论文58
Google 论文:智能体 harness 逐模块受控改动比整体重写省近 10 倍 token
原标题:New Google paper finds that an unchecked full rewrite of an agent harness matched accuracy but cost nearly 10 times more tokens per task ...
Google 新论文发现,对智能体 harness 做不受约束的整体重写,准确率与受控的模块化改动相当,但每个任务消耗的 token 接近后者的 10 倍。研究让优化模型每次只改 142 行编码 harness 四个部分中的一个,每次改动须通过验证集和 token 上限,否则被拒。
中文译文尚未完成,先为你展示原文。
New Google paper finds that an unchecked full rewrite of an agent harness matched accuracy but cost nearly 10 times more tokens per task than gated modular edits.
that self-improving agent harnesses work best when they change 1 code module at a time and must pass validation.
The harness is the code around a model that manages context, runs tools, and checks work before stopping. A harness tuned for 1 model often stalls or wastes tokens on another.
They let an optimizer model improve a 142-line coding harness by editing 1 of its 4 parts at a time. Each edit had to pass a validation set and a token cap, or it was rejected.
On 40 held-out SWE-bench Lite tasks with Gemini 3.8 Flash, the gated harness solved 40.0% against 5.0% for the seed, using 46.7k tokens per task. A full unchecked rewrite solved 42.5% but used 451.6k tokens, and prompt rules dropped accuracy to 2.5%.
If you let agents tune their harness, gate each change on held-out tasks and token cost, and enforce rules in code, not prompts.
