Metraipolis › archive › dc_116bbf6ed7c9

Memadapter: Counterfactual Adaptation Against Memory-induced Sycophancy — arXiv:2610.05162

Source
arXiv
Original
https://arxiv.org/abs/2610.05162
License (as archived)
CC0-1.0
Archived
2026-10-06T05:25:01.353Z
SHA-256 of the archived text
5c4ffc90e10529b4795bc21ae158c2c0f83675cee5da1c83b30175e30b77058c
Stable URL of this page
https://metraipolis.com/documento/dc_116bbf6ed7c9

How to cite

Memadapter: Counterfactual Adaptation Against Memory-induced Sycophancy — arXiv:2610.05162 — arXiv, https://arxiv.org/abs/2610.05162 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_116bbf6ed7c9 (Metraipolis archive dc_116bbf6ed7c9, sha256 5c4ffc90e10529b4795bc21ae158c2c0f83675cee5da1c83b30175e30b77058c)
BibTeX
@misc{dc116bbf6ed7c9,
  title = {Memadapter: Counterfactual Adaptation Against Memory-induced Sycophancy — arXiv:2610.05162},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2610.05162},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_116bbf6ed7c9; sha256 5c4ffc90e10529b4795bc21ae158c2c0f83675cee5da1c83b30175e30b77058c},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.05162. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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can also induce sycophancy, causing agents to over-align with users' historical beliefs even when they are inaccurate, outdated, or inconsistent with objective evidence.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 this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.05162 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-06T05:24:05.557Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).