UI-Ins: Enhancing GUI Grounding with Multi-Perspective Instruction-as-Reasoning
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912665851396096 |
|---|---|
| author | Chen, Liangyu Zhou, Hanzhang Cai, Chenglin Zhang, Jianan Tong, Panrong Kong, Quyu Zhang, Xu Liu, Chen Liu, Yuqi Wang, Wenxuan Wang, Yue Jin, Qin Hoi, Steven |
| author_facet | Chen, Liangyu Zhou, Hanzhang Cai, Chenglin Zhang, Jianan Tong, Panrong Kong, Quyu Zhang, Xu Liu, Chen Liu, Yuqi Wang, Wenxuan Wang, Yue Jin, Qin Hoi, Steven |
| contents | GUI grounding, which maps natural-language instructions to actionable UI elements, is a core capability of GUI agents. Prior works largely treats instructions as a static proxy for user intent, overlooking the impact of instruction diversity and quality on grounding performance. Through a careful investigation of existing grounding datasets, we find a 23.3% flaw rate in their instructions and show that inference-time exploitation of instruction diversity yields up to a substantial 76% relative performance improvement. In this paper, we introduce the Instruction-as-Reasoning paradigm, treating instructions as dynamic analytical pathways that offer distinct perspectives and enabling the model to select the most effective pathway during reasoning. To achieve this, we propose a two-stage training framework: supervised fine-tuning (SFT) on synthesized, diverse instructions to instill multi-perspective reasoning, followed by reinforcement learning (RL) to optimize pathway selection and composition. Our resulting models, UI-Ins-7B and UI-Ins-32B, achieve state-of-the-art results on five challenging grounding benchmarks and exhibit emergent reasoning, selectively composing and synthesizing novel instruction pathways at inference. In particular, UI-Ins-32B attains the best grounding accuracy, scoring 87.3% on UI-I2E-Bench, 57.0% on ScreenSpot-Pro, and 84.9% on MMBench-GUI L2. Furthermore, our model demonstrates strong agentic potential, achieving a 74.1% success rate on AndroidWorld using UI-Ins-7B as the executor. Our in-depth analysis reveals additional insights such as how reasoning can be formulated to enhance rather than hinder grounding performance, and how our method mitigates policy collapse in the SFT+RL framework. All code and model checkpoints will be publicly released in https://github.com/alibaba/UI-Ins. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_20286 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | UI-Ins: Enhancing GUI Grounding with Multi-Perspective Instruction-as-Reasoning Chen, Liangyu Zhou, Hanzhang Cai, Chenglin Zhang, Jianan Tong, Panrong Kong, Quyu Zhang, Xu Liu, Chen Liu, Yuqi Wang, Wenxuan Wang, Yue Jin, Qin Hoi, Steven Computer Vision and Pattern Recognition Artificial Intelligence GUI grounding, which maps natural-language instructions to actionable UI elements, is a core capability of GUI agents. Prior works largely treats instructions as a static proxy for user intent, overlooking the impact of instruction diversity and quality on grounding performance. Through a careful investigation of existing grounding datasets, we find a 23.3% flaw rate in their instructions and show that inference-time exploitation of instruction diversity yields up to a substantial 76% relative performance improvement. In this paper, we introduce the Instruction-as-Reasoning paradigm, treating instructions as dynamic analytical pathways that offer distinct perspectives and enabling the model to select the most effective pathway during reasoning. To achieve this, we propose a two-stage training framework: supervised fine-tuning (SFT) on synthesized, diverse instructions to instill multi-perspective reasoning, followed by reinforcement learning (RL) to optimize pathway selection and composition. Our resulting models, UI-Ins-7B and UI-Ins-32B, achieve state-of-the-art results on five challenging grounding benchmarks and exhibit emergent reasoning, selectively composing and synthesizing novel instruction pathways at inference. In particular, UI-Ins-32B attains the best grounding accuracy, scoring 87.3% on UI-I2E-Bench, 57.0% on ScreenSpot-Pro, and 84.9% on MMBench-GUI L2. Furthermore, our model demonstrates strong agentic potential, achieving a 74.1% success rate on AndroidWorld using UI-Ins-7B as the executor. Our in-depth analysis reveals additional insights such as how reasoning can be formulated to enhance rather than hinder grounding performance, and how our method mitigates policy collapse in the SFT+RL framework. All code and model checkpoints will be publicly released in https://github.com/alibaba/UI-Ins. |
| title | UI-Ins: Enhancing GUI Grounding with Multi-Perspective Instruction-as-Reasoning |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2510.20286 |