# AI 24 Updates · 2026-11-20-1600

Published: November 20, 2026 · 15:57 CET

## In Brief

- Hugging Face — harness adapters: RL-trained LoRAs for Qwen3.8-27B in pi, Hermes Agent and OpenCode

---

## 1. Hugging Face — harness adapters: RL-trained LoRAs for Qwen3.8-27B in pi, Hermes Agent and OpenCode

Company: Hugging Face

Hugging Face trained a LoRA adapter for Qwen3.8-27B inside each of three agent harnesses and merged them into one super-adapter, all released on the Hub.

**Facts:**
- Hugging Face released one LoRA adapter for Qwen3.8-27B per agent harness — pi, Hermes Agent and OpenCode — each trained with reinforcement learning inside the harness itself.
- Datasets, training and agent rollouts ran on Hugging Face Jobs with TRL's AsyncGRPOTrainer, OpenEnv and Harbor; training totalled 598 steps and 167M tokens.
- Each adapter beats the base model under its own harness on Terminal-Bench 2.1 and the 51 hardest SWE-bench Pro tasks; under pi on SWE-bench Pro, the score rises from 40.0% to 64.0%.
- The three LoRAs are also merged into a single rank-96 super-adapter (each update at weight ½) that runs unchanged under pi, Hermes Agent and OpenCode.
- The adapters, GGUF files, RL tasks and the safeagents plugin are published in a Hugging Face collection.

**Sources:**
- [Hugging Face blog](https://huggingface.co/blog/harness-adapters-at-scale)
- [Hugging Face collection](https://huggingface.co/collections/harness-hub/qwen38-27b-harness-adapters)
