arXiv · cs.AI · Allan Grosvenor, Anton Zemlyansky, Abdul Wahab, Kyrylo Bohachov, Aras Dogan, Ryland Adams, Dwyer Deighan · 11 小时前模型评分52
GURU：面向关键任务工程的分层神经符号多智能体系统
GURU: A Hierarchical Neuro-Symbolic Multi-Agent System for Verification-Aware Automation of Mission-Critical Digital Engineering and Operations
导读
作者提出 GURU 分层神经符号多智能体系统，把权限拆成三层：学习模型负责提议、排序和加速，符号规则引擎在执行前用硬性限制检查每个有后果的动作，经验证的物理模型负责确认和决策。
分类置信度
中 · 待人工复核
- 存在未解决的相邻类别：ai-tooling、vertical-solutions，需要人工复核。
- 只有单一媒体来源，需要人工复核。
来源级别：媒体与个人
应用领域：能源、交通与物流、政务与公共事务、制造与工业、科学研究
事件类型：研究发布
证据摘录
- “We present GURU, a hierarchical neuro-symbolic multi-agent system for mission-critical digital engineering and operations, built on one partition of authority: learned models propose, rank, and accelerate; a symbolic rules engine checks every consequential action against hard limits before it executes; and validated physics confirms and decides.”
来源：arXiv · cs.AI · arxiv.org