精确编辑指令可显著影响继承记忆的调用选择。
Plan Pointers and Record-Directive Form in Budgeted Verification of Inherited Agent Memory
- 通过指针、条件或两者结合控制记忆调用
- 条件匹配比单纯标识符提升35分（95%置信区间）
- 适合研究大模型记忆机制与提示工程的实验设计
一个继承六条简短记忆的智能体在行动前最多只能调用一条存档记录；写入存储的指令可引导该选择：指向记录的指针、识别它的条件，或两者兼具。在十二项针对单一仪器谱系（共14,760次尝试）的注册研究中，我们测量了不同指令形式下的调用位置。在六个直接提供者模型上，长度匹配的条件比裸标识符高出+35.0分（[+31.2, +38.8]，研究D）；但在九模型的OpenRouter面板上，该优势未通过预注册优劣规则检验（研究E）。在三个Claude模型上，附加标识符会取消条件效果（Opus 5：40/40 → 0/40，研究F-x）；六次字节匹配的编辑使每个字符串产生独立效应（研究G），且八十大样本重测中，三十个复现对比有十五个在误差范围内，十五个未定，无一超出（研究G'）。一次认证线（Opus 5上+96.0分）和两信用额度恢复了目标调用，在三模型上全部成功（研究J）；对五个条件字符串的测试显示，后缀取消效应在Opus 5上四个成立，在Fable 5.1上全部成立（研究H2）；在第二个存储中，所有模型均遵循条件（研究H1）。进入决策阶段后，条件使选择倾向当前记录（Opus 5：+100.0分），而对Fable 5.1则相反（研究I）。一个字符的计划指针效应（+78.0分；研究B，修正首份报告后）在前瞻性重测中再次确认（+81.7分；研究B'）。所有结果均为固定面板上精确编辑的描述性效应，已注册区间，不涉及机制主张。
原文摘要 · Abstract (English)
An agent that inherits six one-line memories may pull at most one archived source record before acting; a directive written into the store can steer that choice: a pointer to the record, a criterion that identifies it, or both. Across twelve registered studies on one instrument lineage (14,760 attempts) we measured where the request goes under each form. On six direct-provider models a length-matched criterion exceeded a bare id by +35.0 points [+31.2, +38.8] (Study D); the contrast failed its registered superiority rule on a nine-model OpenRouter-served panel (Study E). Appending the id cancelled the criterion on three Claude models (Opus 5: 40/40 to 0/40; Study F-x); six byte-matched edits gave each exact string its own effect (Study G), and a re-run at eighty runs per cell left fifteen of thirty replication contrasts within the margin, fifteen unresolved and none beyond (Study G'). A ratification line (+96.0 points on Opus 5) and a budget of two credits restored the target on all three (Study J); across five criterion strings the suffix's cancellation held for four of the five wordings on Opus 5 and all five wordings on Fable 5.1 (Study H2); in a second store every model followed the criterion (Study H1). Continued into a decision, the criterion moved the choice toward the current record (+100.0 points, Opus 5) and away from it on Fable 5.1 (Study I). A one-character plan pointer's effect (+78.0 points; Study B, after a correction of its first repository report) returned the same verdict under a prospectively registered re-run (+81.7 points; Study B'). All results are descriptive effects of exact edits on fixed panels with registered intervals and no mechanism claim.
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。