Amazon 研究：微调进权重的用户记忆可超过检索方案
Amazon 这篇论文挺有意思：把用户记忆微调进模型权重，准确率 59.9%，比检索方案还高，还给了个校验路由器补短板。
Amazon 的一项研究比较了把用户事实存进模型权重与文本检索两种记忆方式。用同一模型和相同用户数据，普通微调在 HaluMem-Long 上的事实回忆准确率为 36.9%，on-policy 自蒸馏提升到 59.9%。在 8 个 HaluMem-Long 用户上，蒸馏后的模型不检索任何上下文，仍超过 MemOS 式检索的 47.8%、抽取上下文的 51.9% 和原始对话的 51.3%，且在 4B、9B、27B 三个规模上都成立。由于权重记忆会遗忘旧事实、无法识别未记录内容，研究还提出 verify-then-regenerate 路由器，对答案与文本库校验后再生成，可再加 6.2 个百分点。论文建议保留文本库存放近期和缺失事实，把稳定的用户知识移入权重。
Weight memory vs. retrieval in agents. Brilliant work from Amazon. This work shows weight memory can outperform text memory on recall of user facts. But the best part is that you can leverage both. Using the same model and user data, this work shows that plain fine-tuning stores user facts in weights at 36.9% accuracy, while on-policy self-distillation reaches 59.9%. That second number also beats retrieval. On eight HaluMem-Long users, the distilled model answers with no retrieved context and beats MemOS-style retrieval (47.8%), extracted context (51.9%), and the raw dialogue (51.3%). The gain holds for every user and at 4B, 9B, and 27B. How it works: a teacher, which is the same model reading the user's memory, trains a student that has to answer without it. Weight memory has clear limits. It forgets older facts and cannot tell when something was never recorded. A verify-then-regenerate router checks each answer against the text store and adds 6.2 points. The recommendation is to keep a text store for recent and missing facts, and move stable user knowledge into weights. arxiv.org/abs/2611.05636 Chat with Paper: academy.dair.ai/papers/route-t… 💬 0 🔄 0 ❤️ 0 ⚡
