Papers by Sion Weatherhead

Copied to clipboard

Challenge:	Large Language Models (LLMs) demonstrate strong capabilities in translating natural language into code, but applying them to this domain remains challenging.
Approach:	They propose a dual-anchored evolutionary framework that combines a static blueprint and a bi-level optimization to decouple structural refinement from parameter calibration.
Outcome:	The proposed framework identifies two failure modes in long-horizon LLM agents: contextual drift and optimization instability arising from conflating structural and parametric errors.