Context: Proactive Goal-Directed Intelligence via Composable Sandboxed Programs, Declarative Wiring, and Structured Interaction

论文概要

研究领域: NLP 作者: Gregory Magarshak 发布时间: 2026-05-26 arXiv: 2505.21641

中文摘要

我们提出Context，Magarshak架构的智能层，它用主动目标导向型代理取代了被动查询-响应聊天机器人，这些代理无需等待用户提示即可推进共享任务。该架构建立在三个相互强化的机制之上。写时上下文组装通过Groker代理预计算富类型属性，将交互上下文组装为图状态的确定性纯函数；语义变化之间的各轮次中，上下文块是字节相同的，实现接近100%的KV缓存重用。可组合沙盒化智慧程序形成治理库，其中LM生成的命令式程序通过类型化流关系声明式地连接到目标类型，通过阶段排序组合，并在交互时执行而无需进一步的LM调用。主动目标流状态机通过检查图状态并发出结构化交互内容（选项数组、治理功能、澄清提示）来推动对话走向终止状态，而无需等待用户输入。我们证明了六个形式化结果：上下文稳定性定理（将每轮LM成本限制为语义变化率的函数）；程序组合正确性定理；声明式布线可靠性定理；主动优势定理（证明主动代理在到达终止状态的期望轮次上弱优于被动代理）；协调开销消除和质量保持（在多参与者目标聊天中建立帕累托改进）；以及跨平台投票一致性定理。已在开源Qbix/Safebox/Safebots堆栈中实现。

原文摘要

We present Context, the intelligence layer of the Magarshak Architecture, which replaces reactive query-response chatbots with proactive goal-directed agents that advance shared tasks without waiting for user prompts. The architecture rests on three mutually reinforcing mechanisms. Write-time context assembly precomputes enriched typed attributes via Groker agents, assembling interaction context as a deterministic pure function of graph state; context blocks are byte-identical across turns between semantic changes, enabling near-100% KV-cache reuse. Composable sandboxed wisdom programs form a governed library of LM-generated imperative programs declaratively wired to goal types via typed stream relations, composed via phase ordering, and executed at interaction time without further LM calls. Proactive goal stream state machines drive conversations toward terminal states by inspecting graph state and emitting structured interaction content (option arrays, governance affordances, clarification prompts) without awaiting user input. We prove six formal results: the Context Stability Theorem, bounding per-turn LM cost as a function of semantic change rate; a Program Composition Correctness Theorem; a Declarative Wiring Soundness Theorem; the Proactive Dominance Theorem, proving proactive agents weakly dominate reactive agents on expected turns-to-terminal-state; Coordination Overhead Elimination and Quality Preservation, establishing Pareto improvements in multi-participant goal chats; and a Cross-Platform Vote Consistency Theorem. Implemented in the open-source Qbix / Safebox / Safebots stack.

--- *自动采集于 2026-05-27*

#论文 #arXiv #NLP #主动智能 #Agent #小凯