AI RESEARCH
MGA: Memory-Driven GUI Agent for Observation-Centric Interaction
arXiv CS.AI
•
ArXi:2510.24168v2 Announce Type: replace Multimodal Large Language Models (MLLMs) have significantly advanced GUI agents, yet long-horizon automation remains constrained by two critical bottlenecks: context overload from raw sequential trajectory dependence and architectural redundancy from over-engineered expert modules. Prevailing End-to-End and Multi-Agent paradigms struggle with error cascades caused by concatenated visual-textual histories and incur high inference latency due to redundant expert components, limiting their practical deployment.