mlsanityData to 14 Oct 2026

Memadapter: Counterfactual Adaptation Against Memory-induced Sycophancy

arXiv 2610.05162 ↗First posted 4 Oct 2026cs.AIcited by 0

On the map: LLM agents and tool use → Agent memory systems

Abstract (arXiv)

Long-term memory enables LLM-based agents to retain and reuse information across tasks and sessions, supporting personalization and long-horizon interactions. However, persistent memories can also induce sycophancy, causing agents to over-align with users' historical beliefs even when they are inaccurate, outdated, or inconsistent with objective evidence. Existing mitigation methods assume that memory-induced sycophancy originates from biased or incorrect memories and attempt to reduce this risk by filtering such memories at different stages of the memory pipeline. However, in the real world, objective and correct memories can still induce sycophancy, and the same memory can warrant different influence across different contexts. To this end, we propose MemAdapter, a novel framework that adaptively integrates retrieved memories to support objective and reliable reasoning. Specifically, MemAdapter consists of three components: (i) Counterfactual Induction, which leverages counterfactual reasoning to uncover the potential risk of retrieved memories; (ii) Context-Aware Reflection, which calibrates the inferential influence of each retrieved memory in light of the current task via self-reflection; and (iii) Evidence-Based Reasoning, which grounds the final response in appropriate evidence while preserving the legitimate influence of memory. Extensive experiments on three benchmarks demonstrate that MemAdapter consistently improves memory reliability across diverse scenarios. Our code is available at https://github.com/DEEP-JLU/MemAdapter.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Agent memory systems, one of 16 directions in LLM agents and tool use. Builds on 34 of its 43 references that are in the map. First posted on arXiv 4 Oct 2026.

Builds on

34 of 43 references.

Closest ancestors · 10

Same direction, newest first

  1. 2026Zero-Mem: Zero-Token Memory Operations for LLM Agents31 Jul
  2. 2026MemSyco-Bench: Benchmarking Sycophancy in Agent Memory1 Jul
  3. 2026Beyond Similarity: Trustworthy Memory Search for Personal AI Agents4 Jun
  4. 2026STALE: Can LLM Agents Know When Their Memories Are No Longer Valid?7 May
  5. 2026Graph-based Agent Memory: Taxonomy, Techniques, and Applications5 Feb
  6. 2026OP-Bench: Benchmarking Over-Personalization for Memory-Augmented Personalized Conversational Agents20 Jan
  7. 2025Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory28 Apr
  8. 2025In Prospect and Retrospect: Reflective Memory Management for Long-term Personalized Dialogue Agents11 Mar
  9. 2025A-MEM: Agentic Memory for LLM Agents17 Feb
  10. 2024A Survey on the Memory Mechanism of Large Language Model based Agents21 Apr

Other references · 24

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  2. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,276
  3. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,568
  4. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,839
  5. 2023MemGPT: Towards LLMs as Operating Systemscited by 1,389
  6. 2023MemoryBank: Enhancing Large Language Models with Long-Term Memorycited by 556
  7. 2024Agent Workflow Memorycited by 383
  8. 2024Corrective Retrieval Augmented Generationcited by 197
  9. 2023Simple synthetic data reduces sycophancy in large language modelscited by 187
  10. 2025LightMem: Lightweight and Efficient Memory-Augmented Generationcited by 180
  11. 2025Measuring Sycophancy of Language Models in Multi-turn Dialoguescited by 104
  12. 2025A Survey of Graph Retrieval-Augmented Generation for Customized Large Language Modelscited by 88
12 more
  1. 2023Learning to Filter Context for Retrieval-Augmented Generationcited by 83
  2. 2025TRUTH DECAY: Quantifying Multi-Turn Sycophancy in Language Modelscited by 33
  3. 2025FaithfulRAG: Fact-Level Conflict Modeling for Context-Faithful Retrieval-Augmented Generationcited by 28
  4. 2025Interaction Context Often Increases Sycophancy in LLMscited by 26
  5. 2026PersistBench: When Should Long-Term Memories Be Forgotten by LLMs?cited by 21
  6. 2026BenchPreS: A Benchmark for Context-Aware Personalized Preference Selectivity of Persistent-Memory LLMscited by 10
  7. 2025The Personalization Trap: How User Memory Alters Emotional Reasoning in LLMscited by 6
  8. 2026Recalling Too Well: Sycophancy Evaluation and Mitigation in Memory-Augmented Modelscited by 4
  9. 2026When Personalization Misleads: Understanding and Mitigating Hallucinations in Personalized LLMscited by 3
  10. 2026Mitigating Over-Personalization in LLMs via Structured Memorycited by 3
  11. 2026Graph Engineering in the Era of LLM Agents: From Individual Intelligence to System Intelligencecited by 3
  12. 2026MemTrapBench: Benchmarking Cognitive Traps in LLM Memory Usecited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026COUNTERMEM: World-Model Verified Counter-Factual Memory for Language Agents
  2. 2026Defense-in-Depth for LLMs: Evaluating Memory Gates Against Activation-Induced and Memory-Induced Sycophancy
  3. 2026Understanding and Mitigating Inference-Time Overreliance Using Agentic Memory
  4. 2026MemAudit: Auditing Long-Term Agent Memory via Hidden User-State Recovery
  5. 2026MemGuard: Preventing Memory Contamination in Long-Term Memory-Augmented Large Language Models
  6. 2026From Recall to Forgetting: Benchmarking Long-Term Memory for Personalized Agents
  7. 2025Forgetting as a Feature: Cognitive Alignment of Large Language Models
  8. 2026RaMem: Contextual Reinstatement for Long-term Agentic Memory