omarsar0· @omarsar0 · X·· 1 天前AI 评分
Drex Search 用决策模型优化智能体搜索
Drex Search 通过决策模型为智能体搜索大型文件集合，决定查找位置、只读取关键页面，并在能够引用来源后停止。Nace 报告称，该方案平均减少 62% 的智能体步骤和 56% 的每个问题 token 数，同时准确率平均提高 4 个百分点。
Impressive work on decision models for agentic search.
Drex Search looks like a big upgrade for agents working over large file collections. It decides where to look, reads only the pages that matter, and stops when it can cite the source.
This is a great fit for Claude Code, Codex, and Hermes Agent, where poor retrieval often leads to wrong answers.
Nace reports 62% fewer agent steps and 56% fewer tokens per question, with +4 points of accuracy on average.
来源：omarsar0 · x.com