从记忆到引导：面向程序性编码记忆的时空编排器

中文摘要 AI 辅助

记忆增强型智能体通常通过将检索到的技能直接注入文本提示来整合程序性知识。这种方法危险地将可读文本等同于可靠执行。为弥合这一差距，我们引入了“从记忆到引导”（From Memory to Guide）这一新颖范式，将程序性记忆从被动的文本传递转变为主动的、推理时的策略自适应。我们通过时空编排器（Spatio-Temporal Composer）实例化该范式，这是一种主动的策略编译器，明确管理检索到的知识应如何以及何时被应用。编排器不将技能视为即插即用模块，而是动态地将历史知识与当前环境约束对齐（空间自适应），并精确规定其适用的生命周期（时间编排）。它主动将静态记忆转化为严格受限的运行时引导（Runtime Guides），为智能体配备局部目标和行为护栏，而无需任何参数更新。在EngramBench中13项具有挑战性的长时程软件工程任务上的广泛评估证明了该架构的明显优势。编排器不仅稳健地防止了上下文不匹配，还在最复杂的任务上带来了7.2个百分点的绝对通过率提升，同时将主智能体的令牌使用量削减了32.2%。

英文摘要

Memory-augmented agents typically integrate procedural knowledge by injecting retrieved skills directly into text prompts. This approach dangerously equates readable text with reliable execution. To bridge this gap, we introduce From Memory to Guide, a novel paradigm that transitions procedural memory from passive text delivery to active, inference-time policy adaptation. We instantiate this paradigm through the Spatio-Temporal Composer, an active policy compiler that explicitly manages exactly how and when retrieved knowledge should be applied. Rather than treating skills as plug-and-play modules, Composer dynamically aligns historical knowledge with current environmental constraints (spatial adaptation) and precisely dictates its applicable lifecycle (temporal orchestration). It actively transforms static memories into strictly bounded Runtime Guides---equipping the agent with localized objectives and behavioral guardrails without requiring a single parameter update. Extensive evaluations on 13 demanding, long-horizon software engineering tasks in EngramBench demonstrate the clear advantages of this architecture. Composer not only robustly prevents context mismatch but drives an absolute pass-rate increase of 7.2 percentage points on the most complex tasks, while simultaneously slashing the main agent's token usage by 32.2%.

发表机构

• The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））
• MemoraX AI

机构由 AI 辅助整理，请以论文原文为准。