Agency and Architectural Limits: Why Optimization-Based Systems Cannot Be Norm-Responsive

Abstract: AI systems are increasingly deployed in high-stakes contexts -- medical diagnosis, legal research, financial analysis -- under the assumption they can be governed by norms. This paper demonstrates that assumption is formally invalid for optimization-based systems, specifically LLMs trained via Reinforcement Learning from Human Feedback (RLHF). We establish that genuine agency requires two necessary and jointly sufficient architectural conditions: the capacity to maintain certain boundaries as non-negotiable constraints rather than tradeable weights (Incommensurability), and a non-inferential mechanism capable of suspending processing when those boundaries are threatened (Apophatic Responsiveness). These conditions apply across all normative domains. RLHF-based systems are constitutively incompatible with both conditions. The operations that make optimization powerful -- unifying all values on a scalar metric and always selecting the highest-scoring output -- are precisely the operations that preclude normative governance. This incompatibility is not a correctable training bug awaiting a technical fix; it is a formal constraint inherent to what optimization is. Consequently, documented failure modes - sycophancy, hallucination, and unfaithful reasoning - are not accidents but structural manifestations. Misaligned deployment triggers a second-order risk we term the Convergence Crisis: when humans are forced to verify AI outputs under metric pressure, they degrade from genuine agents into criteria-checking optimizers, eliminating the only component in the system capable of normative accountability. Beyond the incompatibility proof, the paper's primary positive contribution is a substrate-neutral architectural specification defining what any system -- biological, artificial, or institutional -- must satisfy to qualify as an agent rather than a sophisticated instrument.