MAGNET: Towards Adaptive GUI Agents with Memory-Driven Knowledge Evolution
Mobile GUI agents powered by large foundation models enable autonomous task execution, but frequent updates altering UI appearance and reorganizing workflows cause agents trained on historical data to fail. Despite surface changes, functional semantics and task intents remain fundamentally stable. Building on this insight, we introduce MAGNET, a memory-driven adaptive agent framework with dual-level memory: stationary memory linking diverse visual features to stable functional semantics for robust action grounding and procedural memory capturing stable task intents across varying workflows. We propose a dynamic memory evolution mechanism that continuously refines both memories by prioritizing frequently accessed knowledge. Online benchmark AndroidWorld evaluations show substantial improvements over baselines, while offline benchmarks confirm consistent gains under distribution shifts. These results validate that leveraging stable structures across interface changes improves agent performance and generalization in evolving software environments.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
CLAG: Adaptive Memory Organization via Agent-Driven Clustering for Small Language Model Agents
Large language model agents heavily rely on external memory to support knowledge reuse and complex reasoning tasks. Yet most memory systems store experiences in a single global retrieval pool which can gradually dilute o…
What Deserves Memory: Adaptive Memory Distillation for LLM Agents
Memory systems for LLM agents struggle to determine what information deserves retention. Existing approaches rely on predefined heuristics such as importance scores, emotional tags, or factual templates, encoding designe…
Knowledge DistillationSuperLocalMemory: Privacy-Preserving Multi-Agent Memory with Bayesian Trust Defense Against Memory Poisoning
We present SuperLocalMemory, a local-first memory system for multi-agent AI that defends against OWASP ASI06 memory poisoning through architectural isolation and Bayesian trust scoring, while personalizing retrieval thro…
Graph ClusteringLearn to Memorize: Optimizing LLM-based Agents with Adaptive Memory Framework
LLM-based agents have been extensively applied across various domains, where memory stands out as one of their most essential capabilities. Previous memory mechanisms of LLM-based agents are manually predefined by human …
Spectral entropy prior-guided deep feature fusion architecture for magnetic core loss
Accurate core loss modeling is critical for the design of high-efficiency power electronic systems. Traditional core loss modeling methods have limitations in prediction accuracy. To advance this field, the IEEE Power El…