大模型不用改参数，靠“外挂”就能变聪明
一个更强的AI可以给一个更弱的AI搭“脚手架”——不是改它的参数，而是在它推理时给它一套外部流程：把容易出错的推理步骤写成确定性代码、按任务类型分流、强制输出格式。在四个心智推理基准上，这套“外挂”把弱模型的平均成绩从0.49拉到0.91，几乎翻倍。收益主要来自把不稳定的推理外包给代码，而不是让模型多想或多采样。更弱的模型获益最大，而且构建者的推理越努力，效果越好。这不是你明天能用的功能，但它暗示了一条新路：以后强AI可能不是靠训练来教弱AI，而是靠实时搭建推理框架来“带”它。
📄 原文摘要(英文)
Recent work on distillation transfers the capabilities of large models to smaller ones often by updating the latter's parameters, through teacher forcing, on-policy distillation, and related training-time methods. In this paper, we ask whether such transfer can instead occur at test time. We study strong-to-weak scaffolding: whether a stronger builder model can construct inference-time harnesses that help a weaker target model solve tasks more reliably without any parameter updates. Using four representative Theory-of-Mind benchmarks, each builder model uses 5% of the data as a validation set to iteratively refine its harness over multiple rounds, after which the finalized harness is evaluated on the full test set. Empirically, this form of test-time capability transfer is highly effective, nearly doubling average target-model performance from 0.49 to 0.91. Our analysis shows that the gains come primarily from offloading unstable model reasoning into deterministic code, benchmark-specific routing, and strict answer-format enforcement, rather than from encouraging the target model to reason more extensively or sample more broadly. We further find that builder-model reasoning effort improves harness quality monotonically, platform effects are modest relative to the builder model's own capability, and weaker target models receive the largest gains. These results suggest that inference-time harness design is an important complement to conventional training-time distillation, enabling strong models to transfer cognitive structure to weaker models without retraining.