智能AI None Evoflux:紧凑代理可执行工具工作流程的推理时间演化 12674v1 Announce Type: new Abstract: Compact language models (LMs) reduce cost, latency, and deployment risk for tool ag and tool that 2026-06-12 Kushal Raj Bhandari, Ling Yue, Ching-Yun Ko, Dhaval Patel, Shaowu Pan, Pin-Yu Chen, Jianxi Gao
安全攻防 None Veeam Backup & Replication RCE 漏洞可让域用户运行远程代码 Veeam has released security patches to address a critical flaw in its Backup & Replication software that could result in Veeam Backup remote 2026-06-10 info@thehackernews.com (The Hacker News)
智能AI None 用于执行轨迹上的推理时间对齐的工具 arXiv:2605.21516v1 Announce Type: new Abstract: Harness engineering has emerged as an important inference-time technique and execution decomposition 2026-05-23 Boyuan Wang, Bochao Li, Minghan Wang, Yuxin Tao, Fang Kong
智能AI None SDOF:通过状态约束调度降低多代理编排中的协调税 arXiv:2605.15204v1 Announce Type: new Abstract: Multi-agent orchestration frameworks such as LangChain, LangGraph, and C and the SDOF 2026-05-18 Zhantao Wang
智能AI None GraphBit:用于非线性代理编排的基于图的代理框架 arXiv:2605.13848v1 Announce Type: new Abstract: Agentic LLM frameworks that rely on prompted orchestration, where the mo and the that 2026-05-16 Yeahia Sarker, Md Rahmat Ullah, Musa Molla, Shafiq Joty
开发者生态 None 法学硕士正在打破 20 年前的系统设计 The ‘cloud-native’ architecture of the last decade is built on a 20-year-old assumption: that state lives in the databas the database and 2026-05-14 zknill
智能AI None PIVOT:通过轨迹细化在 LLM 代理中桥接规划和执行 arXiv:2605.11225v1 Announce Type: new Abstract: Large language model (LLM)-based agents frequently generate seemingly co that execution and 2026-05-13 Tuo Zhang, Alin-Ionut Popa, Yan Xu, Rui Song, Dimitrios Dimitriadis