This post was originally published by Source Author on Venture Beat.
For all their superhuman power, today’s AI models suffer from a surprisingly human flaw: They forget. Give an AI assistant a sprawling conversation, a multi-step reasoning task or a project spanning days, and it will eventually lose the thread. Engineers refer to this phenomenon as “context rot,” and it has quietly become one of the most significant obstacles to building AI agents that can function reliably in the real world.
A research team from China and Hong Kong believes it has created a solution to context rot. Their new paper introduces general agentic memory (GAM), a system built to preserve long-horizon
