MOBA-VL：面向实时MOBA解说的事件定位多轮强化学习
MOBA-VL: Event-Localized Multi-Turn Reinforcement Learning for Real-Time MOBA Commentary
浏览论文内容
中文总结 AI 辅助
提出MOBA-VL，利用游戏遥测和事件定位多轮强化学习提升MOBA实时解说的关键事件召回，在MOBACast-Bench上取得最优性能。
中文摘要 AI 辅助
多人在线战术竞技（MOBA）电竞的实时解说要求视觉语言模型（VLM）每秒流畅且准确地叙述现场比赛。现有的流式VLM听起来自然，但常常遗漏关键事件，如击杀和战略目标。为解决这一局限，我们利用游戏遥测数据——它精确记录每个事件发生的时间——作为监督信号。我们提出MOBA-VL，一个基于该信号训练的9B参数模型，采用事件定位的多轮强化学习，奖励描述每个事件的回合。我们还收集了MOBACast，包含三款MOBA游戏的860场职业比赛（约460小时），配有词级时间戳的解说，以及MOBACast-Bench，一个来自留出锦标赛的基准。在MOBACast-Bench上，MOBA-VL在全场比赛（63.25对StreamingVLM的55.12）和片段（63.45对DeepSeek-V4.1-Flash的56.22）中均取得最高Overall分数。事件定位的信用分配还将事件召回率从34.5提升至42.1，优于监督微调。代码和数据将发布，演示可在匿名项目页面（此https URL）获取。
英文摘要
Real-time commentary for Multiplayer Online Battle Arena (MOBA) esports requires a vision-language model (VLM) to narrate a live match second by second, both fluently and accurately. Existing streaming VLMs sound natural but often miss key events such as kills and objectives. To address this limitation, we use game telemetry, which records exactly when each event occurs, as a supervision signal. We introduce MOBA-VL, a 9B-parameter model trained on this signal with event-localized multi-turn reinforcement learning, which rewards the turns that describe each event. We also collect MOBACast, 860 professional matches (about 460 hours) across three MOBA games with word-level timestamped commentary, and MOBACast-Bench, a benchmark from held-out tournaments. On MOBACast-Bench, MOBA-VL achieves the highest Overall score on full matches (63.25 vs. 55.12 for StreamingVLM) and clips (63.45 vs. 56.22 for DeepSeek-V4.1-Flash). Event-localized credit also raises event recall from 34.5 to 42.1 over supervised fine-tuning. Code and data will be released, and demos are available on an anonymous project page at https://moba-vl.github.io.
发表机构
- Zhejiang University（浙江大学）
- Northeastern University（东北大学）
机构由 AI 辅助整理，请以论文原文为准。
