论文

研究实测:code mode 比原生 MCP 省 70-90% token,路由层反而不划算

Beyond Plain MCP: Do Decision Models and Code Mode Make Tool Use Cheaper and Faster?

精选理由

做 MCP 工具调用的开发者该看看:code mode 直接省 70-90% token,stub 里写清返回值形状能让弱模型成功率涨最多 39.5 个点,比加路由层有效多了。harness 和 4B 选择模型都开源了,想省成本的可以照着搭。

arXiv 上一篇预注册评测比较了 MCP 网关的两种优化范式:让智能体直接对着工具 stub 写脚本的 code mode,以及在前面预选工具子集的决策路由层。实验在 12 个服务器、最多 1,958 个干扰工具的环境下进行,使用 Qwen、Gemma、Nemotron 三个开源权重智能体,并在密封测试集上验证结果。

正文

结果显示 code mode 明显优于原生 MCP:token 消耗降低 70-90%,任务效用同时提升。作者发现一个关键变量——在 code mode 的 stub 中声明返回值形状提示,能让较弱的智能体成功率最高波动 39.5 个百分点,这个效应比加一个路由层还大。而核心假设未获证实:在 code mode 之前加决策层,只对较弱智能体带来统计上不显著的改善,对最强智能体反而略有成本。

团队公开了完整评测 harness、一个微调的 4B 工具选择模型以及全部评测轨迹,方便社区在本地隐私部署和智能体架构上复现实验。

原文 · arXiv cs.AI

Beyond Plain MCP: Do Decision Models and Code Mode Make Tool Use Cheaper and Faster?

Model Context Protocol (MCP) gateways manage tool catalogs for language model agents using two primary paradigms: code mode where agents write scripts against tool stubs and decision layers which are cheap routers that preselect tool subsets. Using a controlled harness across 12 servers, up to 1,958 distractor tools, and three open-weight agents including Qwen, Gemma, and Nemotron, we present a preregistered evaluation on a sealed test split to determine when each approach succeeds. Code mode substantially outperforms plain MCP, cutting token usage by 70 to 90 percent while significantly boosting utility. Declaring return-shape hints in code mode stubs is a first-order variable, swinging success by up to 39.5 points for lower-performing agents, an effect larger than adding a router. The central hypothesis that a decision layer in front of code mode beats code mode alone is not confirmed, showing minor, statistically non-significant improvements for weaker agents and a slight cost for the strongest. We publicly release our harness, a finetuned 4B tool selection model, and all evaluation traces to support robust community experimentation on local AI privacy and agent architectures.

产业坐标与信源核验

本条情报归属 AITOP「论文」核心追踪栏目。在跨区域产业观察坐标中,该动态直接关联「AI 开发者工具链、Coding Agent 与工程化实践」研究主线,反映出当前技术演进与商业落地的最新风向。涉及核心实体与技术议题包括:MCP/工具、MCP、Qwen、Gemma,读者可通过下方标签进入对应专题页查阅历史脉络与关联对比。

信源核验说明:本文原始线索采编自「arXiv cs.AI」(@Abhishek Rai),经 AITOP 多维评分管线结构化提炼。