跳到正文

Qwen3.8-27B-pi-adapted 旨在优化 pi 编程智能体

clem 🤗 · X· @ClementDelangue·· 11 小时前精选

2.9万 次浏览 · 876 赞 · 112 转发 (收录时)

原文

发生了什么

Clément Delangue 介绍了 Qwen3.8-27B-pi-adapted,这是一个通过强化学习和 LoRA 适配器为 pi 编程智能体适配的 Qwen 模型。文章报告称,在 SWE-bench Pro (Hard 51) 上,pass@1 从 29.4% 提升至 62.7%,在 Terminal-Bench 2.1 上从 39.5% 提升至 55.8%,且每个任务的工具调用次数减少了 55–62%。开放权重和方法论已提供链接。

推荐理由

该适配模型提升了在 SWE-bench Pro (Hard 51) 和 Terminal-Bench 2.1 上的 pass@1,同时每个任务的工具调用次数减少了 55–62%,这表明编程智能体可以从针对其特定工具进行调优的模型中受益。

正文 · 中文版本尚未就绪(原文)

Introducing Qwen3.8-27B-pi-adapted 🤗

We adapted Qwen's model specifically for the pi coding agent using reinforcement learning and a LoRA adapter.

The results, measured as pass@1:
🚀 SWE-bench Pro (Hard 51): 29.4% → 62.7%
💻 Terminal-Bench 2.1: 39.5% → 55.8%
⚡ 55–62% fewer tool calls per task

This is the power of open models: you can adapt them to YOUR tools and YOUR use cases. Let’s build! 💛

Open weights: huggingface.co/harness-hub/Qw…
Methodology: huggingface.co/blog/harness-h…

这件事到目前为止

Harness Hub has released Qwen3.8-27B-pi-adapted, an iteration of the Qwen model optimized for the pi coding agent using reinforcement learning and a LoRA adapter. The model's weights and methodology are available publicly. Clément Delangue reported that this adaptation improves performance across coding benchmarks. On SWE-bench Pro (Hard 51), pass@1 rates increased from 29.4% to 62.7%, while scores on Terminal-Bench 2.1 rose from 39.5% to 55.8%. Additionally, the model reportedly requires 55–62% fewer tool calls per task.

接下来读什么

查看这件事的完整进展Harness Hub Releases Qwen3.8-27B-pi-adapted for Improved Coding Agent Performance
这条收录于 11月18日 AI 日报看这一期日报的全部内容