Tag
This paper introduces RD-Forget, a training-free framework for persistent language agents that separates stored memory from query-conditioned evidence to handle changing facts while preserving historical information.
This paper evaluates a graph-based memory framework for long-term LLM agents, finding that it does not outperform flat vector retrieval on recall metrics, but a selective forgetting module effectively reduces storage with minimal performance loss.
Anthropic's memory lead implemented an agent with a memory system that aggressively forgets irrelevant information, focusing only on consequential data to improve decision-making.