Project Riley：具有情感推理与投票机制的多模态多智能体大语言模型协作
Project Riley: Multimodal Multi-Agent LLM Collaboration with Emotional Reasoning and Voting
AI总结：
Project Riley提出一种受《头脑特工队》启发的多智能体LLM架构，通过五个情感智能体对话与投票机制模拟情感推理，并衍生出应急原型Armando，经用户测试验证了情感对齐与沟通清晰度方面的良好性能。
摘要：
本文介绍了Project Riley，一种新颖的多模态、多模型对话式AI架构，旨在模拟受情感状态影响的推理过程。该系统从皮克斯电影《头脑特工队》中汲取灵感，由五个不同的情感智能体组成——Joy（喜悦）、Sadness（悲伤）、Fear（恐惧）、Anger（愤怒）和Disgust（厌恶）——它们通过结构化的多轮对话来生成、批评并迭代优化回复。最终推理机制将这些智能体的贡献综合成一个连贯的输出，该输出要么反映主导情感，要么整合多种视角。该架构融合了文本和视觉大语言模型（LLM），以及先进的推理和自我精炼过程。一个功能原型已在本地离线环境中部署，针对情感表达能力和计算效率进行了优化。从这个初始原型中，衍生出另一个名为Armando的原型，该原型专为应急场景开发，通过集成检索增强生成（RAG）和累积上下文跟踪，提供情感校准且事实准确的信息。Project Riley原型通过用户测试进行了评估，参与者与聊天机器人互动，并完成了一份结构化问卷，评估三个维度：情感适当性、清晰度与实用性，以及自然度与类人程度。结果表明，该系统在结构化场景中表现强劲，尤其在情感对齐和沟通清晰度方面表现出色。
英文摘要：
This paper presents Project Riley, a novel multimodal and multi-model conversational AI architecture oriented towards the simulation of reasoning influenced by emotional states. Drawing inspiration from Pixar's Inside Out, the system comprises five distinct emotional agents - Joy, Sadness, Fear, Anger, and Disgust - that engage in structured multi-round dialogues to generate, criticise, and iteratively refine responses. A final reasoning mechanism synthesises the contributions of these agents into a coherent output that either reflects the dominant emotion or integrates multiple perspectives. The architecture incorporates both textual and visual large language models (LLMs), alongside advanced reasoning and self-refinement processes. A functional prototype was deployed locally in an offline environment, optimised for emotional expressiveness and computational efficiency. From this initial prototype, another one emerged, called Armando, which was developed for use in emergency contexts, delivering emotionally calibrated and factually accurate information through the integration of Retrieval-Augmented Generation (RAG) and cumulative context tracking. The Project Riley prototype was evaluated through user testing, in which participants interacted with the chatbot and completed a structured questionnaire assessing three dimensions: Emotional Appropriateness, Clarity and Utility, and Naturalness and Human-likeness. The results indicate strong performance in structured scenarios, particularly with respect to emotional alignment and communicative clarity.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
