BirdsongChat：多模态具身行为模拟的混合多智能体框架
原标题：BirdsongChat: A Hybrid Multi-Agent Framework for Multimodal Embodied Behavior Simulation
AI 摘要
研究者提出 BirdsongChat，一个混合多智能体框架，用于多模态具身行为模拟。该框架通过统一参数表示（UPR）将基于 LLM 的推理智能体与物理模拟智能体连接，把多模态输入转化为可解释的行为状态和控制参数，从而生成同步的 3D 运动、空间化声音和环境行为。原型系统以鸟类行为模拟为测试平台，在文本和图像引导场景中取得跨模态一致性 94.4%、情感一致性 100%、生成一致性 92.6% 的归一化得分，表明显式中间表示能有效桥接语义推理与物理执行。
正文节选
BirdsongChat: A Hybrid Multi-Agent Framework for Multimodal Embodied Behavior Simulation Abstract Multimodal embodied systems require translating human intentions into interpretable and coordinated behaviors across heterogeneous modalities. However, existing multimodal agents often rely on implicit representations, limiting controllability and cross-modal consistency. We present a hybrid multi-agent framework for interactive multimodal behavior simulation that bridges semantic reasoning and phys