发表机构
MatrixOrigin; Tsinghua University（矩阵起源; 清华大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
ContextPipe将数据库查询执行范式应用于长视距LLM智能体的上下文组装，通过五阶段流水线减少了令牌量、LLM调用次数与响应时间，提升了上下文的可审计性等特性。
AI 中文摘要
长视距大语言模型（LLM）智能体需要上下文组装：在严格的上下文窗口预算和字节敏感的提示缓存约束下，运行时必须决定每个提示中包含的内容、顺序以及何时压缩历史记录。在生产级智能体系统中，该逻辑分散在提示构建器、临时压缩例程、缓存中断变通方案以及各提供商的适配层中。我们认为上下文组装在结构上与关系型数据库中的查询执行同构：两者均在严格预算下执行、利用分层缓存并借助统计信息。我们将该范式应用于ContextPipe：一个由结构化数据源目录、确定性缓存感知优化器以及EXPLAIN ANALYZE跟踪支持的五阶段流水线（计划、绑定、优化、执行、反馈）。结果表明，ContextPipe中的上下文具备可审计、可回放和故障隔离的特性。使用SWE-bench Pro Qutebrowser子集进行的初步评估显示，与仅追加的上下文构建策略相比，ContextPipe将总令牌量减少31%，LLM调用次数减少23%，响应时间缩短9%，代价是KV缓存命中率有所降低。
英文摘要
Long-horizon large language model (LLM) agents require context assembly: the runtime must decide what to include in each prompt, in what order, and when to compact history under a hard context-window budget and a byte-sensitive prompt cache. In production agentic systems, this logic is scattered across prompt builders, ad hoc compaction routines, cache-break workarounds, and per-provider shims. We argue that context assembly is structurally isomorphic to query execution in a relational database: both execute under a hard budget, exploit a tiered cache, and leverage statistics. We adopt this discipline in ContextPipe: a five-phase pipeline (Plan Bind Optimize Execute Feedback) backed by a structured data-source catalog, a deterministic cache-aware optimizer, and an EXPLAIN ANALYZE trace. We show that context in ContextPipe is auditable, replayable, and failure-isolated. A preliminary evaluation using the SWE-bench Pro Qutebrowser subset shows that, compared with the append-only context construction policy, ContextPipe reduces total token volume by 31%, LLM calls by 23%, and response time by 9%, at the cost of a lower KV cache-hit ratio.
