跳到正文
研踪PaperTrail
← 研踪 PaperTrail

arXiv:2610.02001 · v2

Mingbird: A Local-First Agent Harness Enabling Small Open Models to Complete Real Tasks

Mingbird:一个本地优先的智能体框架,使小型开放模型能够完成真实任务

首次提交 2026-10-02 00:32
版本更新 2026-11-18 02:43
雷达观测 2026-11-18 12:34
arXiv ↗PDF ↗

摘要

Small open-weight language models now run on a laptop, but they fail at multi-step work in ways a large model does not: they stop with the files missing, repeat one action until the budget ends, and report success without checking. At the one-to-nine-billion-parameter tier the harness supplies almost all of the procedural control that a large model supplies for itself.We present Mingbird, an open-source harness for that tier on a consumer graphics card: 12k lines of Python, a 628-test suite, and eighteen mechanisms for context economy, completion, time budget and the host boundary, plus a crawl guard outside those four groups. Its design point is completion control: the harness runs executable checks on the working directory and refuses a claim of completion when they fail.Five evaluations accompany it. A configuration-surface audit finds four defects that the 625-test suite of v3.1.1 missed, each because a test checked a property adjacent to the one that broke. A ten-task probe suite gives each mechanism a reason to fire and reports where the change reaches the artifact, including one mechanism that cuts the signal it protects. Disabling five of six completion-time checks costs 0.152 of the artifact score on eighteen held-out tasks, three replications per cell (95% CI [+0.064, +0.246], Holm p = 0.014). On a 288-cell matrix the harness reaches 0.886 against 0.631, 0.479 and 0.405 for three open scaffolds, and on τ 2 -bench it ranks first or tied first in all three domains against the arms evaluated.Tasks, scorer, source and every per-cell result are public.

作者备注:67 pages, 30 tables, 4 figures. v2: substantially revised (18 mechanisms, the 288-cell v1.5.0 matrix, five evaluations). Code, benchmark protocol, scoring code and all per-cell results: https://github.com/Mingbird/Mingbird-agent

AI 论文解读

基于摘要 · 非全文审阅

Mingbird 是一个面向十亿参数级小型开放模型的本地智能体框架,通过完成控制等机制提升多步任务完成率。

正在读取账号与研究记录…

版本差异

本站首次收录为 v2,暂无更早版本可对照。

观测到的版本

相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。

v2 · 2026-11-18 02:43 · 最新观测版本

Mingbird: A Local-First Agent Harness Enabling Small Open Models to Complete Real Tasks

Small open-weight language models now run on a laptop, but they fail at multi-step work in ways a large model does not: they stop with the files missing, repeat one action until the budget ends, and report success without checking. At the one-to-nine-billion-parameter tier the harness supplies almost all of the procedural control that a large model supplies for itself.We present Mingbird, an open-source harness for that tier on a consumer graphics card: 12k lines of Python, a 628-test suite, and eighteen mechanisms for context economy, completion, time budget and the host boundary, plus a crawl guard outside those four groups. Its design point is completion control: the harness runs executable checks on the working directory and refuses a claim of completion when they fail.Five evaluations accompany it. A configuration-surface audit finds four defects that the 625-test suite of v3.1.1 missed, each because a test checked a property adjacent to the one that broke. A ten-task probe suite gives each mechanism a reason to fire and reports where the change reaches the artifact, including one mechanism that cuts the signal it protects. Disabling five of six completion-time checks costs 0.152 of the artifact score on eighteen held-out tasks, three replications per cell (95% CI [+0.064, +0.246], Holm p = 0.014). On a 288-cell matrix the harness reaches 0.886 against 0.631, 0.479 and 0.405 for three open scaffolds, and on τ 2 -bench it ranks first or tied first in all three domains against the arms evaluated.Tasks, scorer, source and every per-cell result are public.

查看此版本解读 →查看此版本原文 ↗