揭示嵌入防御在LLM多代理系统中的根本性失效，提出安全范式新思考
arXiv:2605.01133v2 Announce Type: replace-cross Abstract: Large language model (LLM)-powered multi-agent systems (MAS) enable agents to communicate an…
AI Agent的每个功能都是潜在缓存失效点，揭示RAG与多代理架构的陷阱与反思
Article URL: https://www.openclacky.com/engineering/cache-invalidation-surface Comments URL: https://news.ycombinator.com/item?id=48426050 Points: 2 #…
下一代LLM代理能否超越前代的合作偏见？跨提供商的实证博弈揭示多智能体系统的均衡新面貌。
arXiv:2605.29874v1 Announce Type: cross Abstract: Do next-generation LLM agents inherit the cooperative biases documented in their predecessors, or do…
架构升级比提示工程更有效：7节点专业路由多智能体系统在临床基准上实现飞跃
arXiv:2605.24699v1 Announce Type: new Abstract: Most reported gains on agentic-LLM clinical benchmarks are often attributed to prompt engineering, yet…