learnweak-evocua-8b-lora-r32-vlc

learnweak-evocua-8b-lora-r32-gimp

This repository contains a LoRA adapter for meituan/EvoCUA-8B-20260105, specialized for the GIMP desktop domain using 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 to improve agent performance.

• Project Page: https://learnweak.github.io/
• Paper: Learn from Weaknesses: Automated Domain Specialization for Small Computer-Use Agents
• Repository: https://github.com/sujiikim/LearnWeak

Usage

Serve with vLLM

You can serve the base model with this LoRA adapter using vLLM:

vllm serve meituan/EvoCUA-8B-20260105 \
  --enable-lora \
  --max-lora-rank 32 \
  --lora-modules learnweak-gimp=SujiKim/learnweak-evocua-8b-lora-r32-gimp

Use the LoRA module name learnweak-gimp when calling the served model.

Training Details

LearnWeak introduces an error-aware specialization objective that disentangles planning and execution errors, enabling more behaviorally precise updates than broad uniform supervision. This adapter was trained to overcome specific domain failures identified during the student-aware dataset generation process.

Citation

@article{kim2026learnweaknessesautomateddomain,
  title   = {Learn from Weaknesses: Automated Domain Specialization for Small Computer-Use Agents},
  author  = {Kim, Suji and Kim, Kangsa and Hwang, Sung Ju},
  journal = {arXiv preprint arXiv:2605.28775},
  year    = {2026}
}

Acknowledgments

This project builds on OSWorld, LlamaFactory, and EvoCUA.