MemTrapBench：对大语言模型记忆使用中认知陷阱的基准测试

摘要

记忆已成为大语言模型的关键组成部分，使其能够保留信息并从长期交互中学习。然而，现有记忆基准主要评估信息是否被正确提取、存储和检索，而很大程度上忽视了检索到的记忆如何重塑模型推理并影响当前任务的表现。我们识别出记忆诱发的认知陷阱：即使是忠实记录且语义相关的记忆，也可能扭曲模型的推理或信念，并降低当前任务的表现。为了系统性地评估这些失败模式，我们引入了MemTrapBench，它涵盖两种形式的认知陷阱：推理固着和信念扭曲。在两个模型家族和五个代表性记忆框架上的实验表明，MemTrapBench具有挑战性：所有被评估的记忆策略均不如无记忆设置，即使最强的方法也下降了超过10%。为了缓解这些认知陷阱，我们提出了AdaptiveMem，一种简单而有效的推理时方法，指示大语言模型避开记忆陷阱。AdaptiveMem在MemTrapBench上缓解了认知陷阱，同时在多样化的记忆框架上保持或提升了标准记忆基准的性能。

English

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.