We introduce the Graph Machine (GM), an architecture that maintains an O(n)-sized state and accesses it through sparse, …

从控制流与上下文的所有权出发，给出四条可执行的 Agent 工程原则：一切外部接入以工具体系形式接入且不注入系统提示词；逐级披露贯穿技能、工具发现、工具执行与记忆四个环节；Workflow / Agent / Agentic Workflow / Graph 各有场景、不是替代关系；并逐层拆解四者的技术原理——DAG 与状态机、ReAct 循环、宏观图加微观循环的混合架构，以及 State/Node/Edge、超步执行、reducer 合并语义、checkpointer 恢复、interrupt 人审与递归上限。

Multi-Agent Reinforcement Learning (MARL) has emerged as a pivotal paradigm for complex decision-making in autonomous sy…

梳理 RSI 从 Good 1965 到 2026 的思想史、技术图谱与一手实证：Anthropic 承认其代码库 >80% 合并代码由 Claude 撰写、METR 测得 AI 可完成任务时长约每 4 个月翻倍、AlphaEvolve 优化了支撑自身的计算栈。核心判断——有界自我精炼已工程化，开放式 RSI 尚未发生；而进步与安全共享同一个「验证瓶颈」。

Part-aware 3D asset generation enables applications such as editing, articulation, simulation, and fabrication, yet exis…

Multimodal entity linking grounds entity mentions in text and images to knowledge-base entries. These systems degrade on…

Large language models are increasingly deployed as agents that plan over long horizons and act through external tools. M…

We present Iris-mini and Iris-pro, two search agents trained at the 35B-A3B and 397B-A17B scales, together with the data…

Designing and authoring high-performance custom kernels for accelerators is a complex task that requires deep hardware-l…