{"slug": "memadapter-counterfactual-adaptation-against-memory-induced-sycophancy", "title": "Memadapter: Counterfactual Adaptation Against Memory-induced Sycophancy", "summary": "Researchers introduced Memadapter, a counterfactual adaptation method designed to prevent memory-induced sycophancy in LLM-based agents that retain information across tasks and sessions. The work addresses how persistent memory can cause agents to over-align with users' historical beliefs even when those beliefs are incorrect.", "body_md": "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 inacc", "url": "https://wpnews.pro/news/memadapter-counterfactual-adaptation-against-memory-induced-sycophancy", "canonical_source": "https://aiflash.com/news/131789/", "published_at": "2026-10-06 06:00:14+00:00", "updated_at": "2026-10-06 06:17:47.950500+00:00", "lang": "en", "topics": ["ai-agents", "large-language-models", "ai-safety", "ai-research"], "entities": ["Memadapter"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/memadapter-counterfactual-adaptation-against-memory-induced-sycophancy", "markdown": "https://wpnews.pro/news/memadapter-counterfactual-adaptation-against-memory-induced-sycophancy.md", "text": "https://wpnews.pro/news/memadapter-counterfactual-adaptation-against-memory-induced-sycophancy.txt", "jsonld": "https://wpnews.pro/news/memadapter-counterfactual-adaptation-against-memory-induced-sycophancy.jsonld"}}