做蛋白质结构预测的可以看看这篇，它对比了四种 oracle 预算分配方法，告诉你低预算用 O3，高预算用 FK-steering 和 DPO，挺实用。
蛋白质结构预测基础模型在某些靶标上仍不可靠，外部 oracle 可纠正错误但成本高昂。一篇论文系统对比了 FK-steering、DPO、Best K-of-N 和最新提出的 O3 四种预算分配方法。在钙调蛋白（1CLL）和大肠杆菌天冬氨酸转氨甲酰酶（9EEH）两个靶标上，没有单一方法在所有预算下都占优。O3 在低预算时最有效，而 FK-steering 和 DPO 随预算增加表现更好。该研究给出了针对实际 oracle 预算约束的可操作建议。
How to Spend Your Oracle Budget: Practical Guidance for Protein Structure Prediction Models
Foundation models for protein structure prediction remain unreliable on certain targets. External oracles can flag and correct these failures, but biological oracles are expensive, making oracle budget a critical constraint. Existing guidance methods, such as FK-steering, DPO, and Best K-of-N sampling, differ in how they spend this budget, yet no systematic comparison exists to guide method selection. To bridge this gap, we benchmark these methods alongside the recently proposed Optimisation Over Outputs (O3), which applies off-the-shelf optimisers within a generative model's latent subspace. We extend the usage of O3 to protein structure prediction models. Overall, our work provides the first practical reference for oracle budget-aware guidance. Our evaluation on two protein targets, calmodulin (1CLL) and E. coli aspartate transcarbamoylase (9EEH), reveals that no single method consistently dominates across all budgets and oracles. Specifically, O3 proves most effective at low oracle budgets, while FK-steering and DPO demonstrate improved performance as the budget increases. We distil these findings into actionable recommendations for practitioners operating under real-world oracle-budget constraints.