the Model, Missing the System: Measurement and Accountability in Offensive AI Governance
It is argued that restricting access to a model is necessary but not sufficient and that policy and procurement also need system-level, harm-grounded capability assessment, and a study of an open-source framework in which lightweight large language model (LLM) agents coordinate through shared memory and evolutionary op...
M. A. Riegler, Finn Schwall, A. W. Olstad et al.
· 0 citations