[2604.04853] MemMachine: A Ground-Truth-Preserving Memory System for Personalized AI Agents

Computer Science > Artificial Intelligence arXiv:2604.04853 (cs) [Submitted on 6 Apr 2026] Title:MemMachine: A Ground-Truth-Preserving Memory System for Personalized AI Agents Authors:Shu Wang, Edwin Yu, Oscar Love, Tom Zhang, Tom Wong, Steve Scargall, Charles Fan View a PDF of the paper titled MemMachine: A Ground-Truth-Preserving Memory System for Personalized AI Agents, by Shu Wang and 6 other authors View PDF HTML (experimental) Abstract:Large Language Model (LLM) agents require persistent memory to maintain personalization, factual continuity, and long-horizon reasoning, yet standard context-window and retrieval-augmented generation (RAG) pipelines degrade over multi-session interactions. We present MemMachine, an open-source memory system that integrates short-term, long-term episodic, and profile memory within a ground-truth-preserving architecture that stores entire conversational episodes and reduces lossy LLM-based extraction. MemMachine uses contextualized retrieval that expands nucleus matches with surrounding context, improving recall when relevant evidence spans multiple dialogue turns. Across benchmarks, MemMachine achieves strong accuracy-efficiency tradeoffs: on LoCoMo it reaches 0.9169 using gpt4.1-mini; on LongMemEvalS (ICLR 2025), a six-dimension ablation yields 93.0 percent accuracy, with retrieval-stage optimizations -- retrieval depth tuning (+4.2 percent), context formatting (+2.0 percent), search prompt design (+1.8 percent), and query bias correct...