EliteTable: LLM-guided self-improving program search for control policies (arXiv:2610.12536v1)

KEY POINTS

1. EliteTable is a program-search algorithm guided by large language models that maintains a fixed-capacity table of high-scoring solutions to propose, edit, and remix candidate executable control programs.
2. The paper reports experiments on six Gymnasium control tasks (ten generations, 50 candidates per generation, 10 independent searches): candidate-score medians increased in all six tasks and selected-winner medians increased in five; CartPole-v1 winners hit the reported score ceiling immediately, while BipedalWalker-v3 and CarRacing-v3 improved without reaching targets and Acrobot-v1 showed mixed/negative held-out performance; the authors note that comparisons and ablations are needed to establish relative contributions.
3. This presents a new LLM-guided program-search approach that shows within-search improvement and some transfer to held-out episodes, indicating a promising direction for synthesizing executable control policies though further comparisons are required.