Tag
The article explains how GEPA (Genetic-Pareto Optimization) within DSPy is used for efficient prompt tuning, specifically applied to pretraining data curation at Microsoft AI, allowing researchers to replace manual prompt engineering with automated compute-driven optimization.
GEPA-optimized LLM judges from dspy are used for data filtering in Microsoft's MAI-Thinking-1 model pre-training pipeline.
A tweet praising the combination of RLMs and GEPA, expressing anticipation for a follow-up.
The post explains why Reinforcement Learning struggles with long-horizon tasks due to sparse rewards and highlights GEPA, a method that uses trajectory-level textual reflection to preserve richer feedback signals for optimization.