The work will focus on evaluating how different strategies for storing, retrieving, consolidating, and forgetting experiences affect an embodied agent’s ability to perform tasks in dynamic environments. Particular emphasis will be placed on understanding the trade-offs between memory capacity, retention, recall accuracy, interference resistance, and behavioral adaptation. The thesis will include a literature review of memory mechanisms for embodied and LLM-based agents, the implementation of a memory architecture supporting long-term memory consolidation, and evaluation in a simulated environment. Experiments will assess memory performance and agent behavior using benchmarks measuring recall accuracy, retention, interference resistance, spatial-temporal reasoning, and adaptation to changing conditions. The goal is to identify principles for scalable long-term memory systems that improve both memory performance and agent decision-making.