AICVNov 17, 2025

Yanyun-3: Enabling Cross-Platform Strategy Game Operation with Vision-Language Models

arXiv:2511.12937v1
Originality Highly original
AI Analysis

This work provides an efficient solution for strategy game automation and establishes a general paradigm for enhancing VLM performance through structured multimodal data organization.

The paper tackled the problem of enabling autonomous cross-platform operation in strategy games by introducing Yanyun-3, a framework that integrates vision-language models with UI execution, achieving a 63% reduction in inference time and a 12.98x boost in BLEU-4 score.

Automated operation in cross-platform strategy games demands agents with robust generalization across diverse user interfaces and dynamic battlefield conditions. While vision-language models (VLMs) have shown considerable promise in multimodal reasoning, their application to complex human-computer interaction scenarios--such as strategy gaming--remains largely unexplored. Here, we introduce Yanyun-3, a general-purpose agent framework that, for the first time, enables autonomous cross-platform operation across three heterogeneous strategy game environments. By integrating the vision-language reasoning of Qwen2.5-VL with the precise execution capabilities of UI-TARS, Yanyun-3 successfully performs core tasks including target localization, combat resource allocation, and area control. Through systematic ablation studies, we evaluate the effects of various multimodal data combinations--static images, multi-image sequences, and videos--and propose the concept of combination granularity to differentiate between intra-sample fusion and inter-sample mixing strategies. We find that a hybrid strategy, which fuses multi-image and video data while mixing in static images (MV+S), substantially outperforms full fusion: it reduces inference time by 63% and boosts the BLEU-4 score by a factor of 12 (from 4.81% to 62.41%, approximately 12.98x). Operating via a closed-loop pipeline of screen capture, model inference, and action execution, the agent demonstrates strong real-time performance and cross-platform generalization. Beyond providing an efficient solution for strategy game automation, our work establishes a general paradigm for enhancing VLM performance through structured multimodal data organization, offering new insights into the interplay between static perception and dynamic reasoning in embodied intelligence.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes