A new technique from Zhejiang University and Alibaba Group called Memp, provides agents with a “procedural memory” that is continuously updated as they gain experience, much like how humans learn from practice, a key requirement for reliable enterprise automation. Memp is a task-agnostic framework that treats procedural memory as a core component to be optimized. It consists of three key stages that work in a continuous loop: building, retrieving, and updating memory. Memories are built from an agent’s past experiences, or “trajectories.” The most critical component is the update mechanism. Memp introduces several strategies to ensure the agent’s memory evolves. As an agent completes more tasks, its memory can be updated by simply adding the new experience, filtering for only successful outcomes or, most effectively, reflecting on failures to correct and revise the original memory. This focus on dynamic, evolving memory places Memp within a growing field of research aimed at making AI agents more reliable for long-term tasks. Memp targets cross-trajectory procedural memory.” It focuses on “how-to” knowledge that can be generalized across similar tasks, preventing the agent from re-exploring from scratch each time. By distilling past successful workflows into reusable procedural priors, Memp raises success rates and shortens steps. One of the most significant findings for enterprise applications is that procedural memory is transferable. For example, memory created by a powerful model like GPT-4o can be used by a smaller model like Qwen2.5-14B, significantly boosting its performance and reducing task completion steps. This makes it possible to train using high-end models and deploy with more cost-effective ones. Overall, Memp supports continual learning and mastery, making AI agents more reliable and scalable for enterprise automation.