Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Wang, Guoyan, Huang, Yanyan, Chen, Chunlin, Wang, Lifeng, Sun, Yuxiang
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2511.12937
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866912727316824064
author Wang, Guoyan
Huang, Yanyan
Chen, Chunlin
Wang, Lifeng
Sun, Yuxiang
author_facet Wang, Guoyan
Huang, Yanyan
Chen, Chunlin
Wang, Lifeng
Sun, Yuxiang
contents Cross-platform strategy game automation remains a challenge due to diverse user interfaces and dynamic battlefield environments. Existing Vision--Language Models (VLMs) struggle with generalization across heterogeneous platforms and lack precision in interface understanding and action execution. We introduce Yanyun-3, a VLM-based agent that integrates Qwen2.5-VL for visual reasoning and UI-TARS for interface execution. We propose a novel data organization principle -- combination granularity -- to distinguish intra-sample fusion and inter-sample mixing of multimodal data (static images, multi-image sequences, and videos). The model is fine-tuned using QLoRA on a curated dataset across three strategy game platforms. The optimal strategy (M*V+S) achieves a 12.98x improvement in BLEU-4 score and a 63% reduction in inference time compared to full fusion. Yanyun-3 successfully executes core tasks (e.g., target selection, resource allocation) across platforms without platform-specific tuning. Our findings demonstrate that structured multimodal data organization significantly enhances VLM performance in embodied tasks. Yanyun-3 offers a generalizable framework for GUI automation, with broader implications for robotics and autonomous systems.
format Preprint
id arxiv_https___arxiv_org_abs_2511_12937
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Yanyun-3: Enabling Cross-Platform Strategy Game Operation with Vision-Language Models
Wang, Guoyan
Huang, Yanyan
Chen, Chunlin
Wang, Lifeng
Sun, Yuxiang
Artificial Intelligence
Computer Vision and Pattern Recognition
I.2.7; I.2.10; I.6.8; H.5.2
Cross-platform strategy game automation remains a challenge due to diverse user interfaces and dynamic battlefield environments. Existing Vision--Language Models (VLMs) struggle with generalization across heterogeneous platforms and lack precision in interface understanding and action execution. We introduce Yanyun-3, a VLM-based agent that integrates Qwen2.5-VL for visual reasoning and UI-TARS for interface execution. We propose a novel data organization principle -- combination granularity -- to distinguish intra-sample fusion and inter-sample mixing of multimodal data (static images, multi-image sequences, and videos). The model is fine-tuned using QLoRA on a curated dataset across three strategy game platforms. The optimal strategy (M*V+S) achieves a 12.98x improvement in BLEU-4 score and a 63% reduction in inference time compared to full fusion. Yanyun-3 successfully executes core tasks (e.g., target selection, resource allocation) across platforms without platform-specific tuning. Our findings demonstrate that structured multimodal data organization significantly enhances VLM performance in embodied tasks. Yanyun-3 offers a generalizable framework for GUI automation, with broader implications for robotics and autonomous systems.
title Yanyun-3: Enabling Cross-Platform Strategy Game Operation with Vision-Language Models
topic Artificial Intelligence
Computer Vision and Pattern Recognition
I.2.7; I.2.10; I.6.8; H.5.2
url https://arxiv.org/abs/2511.12937