混合自演化结构记忆用于GUI智能体

The remarkable progress of vision-language models (VLMs) has enabled GUI agents to interact with computers in a human-like manner. However, real-world computer-use tasks remain challenging due to long-horizon workflows, diverse interfaces, and frequent intermediate errors. Previous works equipped agents with external memory built from large collections of trajectories, relying on flat retrieval over discrete summaries or continuous embeddings, which fall short of the structured organization and self-evolving characteristics of human memory. Inspired by the brain, this research proposes Hybrid Self-evolving Structured Memory (HyMEM), a graph-based memory that couples discrete high-level symbolic nodes with continuous trajectory embeddings. HyMEM maintains a graph structure that can more effectively handle complex computer-use tasks.