<!-- mobian-agent-page publisher="dailydev" canonical="https://daily.dev/posts/fN7UvvLGv" -->

---
title: Qwen3.8-27B-pi-adapted: a LoRA adapter tuned for the pi...
description: Qwen3.8-27B-pi-adapted, a LoRA adapter that tunes Qwen's 27B model for the pi coding agent using reinforcement learning, was announced by @ClementDelangue. On...
canonical: https://daily.dev/posts/fn7uvvlgv
twitter:card: summary_large_image
twitter:site: @dailydotdev
og:type: website
og:site_name: daily.dev
og:title: Qwen3.8-27B-pi-adapted: a LoRA adapter tuned for the pi coding agent | daily.dev
og:description: Qwen3.8-27B-pi-adapted, a LoRA adapter that tunes Qwen's 27B model for the pi coding agent using reinforcement learning, was announced by @ClementDelangue. On...
og:url: https://daily.dev/posts/fn7uvvlgv
og:image: https://api.daily.dev/og/posts/fN7UvvLGv.png
og:image:alt: Post cover image
og:image:width: 1200
og:image:height: 630
og:locale: en
---

> ## Documentation Index
> Fetch the complete documentation index at: https://daily.dev/llms.txt
> Use this file to discover all available pages before exploring further.

# Qwen3.8-27B-pi-adapted: a LoRA adapter tuned for the pi coding agent

**[Qwen](https://daily.dev/sources/qwen)** · [@nerdalytics](https://daily.dev/nerdalytics) · 5 upvotes · 0 comments

## Summary

Qwen3.8-27B-pi-adapted, a LoRA adapter that tunes Qwen's 27B model for the pi coding agent using reinforcement learning, was announced by @ClementDelangue. On SWE-bench Pro (Hard 51), pass@1 jumped from 29.4% to 62.7%. Terminal-Bench 2.1 rose from 39.5% to 55.8%, and tool calls per task dropped 55-62%. Open weights and a methodology write-up were announced alongside the release. The big jumps are on a single harness, so it's worth checking whether they hold up on your own tasks.

## Full article

daily.dev links to this article rather than hosting it. Read it at the original source: <https://daily.dev/posts/fn7uvvlgv>

## Similar posts on daily.dev

- [GitHub - Danau5tin/ai-trains-ai: RL-training an AI agent to RL-train AI agents.](https://daily.dev/posts/github---danau5tin-ai-trains-ai-rl-training-an-ai-agent-to-rl-train-ai-agents--gqshn7as2) · Hacker News · 0 upvotes · 0 comments
- [How to Customize an LLM for AI Agents using SFT and QLoRA](https://daily.dev/posts/how-to-customize-an-llm-for-ai-agents-using-sft-and-qlora-jeancs7na) · freeCodeCamp · 0 upvotes · 0 comments
- [Qwen-VLA: The AI Model That Sees, Thinks, and Acts](https://daily.dev/posts/qwen-vla-the-ai-model-that-sees-thinks-and-acts-uv9ejhq1d) · C\# Corner · 0 upvotes · 0 comments

---

Tags: [#ai](https://daily.dev/tags/ai), [#ai-agents](https://daily.dev/tags/ai-agents), [#reinforcement-learning](https://daily.dev/tags/reinforcement-learning), [#qwen](https://daily.dev/tags/qwen), [#lora](https://daily.dev/tags/lora)

[View this post on daily.dev](https://daily.dev/posts/fn7uvvlgv)

```json
{"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]}
{"@context":"https://schema.org","@type":"DiscussionForumPosting","mainEntityOfPage":"https://daily.dev/posts/fn7uvvlgv","headline":"Qwen3.8-27B-pi-adapted: a LoRA adapter tuned for the pi coding agent","text":"Shared: Qwen3.8-27B-pi-adapted: a LoRA adapter tuned for the pi coding agent","url":"https://daily.dev/posts/fn7uvvlgv","datePublished":"2026-11-19T05:26:58.303Z","dateModified":"2026-11-19T05:26:58.310Z","author":{"@type":"Person","name":"nerdalytics","url":"https://daily.dev/nerdalytics","image":"https://avatars.githubusercontent.com/u/97166791?v=4","description":"Husband. Cat and dog dad. Nerd.","interactionStatistic":{"@type":"InteractionCounter","interactionType":{"@type":"EndorseAction"},"userInteractionCount":14050}},"image":"https://media.daily.dev/image/upload/s--2-1xRawN--/f_auto/v1722860399/public/Placeholder%2011","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":5},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"sharedContent":{"@type":"WebPage","url":"https://api.daily.dev/r/NteXKkcg7"},"isPartOf":{"@type":"WebPage","url":"https://daily.dev/squads/qwen","name":"Qwen"}}
{"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Qwen","item":"https://daily.dev/squads/qwen"},{"@type":"ListItem","position":3,"name":"Qwen3.8-27B-pi-adapted: a LoRA adapter tuned for the pi coding agent"}]}
```

