Microsoft 发布 ParetoSaddler：智能体 harness 同时优化质量与成本
微软这个 ParetoSaddler 挺有意思，做法是成本筛选放最后一步，GAIA2 上质量涨到 62.89%、成本砍到 $0.45，做 agent 的可以参考。
Microsoft 推出 ParetoSaddler，核心思路是把成本偏好放到搜索最后一步，避免中途丢弃可能导向更优 harness 的候选。每步优化器编辑父 harness，两版多次运行后用 Bayesian bootstrap 判断候选是否在质量或成本上有可信进展。在 GAIA2 上质量从 56.22% 提到 62.89%，单任务成本从 $0.78 降到 $0.45；在 ClawMark 上质量从 70.86% 提到 81.35%，成本从 $1.17 降到 $1.01。Pareto 选出的 harness 在质量和成本两项上都超过只优化质量的方法。
Super interesting finding on optimizing agent harnesses. When you optimize an agent harness for both quality and cost, apply your cost preference only at the end of the search, since applying it at every step throws away harnesses that lead to better ones. That is the key insight behind Microsoft's ParetoSaddler. At each step, an optimizer edits a parent harness. Both versions run several times, and a Bayesian bootstrap over those runs decides whether the candidate shows credible progress in quality or in cost. Promoted candidates stay available as parents, and the final deployment choice is made separately. On GAIA2, quality goes from 56.22% to 62.89% while cost per task drops from $0.78 to $0.45. On ClawMark, quality goes from 70.86% to 81.35%, and cost drops from $1.17 to $1.01. The Pareto-selected harnesses also beat quality-only optimization on both quality and cost. If your harness search only tracks accuracy, add repeated runs and a cost axis before deciding which candidates to keep. arxiv.org/abs/2611.02079 Chat with Paper: academy.dair.ai/papers/paretos… 💬 24 🔄 5 ❤️ 30 👀 3804 📊 28 ⚡
