为大模型代理设计可编程的内存系统，提升任务成功率。
RAMPART: Registry-based Agentic Memory with Priority-Aware Runtime Transformation
- 用编译时注册表管理内存块，运行时按策略动态组装上下文。
- 第7个位置后任务成功率骤降，分组提升关键块效果显著。
- 适合需要高效记忆管理和多智能体协作的复杂任务场景。
RAMPART 是一种编译时内存模型与纯内存块注册表，用于基于大语言模型的智能体。上下文组装是可编程的运行时操作，内容从结构化注册表中按明确策略（排序、包含、淘汰）编译生成。五个可组合原语（提升、门控、写入、淘汰、回滚）在编译前作用于命名可寻址块，零提示词成本。溯源标签和不可淘汰的所有权标志实现基于块级别的权限内存模型。对 Qwen3-8B Q4 的控制探针显示，编译时放置和块与任务查询的结构关系影响任务成功，当任务跟随注册表时第七块处出现断崖式下降，若任务先于注册表则在第十二块处下降。将关键块与其内容相邻邻居分组并整体提升，可在单块失败的位置使任务成功率提升数十个百分点。在 Qwen2.5-7B、Llama-3.1-8B、Mistral-7B-v0.3、Qwen3-14B 上的跨模型验证表明，内容预热效应在绝对位置上一致，幅度随模型强度变化。分组使 Mistral 在最困难的注册表规模下平均通过率提升约五倍；小模型经干预后可在中等注册表区超越未干预的大模型。相关性门控降低 67.8% 提示成本，同时恢复 83% 的提升条件成功率。模式淘汰机制实现 0% 调用（相比有模式时的 100%），这是基于策略的方法无法保证的特性。共享注册表协调使智能体间通信降至方法调用级别，零协调词成本。
原文摘要 · Abstract (English)
RAMPART is a compile-time memory model and pure in-RAM block registry for LLM-based agents. Context assembly is a programmable runtime operation where content is compiled from a structured registry under explicit policy for ordering, inclusion, and eviction. Five composable primitives (promote, gate, write, evict, rollback) act on named addressable blocks before compilation at zero prompt-token cost. Provenance tags and non-evictable authorship flags implement a permissioned memory model with block-level ownership. Controlled probes with Qwen3-8B Q4 show that compile-time placement and the structural relationship between blocks and the task query affect task success, with the cliff falling at roughly the seventh block position when the task follows the registry and the twelfth when it precedes. Grouping the critical block with content-adjacent neighbours and promoting the group as a unit lifts task success by tens of percentage points at positions where single-block placement fails. Cross-model replication on Qwen2.5-7B, Llama-3.1-8B, Mistral-7B-v0.3, and Qwen3-14B shows the content-priming effect appears at the same absolute positions across families, with magnitude varying with model strength. Block grouping raises Mistral's mean pass rate roughly fivefold at the hardest registry size, and a smaller model with the intervention can outperform a larger model without it in the mid-registry zone. Relevance gating reduces prompt cost by 67.8\% while recovering 83% of the promoted-condition success rate. Schema eviction produces 0% invocations against 100% with the schema present, a property policy-based approaches cannot guarantee by construction. Shared-registry coordination reduces inter-agent communication to a method call at zero coordination token cost.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。