LLMs Can Program Tabular Foundation Models Without Gradient Descent, Shows New Paper

RexDouglass · x · 2026-11-17

The arXiv paper 'Weights & Caches' (Hoo, Buehler, Swelam, Hutter et al.) shows LLMs can build, repair and steer tabular foundation models (TFMs) by directly manipulating weights — no gradient descent. Using GPT-6 Astra across three settings:

The authors argue LLM-driven weight programming could complement gradient-based optimization across TFM development and usage.

Original post →

More from Research

Research channel →