为AI智能体与工具交互提供声明式安全策略，通过预准入审查机制有效防范风险，是智能体安全领域的前沿方案
arXiv:2607.21835v1 Announce Type: cross Abstract: LLM agents increasingly rely on external tools, expanding capability while creating a new security b…
开源授权引擎Lelu，专为AI代理设计，支持置信度感知和策略驱动，从个人项目到生产集群都能用。
Article URL: https://lelu-ai.com Comments URL: https://news.ycombinator.com/item?id=48299318 Points: 1 # Comments: 0
探索基于策略驱动的运行时层，为Agentic LLM服务提供高效可扩展的系统架构方案
arXiv:2605.27744v1 Announce Type: new Abstract: Multi-agent LLM systems have become the dominant production workload, but the serving stack was not bu…