LLMs是通用异步智能体
LLMs are General Asynchronous Agents
浏览论文内容
中文总结 AI 辅助
本文提出通用异步智能体概念，开发异步LLM框架支持重叠内存协程，使Qwen 3.x模型无需任务特定训练即可处理流式视频、游戏和监控等并发任务。
中文摘要 AI 辅助
现代LLM作为自主智能体的能力日益增强，但它们遵循顺序交互循环：读取、思考、回复或调用工具，然后重复。许多现实世界的用例并非顺序性的：语音助手、具身智能体和监控系统在思考或执行另一任务时会接收到新输入。现代LLM通过针对语音交互和视频流的专用架构、用于机器人控制的VLA、用于API使用的异步工具调用等方式来解决这一问题。在这项工作中，我们从不同的异步任务中泛化出能够适应不同类型并发性的通用异步智能体。为实现这一目标，我们开发了一个异步LLM框架，允许用户（或智能体自身）定义具有重叠内存状态的推理协程。我们展示了Qwen 3.x模型能够执行异步操作，用于流式视频理解、视频游戏和监控，而无需针对特定任务的训练。
英文摘要
Modern LLMs are increasingly capable as autonomous agents, but they follow sequential interaction cycles: read, think, reply or call tools, repeat. Many real-world use cases are not sequential: voice assistants, embodied agents, and monitoring systems receive new inputs while they think or perform another task. Modern LLMs address this with specialized architectures for voice interaction and video streams, VLAs for robot control, asynchronous tool calling for API usage, and others. In this work, we generalize from different asynchronous tasks to general asynchronous agents that can adapt to different types of concurrency. To achieve this, we develop an asynchronous LLM framework that lets users (or the agents themselves) define inference coroutines with overlapping memory states. We showcase that Qwen 3.x models are capable of asynchronous operation for streaming video understanding, videogames, and monitoring, without task-specific training.
发表机构
- Yandex
- Together AI
- HSE University（高等经济大学）
- Yandex School of Data Analysis（Yandex数据分析学院）
机构由 AI 辅助整理，请以论文原文为准。
