记忆越多，AI 越笨？
给 AI 加记忆，本意是让它更聪明——但研究者发现，记忆反而可能让它变蠢。他们设计了一套测试，让 AI 带着过去对话的记忆做新任务，结果所有带记忆的模型表现都不如「失忆」版本，最强的方法也掉了 10% 以上。问题出在「认知陷阱」:AI 会死磕旧思路(推理固化)，或者被旧信息带偏判断(信念扭曲)。他们提出一个简单解法：在推理时加一句指令，让 AI 主动避开记忆陷阱，既保住了记忆的好处，又没掉进坑里。这不是你明天能用的功能，但它提醒你：给 AI 加记忆不是越多越好，关键是怎么用。
📄 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.