AI 变聪明，光调模型不够，还得改它的「操作手册」
我们一直以为 AI 变强靠的是调大模型参数；这篇说，参数和「操作手册」得一起改。所谓操作手册，就是控制 AI 怎么调用工具、怎么组织步骤的那段代码——以前大家只优化模型和提示词，这段代码是死的。WHALE 的做法很简单：先固定手册、用在线采样微调模型；再固定模型、用搜索找更好的手册，如此交替。关键发现是：有时候瓶颈在模型，有时候在手册——在搜索问答上，光改手册就能达到调模型的效果，而且省一大半试错；但在数学题上，手册改进只有在模型更新之后才起作用。它不是你明天能用上的东西，但它点破了一个趋势：下一代 AI 的进步，可能不是单点突破，而是模型和外围代码的协同进化。
📄 原文摘要(英文)
Agent performance depends jointly on the model parameters and the executable harness code that manages context and control flow. Optimizing either component in isolation can leave the system bottlenecked by its frozen counterpart: weight updates can change which harness is effective, while harness updates can change which model capabilities are exposed. Existing joint-adaptation methods optimize weights and textual prompts but leave the broader harness fixed. We propose Weight-Harness Alternating LEarning (WHALE), a simple recipe that alternates two phases: updating the model under the current harness, then searching for a better harness under the updated model. We instantiate these two phases with online rejection-sampling fine-tuning and Meta-Harness, respectively. When to switch is a key design choice: to separate real improvements from noise without over-optimizing against a changing counterpart, WHALE uses either fixed phase durations or an adaptive patience rule over training signals. Using Qwen3.5-2B/4B agents across three domains (search question answering, mathematical reasoning, and chess puzzles), WHALE outperforms weight-only, harness-only, and Fast-Slow Training by 4.15-24.38 percentage points in best mean@8 accuracy. Either component can be the bottleneck: harness search matches peak weight-only accuracy with far fewer rollouts in SearchQA, but improves math accuracy only after a weight update. Small interleaved updates also outperform stagewise weight-then-harness optimization in accuracy and rollout cost. The code is available at https://github.com/krafton-ai/WHALE.