MemTrapBench: Benchmarking Cognitive Traps in LLM Memory Use

• URL: http://arxiv.org/abs/2608.20202v1
• Date: Thu, 20 Aug 2026 16:00:17 GMT
• Title: MemTrapBench: Benchmarking Cognitive Traps in LLM Memory Use
• Abstract summary: Existing memory benchmarks mainly evaluate whether information is correctly extracted, stored, and retrieved.<n>We identify memory-induced cognitive traps: even faithfully recorded and semantically relevant memories can distort model reasoning.<n>We propose AdaptiveMem, a simple yet effective inference-time method that instructs LLMs to avoid memory traps.
• Score: 30.64715962774191
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Mechanistic Attention Guidance for Agent Memory Refinement [32.57216046158823]
  We show that retrieval-head attention provides a mechanistic signal for revealing segment-level memory utilization.<n>We propose Attention-Guided Memory Refinement (AGMR), a framework that uses utilization patterns revealed by attention to guide targeted segment-level memory updates.
  arXiv  Detail & Related papers  (2026-07-20T07:17:50Z)
• MemSyco-Bench: Benchmarking Sycophancy in Agent Memory [32.49512092540906]
  MemSyco-Bench is a benchmark for evaluating memory-induced sycophancy in agent systems.<n>MemSyco-Bench measures when memory should influence a decision and how valid memory should be used.
  arXiv  Detail & Related papers  (2026-07-01T15:30:33Z)
• Is One Score Enough? Rethinking the Evaluation of Sequentially Evolving LLM Memory [50.857546269660276]
  We introduce SeqMem-Eval, a diagnostic evaluation framework for sequentially evolving large language models (LLMs) memory.<n>Rather than focusing only on final performance, SeqMem-Eval evaluates how memory states evolve, generalize, consolidate experience, and retain useful information during sequential inference.
  arXiv  Detail & Related papers  (2026-05-14T20:15:22Z)
• The Trap of Trajectory: Towards Understanding and Mitigating Spurious Correlations in Agentic Memory [7.707732051915869]
  Diagnosing agentic memory systems reveals that memory improves reasoning on clean inputs but amplifies reliance on spurious patterns when they are present.<n>We propose CAMEL, a plug-and-play calibration method that operates across diverse memory architectures at both write and retrieval time.<n>Overall, CAMEL offers a principled and lightweight solution toward more reliable agentic memory deployment.
  arXiv  Detail & Related papers  (2026-05-10T05:04:13Z)
• MemEvoBench: Benchmarking Memory MisEvolution in LLM Agents [78.95081012334116]
  Large Language Models (LLMs) with persistent memory enhances interaction continuity and personalization but introduces new safety risks.<n> contaminated or biased memory accumulation can trigger abnormal agent behaviors.<n>MemeEvoBench is the first benchmark evaluating memory safety in LLM agents against adversarial memory injection, noisy tool outputs, and biased feedback.
  arXiv  Detail & Related papers  (2026-04-17T07:29:52Z)
• MetaMem: Evolving Meta-Memory for Knowledge Utilization through Self-Reflective Symbolic Optimization [57.17751568928966]
  We propose MetaMem, a framework that augments memory systems with a self-evolving meta-memory.<n>During meta-memory optimization, MetaMem iteratively distills transferable knowledge utilization experiences across different tasks.<n>Extensive experiments demonstrate the effectiveness of MetaMem, which significantly outperforms strong baselines by over 3.6%.
  arXiv  Detail & Related papers  (2026-01-27T04:46:23Z)
• Evaluating Long-Term Memory for Long-Context Question Answering [100.1267054069757]
  We present a systematic evaluation of memory-augmented methods using LoCoMo, a benchmark of synthetic long-context dialogues annotated for question-answering tasks.<n>Our findings show that memory-augmented approaches reduce token usage by over 90% while maintaining competitive accuracy.
  arXiv  Detail & Related papers  (2025-10-27T18:03:50Z)
• Multiple Memory Systems for Enhancing the Long-term Memory of Agent [9.43633399280987]
  Existing methods, such as MemoryBank and A-MEM, have poor quality of stored memory content.<n>We have designed a multiple memory system inspired by cognitive psychology theory.
  arXiv  Detail & Related papers  (2025-08-21T06:29:42Z)
• Stable Hadamard Memory: Revitalizing Memory-Augmented Agents for Reinforcement Learning [64.93848182403116]
  Current deep-learning memory models struggle in reinforcement learning environments that are partially observable and long-term. We introduce the Stable Hadamard Memory, a novel memory model for reinforcement learning agents. Our approach significantly outperforms state-of-the-art memory-based methods on challenging partially observable benchmarks.
  arXiv  Detail & Related papers  (2024-10-14T03:50:17Z)
• MADial-Bench: Towards Real-world Evaluation of Memory-Augmented Dialogue Generation [15.64077949677469]
  We present a novel Memory-Augmented Dialogue Benchmark (MADail-Bench) to evaluate the effectiveness of memory-augmented dialogue systems (MADS) The benchmark assesses two tasks separately: memory retrieval and memory recognition with the incorporation of both passive and proactive memory recall data. Results from cutting-edge embedding models and large language models on this benchmark indicate the potential for further advancement.
  arXiv  Detail & Related papers  (2024-09-23T17:38:41Z)
• A Model or 603 Exemplars: Towards Memory-Efficient Class-Incremental Learning [56.450090618578]
  Class-Incremental Learning (CIL) aims to train a model with limited memory size to meet this requirement. We show that when counting the model size into the total budget and comparing methods with aligned memory size, saving models do not consistently work. We propose a simple yet effective baseline, denoted as MEMO for Memory-efficient Expandable MOdel.
  arXiv  Detail & Related papers  (2022-05-26T08:24:01Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.