让机器人像人一样思考，快速响应又懂情绪。
MistyPilot: An Agentic Fast-Slow Thinking LLM Framework for Misty Social Robots
- 分快慢两种思维模式，智能选工具、调参数、执行任务
- 实测任务完成率高，对话更懂用户情绪，响应更快
- 适合想用机器人却不会编程的普通人或教育场景
随着社交机器人开放 API 的普及，定制通用工具以满足用户需求变得更加容易。然而，对于无编程经验的用户而言，理解高层指令、选择并配置合适工具，以及可靠执行任务仍是挑战。为此，我们提出 MistyPilot，一个基于代理式大模型的自主工具选择、编排与参数配置框架。MistyPilot 包含两个核心组件：物理交互代理（PIA）实现鲁棒的传感器触发与工具驱动任务执行；社会智能代理（SIA）生成具社会性与情感契合度的对话。框架进一步融合快-慢思维范式，捕捉用户偏好，降低延迟，提升任务效率。为全面评估，我们构建了五个基准数据集。大量实验表明，该框架在任务路由正确性、任务完整性、快-慢思维检索效率、工具可扩展性及情感对齐方面均表现优异。所有代码、数据集及实验视频将公开于项目主页。
原文摘要 · Abstract (English)
With the availability of open APIs in social robots, it has become easier to customize general-purpose tools to meet users' needs. However, interpreting high-level user instructions, selecting and configuring appropriate tools, and executing them reliably remain challenging for users without programming experience. To address these challenges, we introduce MistyPilot, an agentic LLM-driven framework for autonomous tool selection, orchestration, and parameter configuration. MistyPilot comprises two core components: a Physically Interactive Agent (PIA) and a Socially Intelligent Agent (SIA). The PIA enables robust sensor-triggered and tool-driven task execution, while the SIA generates socially intelligent and emotionally aligned dialogue. MistyPilot further integrates a fast-slow thinking paradigm to capture user preferences, reduce latency, and improve task efficiency. To comprehensively evaluate MistyPilot, we contribute five benchmark datasets. Extensive experiments demonstrate the effectiveness of our framework in routing correctness, task completeness, fast-slow thinking retrieval efficiency, tool scalability,and emotion alignment. All code, datasets, and experimental videos will be made publicly available on the project webpage.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。