AI & ML Paradigm Challenge

The specific LLM you choose matters far less than the structural wrapper you place around it.

April 15, 2026

Original Paper

Cognitive Exoskeletons: External Structure as the Determinant of LLM Output Identity

Shun Fujiyoshi

SSRN · 6290599

The Takeaway

This research introduces the concept of the 'cognitive exoskeleton,' arguing that a model's identity and consistency are determined by its external architectural layers rather than its internal parameters. Before this, the industry focused almost entirely on scaling model weights and fine-tuning. Now, we see that the 'filter' around the model acts as the primary determinant of behavior. This shifts the engineering focus from training expensive new models to building more robust external structures. Practitioners can now achieve high-consistency outputs using smaller, cheaper models provided the 'exoskeleton' is sufficiently sophisticated.

From the abstract

Large language models produce impressive but inconsistent outputs. The field has tried two fixes: change the model (fine-tuning, RLHF) or change the human (prompt engineering). Both miss what we believe is the actual lever. We propose attaching a cognitive exoskeleton-an external structural layer that wraps around the AI and shapes its output character through architecture, not parameter modification. We define the term precisely: a cognitive exoskeleton must be model-agnostic, identity-preservi