This repository contains a LoRA adapter for
meituan/EvoCUA-8B-20260105 specialized for the
GIMP desktop domain. It was developed using
LearnWeak, an annotation-free specialization framework for small computer-use agents (CUAs).
LearnWeak identifies a student agent's weaknesses in a specific software domain using a stronger reference agent (teacher). It then synthesizes targeted tasks and constructs automated supervision. LearnWeak further introduces an error-aware specialization objective that disentangles planning and execution errors, enabling more behaviorally precise updates than broad uniform supervision.
This specific adapter improves the performance of the 8B student agent on tasks related to the GIMP image editor.
You can use this adapter with
vLLM by enabling LoRA support and providing the module name:
1vllm serve meituan/EvoCUA-8B-20260105 \
2 --enable-lora \
3 --max-lora-rank 32 \
4 --lora-modules learnweak-gimp=SujiKim/learnweak-evocua-8b-lora-r32-gimp
1@article{kim2026learnweaknessesautomateddomain,
2 title = {Learn from Weaknesses: Automated Domain Specialization for Small Computer-Use Agents},
3 author = {Kim, Suji and Kim, Kangsa and Hwang, Sung Ju},
4 journal = {arXiv preprint arXiv:2605.28775},
5 year = {2026}
6}
