Jul 2026
TRACE: An Operational Reasoning Schema for Auditable Agentic Commitments
This paper argues in three layers that reasoning is not in the language model: the autoregressive mechanism natively computes association; chain-of-thought and reinforcement learning inherit its limits; and the formal constructs of reasoning theory are absent as machinery.
E. Y. Chang, Emily J. Chang
· arXiv.org · 1 citation