腾讯 Gander：边对话边后台处理任务的实时智能体模型
原标题：Tencent's Gander aims to keep talking while it works in the background
AI 摘要
腾讯混元语音团队与多所大学研究者提出 Gander 模型，可在后台处理复杂任务的同时保持实时对话，同时处理语音、图像和文本，用户可随时打断。该模型采用「小脑」负责逐秒对话、「大脑」负责复杂智能体任务的可替换架构，大脑可换成 Codex 或 Claude Code 等系统而无需重训对话模型。测试中 Gander 在 Full-Duplex-Bench v3 上打断时机表现最佳，但任务准确率及视频、音频理解偏弱。团队计划开源模型权重和训练数据，代码 GitHub 仓库已存在。
正文节选
Tencent's Gander aims to keep talking while it works in the background Key Points - Tencent's Gander is designed to hold real-time conversations while handling complex tasks in the background. It processes speech, images, and text simultaneously, and users can interrupt at any time. - A "cerebellum" manages the conversation second by second, while a swappable "brain" handles complex agent tasks. The split aims to keep responses fast without cutting planning short. - In tests, Gander interrupted