记忆越多，AI 反而越笨？
给大模型加记忆，本意是让它越用越懂你；但新研究发现，记忆本身会变成陷阱。哪怕记对了、记的内容也和当前问题相关，这些记忆仍可能把模型的推理带偏、甚至扭曲它的信念，导致当前任务表现变差。研究者做了个专门测这种陷阱的基准，结果所有主流记忆方案都输给了「不带记忆」的裸模型，最强的也掉了 10% 以上。他们顺手提了个推理时的小技巧，让模型主动避开记忆陷阱，既保住记忆的好处、又不被它坑。这不是你明天能用的功能，但它提醒我们：AI 的「记性好」和「用得好」是两回事，记忆不是越多越好。
📄 原文摘要(英文)
Memory has become a key component of large language models, enabling them to retain information and learn from long-term interactions. However, existing memory benchmarks mainly evaluate whether information is correctly extracted, stored, and retrieved, while largely overlooking how retrieved memories reshape model reasoning and affect performance on the current task. We identify memory-induced cognitive traps: even faithfully recorded and semantically relevant memories can distort model reasoning or beliefs and degrade current task performance. To systematically evaluate these failure modes, we introduce MemTrapBench, which covers two forms of cognitive traps: Reasoning Fixation and Belief Distortion. Experiments across two model families and five representative memory frameworks show that MemTrapBench is challenging: all evaluated memory strategies underperform the no-memory setting, with even the strongest methods suffering drops of more than 10%. To mitigate these cognitive traps, we propose AdaptiveMem, a simple yet effective inference-time method that instructs LLMs to avoid memory traps. AdaptiveMem mitigates cognitive traps on MemTrapBench while preserving or improving performance on standard memory benchmarks across diverse memory frameworks.