不更新模型权重，用控制机制让记忆更好助力推理
A Control Architecture for Training-Free Memory Use
- 基于不确定性和置信度设计记忆触发与采纳策略
- 在SVAMP和ASDiv上分别提升7.0和7.67分
- 适合需要零训练更新的推理系统部署
提示注入的记忆能在不更新模型权重的情况下提升推理能力，但带来控制难题：仅在正确时机应用检索内容才有效。本文在严格的零训练设置下研究该问题，提出适用性控制框架——决定何时触发记忆辅助的二次推理、是否信任记忆、如何长期维护记忆库。方法融合基于不确定性的路由、基于置信度的选择性接纳、规则与范例记忆的库选择，以及基于证据的长期记忆治理。在计算量匹配的零训练协议下，该架构使两个核心算术基准在SVAMP上提升7.0分，在ASDiv上提升7.67分。相同架构在问答与智能体任务中也呈现正向效果，且主算术任务的第二检查点仍保持正向提升。实证表明，提升主要来自控制机制而非单纯记忆暴露；置信度可区分有益与有害的规则库干预，固定检索下修复与错误差异集中于实际包含编辑条目的行。
原文摘要 · Abstract (English)
Prompt-injected memory can improve reasoning without updating model weights, but it also creates a control problem: retrieved content helps only when it is applied in the right state. We study this problem in a strict training-free setting and formulate it as applicability control: when to trigger a memory-assisted second pass, when to trust it, and how to maintain the memory bank over time. Our method combines uncertainty-based routing, confidence-based selective acceptance, bank selection across rule and exemplar memory, and evidence-based governance of the memory bank over time. Under a locked training-free protocol with compute-matched controls, it improves two core arithmetic benchmarks by +7.0 points on SVAMP and +7.67 points on ASDiv over baseline. The same architecture also transfers to QA and agent benchmarks with smaller positive effects and shows the same positive direction on a second checkpoint for the main arithmetic tasks. On arithmetic, the main empirical pattern is that the control architecture, rather than raw memory exposure, drives the improvements on SVAMP and ASDiv. Mechanistically, confidence separates helpful from harmful rule-bank interventions, and under fixed retrieval the repair-versus-corrupt difference localizes to rows whose retrieved set actually contains the edited entries.
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。