# Zoom 实证研究：编码智能体 harness 设计取舍

- 来源：DAIR.AI (@dair_ai)
- 发布时间：2026-09-19 06:30
- AIHOT 分数：50
- AIHOT 链接：https://aihot.news/items/cmu7k918r0gi8rogri6xk26y6
- 原文链接：https://x.com/dair_ai/status/2101076312857477393

## AI 摘要

Zoom 团队在 176 组匹配设置、4 个模型上，用 SWE-Bench Verified 和 Terminal-Bench 2.1 固定编码 harness 执行循环，逐一变化规划、动作空间与上下文管理。

## 正文

Super interesting work from Zoom and colleagues.

If you maintain a hand-built coding harness, there are some great insights here.

(bookmark it)

They held the execution loop of a coding harness fixed and varied planning, the action space, and context management one at a time.

They did across 176 matched settings, four models, SWE-Bench Verified and Terminal-Bench 2.1.

Context management pays off more as the context window tightens.

Most of its benefit comes from preventing overflow failures rather than from better reasoning.

Staging rule-based elision before LLM summarization gave the best accuracy to cost ratio of the five strategies tested.

Making elided content recoverable added machinery the models rarely used and produced no accuracy gain.

Planning changed role with model strength.

For the weakest model it raised the success rate. For stronger models accuracy barely moved and the gain showed up as lower cost, because planning shortened post-edit verification.

On the action space, predefined tools helped models with weak bash proficiency, while bash-capable models ran a bash-only interface at substantially lower cost on command-line tasks.

Paper: https://academy.dair.ai/papers/an-empirical-study-of-harness-design-for-coding-agents-2609.20804