PUBG Ally：作为AI队友的对话式具身智能体
PUBG Ally: A Conversational Embodied Agent as an AI Teammate
中文总结 AI 辅助
本文提出PUBG Ally，一种语音交互的具身智能体队友，结合语言模型推理与实时控制，利用近3.9万场真实对局数据训练，并通过在线评估与部署优化，获得玩家广泛认可。
中文摘要 AI 辅助
我们介绍了PUBG Ally，一个用于《绝地求生》的具身智能体，它能够推理、自主行动，并作为支持语音的队友与玩家并肩作战。构建这样的队友需要结合两种困难的能力：它必须在严格的延迟约束下感知并响应不断变化的游戏世界，同时与玩家自然互动，使其语音与动作保持同步。因此，Ally将智能体工具使用与实时游戏控制相结合。一个语言模型智能体通过受控接口检查游戏信息、解析玩家语音、维护上下文、决定要说什么，并发出高级行动选择，以引导一个更快的控制层进行移动、战斗和恢复。由于玩家和Ally的语音与行动不断相互影响并塑造比赛进程，训练需要来自实际游戏对局的数据。因此，我们在近39000场真实玩家与Ally并肩作战的会话中收集数据，记录游戏过程、玩家语音、智能体决策、工具使用、行动和玩家反馈，并利用这些记录进行迭代训练。为了评估队友质量，我们使用玩家反馈和偏好比较来识别离线评估与玩家偏好之间的差距，并迭代完善评估标准。在实时服务中部署Ally还需要低延迟的端侧执行和面向玩家的通信保障，我们通过模型压缩、上下文精简、针对性安全训练、运行时护栏和内存擦除来解决这些问题。在实时服务期间，我们调查了141个国家的玩家。在游戏记录中确认与Ally一起游玩的受访者中，当被问及是否会推荐Ally时，正面回应超过负面回应25.1个百分点，玩家不仅将Ally描述为工具，还将其视为队友或伙伴。
英文摘要
We introduce PUBG Ally, an embodied agent for PUBG: BATTLEGROUNDS that can reason, act autonomously, and play alongside players as a voice-enabled teammate. Building such a teammate requires combining two difficult capabilities: it must perceive and respond to a constantly changing game world under strict latency constraints while interacting naturally with players, keeping its speech synchronized with its actions. Ally therefore combines agentic tool use with real-time game control. A language-model agent uses a controlled interface to inspect game information, interpret player speech, maintain context, decide what to say, and issue high-level action choices that steer a faster control layer for movement, combat, and recovery. Because the player's and Ally's speech and actions continually shape each other and the course of the match, training requires data from actual gameplay. We therefore collect data across nearly 39k sessions in which real players play alongside Ally, recording gameplay, player speech, agent decisions, tool use, actions, and player feedback, and use these records for iterative training. To evaluate teammate quality, we use player feedback and preference comparisons to identify gaps between offline evaluations and player preferences, and iteratively refine the evaluation criteria. Deploying Ally in live service further requires low-latency on-device execution and safeguards for player-facing communication, which we address through model compression, context compaction, targeted safety training, runtime guardrails, and memory redaction. During the live service, we surveyed players in 141 countries. Among respondents whose play with Ally was confirmed in game records, positive responses exceeded negative responses by 25.1 percentage points when asked whether they would recommend Ally, with players describing Ally not only as a tool but also as a teammate or companion.
