This repository contains a domain-specialized LoRA adapter for EvoCUA-8B, developed as part of the LearnWeak framework.

LearnWeak is an annotation-free specialization framework for small computer-use agents (CUAs). It uses a stronger reference agent to identify a student model's weaknesses in a target domain, synthesizes targeted tasks, and constructs supervision automatically. This model focuses on specializing the agent for desktop software environments.

Small open computer-use agents are practical specialization targets but often exhibit domain-specific failures. LearnWeak introduces an error-aware specialization objective that disentangles planning and execution errors, enabling more behaviorally precise updates. On OSWorld, LearnWeak achieves significant performance gains across various domains such as GIMP, LibreOffice, and VS Code.

You can serve the base model with this LoRA adapter enabled using vLLM. Replace the LoRA module name and path as appropriate for the specific domain:

Use the LoRA module name (e.g., learnweak-adapter) when calling the served model's API.

If you find this work useful, please consider citing:

This project builds on OSWorld, LlamaFactory, and EvoCUA.