高效视觉语言动作模型，让游戏战斗更智能更快。
CombatVLA: An Efficient Vision-Language-Action Model for Combat Tasks in 3D Action Role-Playing Games
- 基于动作思维序列训练30亿参数模型，实现精准战术理解。
- 比现有模型快50倍，战斗成功率超人类玩家。
- 专为3D动作角色扮演设计，适合游戏AI研究者使用。
视觉-语言-动作模型（VLAs）在具身智能领域取得进展，但在复杂3D环境中仍面临实时决策挑战，需秒级响应、高分辨率感知与动态条件下的策略推理。为此，我们提出CombatVLA，一个针对3D动作角色扮演游戏（ARPG）战斗任务优化的高效VLA模型。该模型为30亿参数规模，基于动作追踪器采集的视频-动作对数据训练，数据格式为动作思维（AoT）序列。通过引入截断式AoT策略，CombatVLA可无缝集成至动作执行框架，实现高效推理。实验表明，CombatVLA不仅在战斗理解基准上超越所有现有模型，且在游戏战斗中实现50倍加速，任务成功率高于人类玩家。所有资源（包括动作追踪器、数据集、基准、模型权重、训练代码及框架实现）将开源，详见https://combatvla.github.io/。
原文摘要 · Abstract (English)
Recent advances in Vision-Language-Action models (VLAs) have expanded the capabilities of embodied intelligence. However, significant challenges remain in real-time decision-making in complex 3D environments, which demand second-level responses, high-resolution perception, and tactical reasoning under dynamic conditions. To advance the field, we introduce CombatVLA, an efficient VLA model optimized for combat tasks in 3D action role-playing games(ARPGs). Specifically, our CombatVLA is a 3B model trained on video-action pairs collected by an action tracker, where the data is formatted as action-of-thought (AoT) sequences. Thereafter, CombatVLA seamlessly integrates into an action execution framework, allowing efficient inference through our truncated AoT strategy. Experimental results demonstrate that CombatVLA not only outperforms all existing models on the combat understanding benchmark but also achieves a 50-fold acceleration in game combat. Moreover, it has a higher task success rate than human players. We will open-source all resources, including the action tracker, dataset, benchmark, model weights, training code, and the implementation of the framework at https://combatvla.github.io/.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。