Recalling Too Well: Sycophancy Evaluation and Mitigation in Memory-Augmented Models

• URL: http://arxiv.org/abs/2606.10949v1
• Date: Tue, 09 Jun 2026 14:53:32 GMT
• Title: Recalling Too Well: Sycophancy Evaluation and Mitigation in Memory-Augmented Models
• Abstract summary: We show Persistent memory systems make models less correct by systematically amplifying sycophancy.<n>We conduct the first systematic evaluation of this effect, introducing MIST.<n>We propose two lightweight mitigations that substantially reduce sycophancy while matching or exceeding memory systems at factual recall.
• Score: 2.3899114972369744
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Persistent memory systems promise to make LLMs more helpful by storing user beliefs over time. We show they also make models less correct by systematically amplifying sycophancy, wherein models prioritize agreement with users over accuracy. We conduct the first systematic evaluation of this effect, introducing MIST: a benchmark of synthetically generated multi-turn conversations where users express plausible misconceptions in scientific, medical, and moral reasoning domains. Testing across three state-of-the-art memory systems and five model families reveals that memory amplifies sycophantic behavior across all conditions, with up to 25x higher sycophancy rates than in-context baselines. Error analyses suggest memory extraction as the primary culprit: lossy compression into discrete snippets encodes user misconceptions while discarding corrective context. Based on these results, we propose two lightweight mitigations that substantially reduce sycophancy while matching or exceeding memory systems at factual recall.

Related papers

• Dual-Grained Agent Memory and Shapley Context Attribution for Multimodal Agentic Learner [55.80248281761638]
  multimodal large language models (MLLMs) deliver impressive perception yet still falter on scientific and mathematical reasoning.<n>We propose DG-Mem, a dual-grained agentic memory framework that augments a frozen MLLM with a non- externally stored memory built once from training-time rollouts and consulted read-only at test time.
  arXiv  Detail & Related papers  (2026-08-24T13:56:01Z)
• 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)
• MemReranker: Reasoning-Aware Reranking for Agent Memory Retrieval [37.54115468116941]
  This report introduces MemReranker, a reranking model family (0.6B/4B) built on Qwen3-Reranker through multi-stage LLM knowledge distillation.<n>On the memory retrieval benchmark, MemReranker-0.6B substantially outperforms BGE-Reranker and matches open-source 4B/8B models as well as GPT-4o-mini on key metrics.<n>MemReranker-4B further achieves 0.737 MAP, with several metrics on par with Gemini-3-Flash, while maintaining inference latency at only 10-20% of large models.
  arXiv  Detail & Related papers  (2026-05-07T12:33:57Z)
• 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)
• Evoking User Memory: Personalizing LLM via Recollection-Familiarity Adaptive Retrieval [59.295767860331004]
  RF-Mem is a familiarity uncertainty-guided dual-path memory retriever.<n>It embeds human-like dual-process recognition into the retriever.<n>It consistently outperforms one-shot retrieval and full-context reasoning under fixed budget and latency constraints.
  arXiv  Detail & Related papers  (2026-03-10T06:31:44Z)
• From Verbatim to Gist: Distilling Pyramidal Multimodal Memory via Semantic Information Bottleneck for Long-Horizon Video Agents [78.30630000529133]
  We propose MM-Mem, a pyramidal multimodal memory architecture grounded in Fuzzy-Trace Theory.<n> MM-Mem memory structures hierarchically into a Sensory Buffer, Episodic Stream, and Symbolic.<n>Experiments confirm the effectiveness of MM-Mem on both offline and streaming tasks.
  arXiv  Detail & Related papers  (2026-03-02T05:12:45Z)
• NextMem: Towards Latent Factual Memory for LLM-based Agents [58.35585202907478]
  NextMem is a latent factual memory framework that utilizes an autoregressive autoencoder to efficiently construct latent memory.<n>Extensive experiments demonstrate that NextMem achieves superior performance.
  arXiv  Detail & Related papers  (2026-02-26T14:35:27Z)
• MemRec: Collaborative Memory-Augmented Agentic Recommender System [57.548438733740504]
  We propose MemRec, a framework that architecturally decouples reasoning from memory management.<n>MemRec introduces a dedicated LM_Mem to manage a dynamic collaborative memory graph.<n>It achieves state-of-the-art performance on four benchmarks.
  arXiv  Detail & Related papers  (2026-01-13T18:51:16Z)
• Memory Poisoning Attack and Defense on Memory Based LLM-Agents [3.7127635602605014]
  Large language model agents equipped with persistent memory are vulnerable to memory poisoning attacks.<n>Recent work demonstrated that the MINJA (Memory Injection Attack) achieves over 95 % injection success rate.<n>This work addresses gaps through systematic empirical evaluation of memory poisoning attacks and defenses.
  arXiv  Detail & Related papers  (2026-01-09T03:26:10Z)
• Agentic Learner with Grow-and-Refine Multimodal Semantic Memory [50.81667005063605]
  ViLoMem is a dual-stream memory framework that constructs compact, schema-based memory.<n>It encodes visual distraction patterns and logical reasoning errors, enabling MLLMs to learn from their successful and failed experiences.
  arXiv  Detail & Related papers  (2025-11-26T18:55:08Z)
• Adversarially Diversified Rehearsal Memory (ADRM): Mitigating Memory Overfitting Challenge in Continual Learning [0.0]
  Continual learning focuses on learning non-stationary data distribution without forgetting previous knowledge. Rehearsal-based approaches are commonly used to combat catastrophic forgetting. We introduce the Adversarially Diversified Rehearsal Memory to address the memory overfitting challenge.
  arXiv  Detail & Related papers  (2024-05-20T06:56:43Z)

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.