发表机构
Warsaw University of Technology（华沙理工大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对多目标智能体记忆，研究摘要写入策略：按目标分别写摘要优于统一摘要或无目标摘要，在相关性、完整性和准确性上胜出，但收益仅对后续提问的目标有效。
AI 中文摘要
长期运行的助手无法保留其所见的一切，因此它会进行摘要。摘要并非中立：保留什么内容是基于对记录用途的某种观念来选择的，而且这一选择是在任何人知道用户的长期目标中哪一个会提出请求之前一次性做出的。目标很少对发生的事情产生分歧。它们分歧的是哪些部分值得占用空间。一旦历史记录过长而无法重新阅读，摘要便取代了原始流，而摘要遗漏的内容便永久丢失了。我们探讨当记忆同时服务于多个长期目标时，记忆应针对什么进行摘要。三种策略给出了不同的答案：不针对任何目标进行摘要、撰写一份覆盖所有目标的摘要、或为每个目标各写一份摘要并一起阅读。我们在多个模型和事件流上对它们进行比较，保持读取步骤固定，以便只有写入步骤不同。目标确实会产生分歧：为不同目标撰写的摘要彼此之间的重叠程度，低于一份摘要与其自身重写版本的重叠程度。按目标分别撰写的摘要在相关性、完整性和准确性方面胜出，而覆盖所有目标的摘要甚至输给了以极少预算撰写的无目标摘要。在写入时进行解释是值得的，但仅限于对后来提出请求的目标而言。
英文摘要
A long-running assistant cannot keep everything it has seen, so it summarises. Summarising is not neutral: what is kept is chosen against some notion of what the record is for, and that choice is made once, before anyone knows which of the user's standing goals will ask. Goals rarely disagree about what happened. They disagree about which parts of it were worth the space. Once the history is too long to re-read, the summary replaces the stream, and whatever it left out is gone. We ask what a memory should summarise for when it serves several standing goals at once. Three policies answer differently: summarise with no goal in view, write one summary covering every goal, or write one summary per goal and read them together. We compare them across several models and event streams, holding the read step fixed so that only the write differs. The goals do pull apart: summaries written for different goals overlap each other less than a summary overlaps a rewrite of itself. Per-goal summaries win on relevance, completeness and accuracy, and the all-goal summary loses even to the neutral one written at a fraction of its budget. Interpreting at write pays off, but only for the goal that later asks.
CommentsAccepted to PALM workshop at NeurIPS 2026
