AI RESEARCH
Multi-Layered Memory Architectures for LLM Agents: An Experimental Evaluation of Long-Term Context Retention
arXiv CS.AI
•
ArXi:2603.29194v1 Announce Type: cross Long-horizon dialogue systems suffer from semanticdrift and unstable memory retention across extended sessions. This paper presents a Multi-Layer Memory Framework that decomposes dialogue history into working, episodic, and semantic layers with adaptive retrieval gating and retention regularization. The architecture controls cross-session drift while maintaining bounded context growth and computational efficiency.