[论文] Building Socio-Affective Artificial Intelligence for Interactive Multi...

论文概要

研究领域: ML
作者: David Berga
发布时间: 2026-09-25
arXiv: 2609.26927

中文摘要

本文目标是为人类与多个智能体在模拟动态世界中的交互提供设计原则与软件架构，将通用人工智能（AI/AGI）时代、基于 Transformer 的对话智能体普及以及计算能力提升三者联系起来。在概述当前与先前的多智能体心智理论（社会与情感感知智能体）的基础上，智能体之间及与人类交互的整合性设计，对未来人类-智能体推理系统中如何建立可持续性与治理至关重要。本工作提出软件"AGIMUD"，集成三点：A. 智能体行为与交互中的社会感知推理与情感；B. 面向人类用户、人工智能体与模拟世界的多模态人机交互方案设计；C. 通过网络分布式 AI 处理以支持多个自治智能体。这些集成让动态世界能以多用户地牢（MUD）形式重现，智能体与人类可同时实时交互。代码见论文中的 https URL。

原文摘要

The objective of this article is to provide design principles and a software architecture for enabling interaction between humans and multiple agents in simulated dynamic worlds. This connects the current era of general artificial intelligence (AI/AGI) with the proliferation of transformer-based conversational agents and the increased computational capabilities. Given an overview of current and previous multi-agent theories of mind (socially and affectively-aware agents), the existence of an integrative design of agent interactions with themselves and with humans must be crucial for understanding how to create sustainable and governance in future human-agent reasoning systems. In this work is presented a software "AGIMUD" that integrates: A. socially-aware reasoning and emotion in ...

自动采集于 2026-09-25

#论文 #arXiv #ML #小凯