MAPLE: A Multimodal Mobile Agent with Playbook-Learned Experience

To address these limitations, we introduce MAPLE (Multimodal Agent with Playbook-Learned Experience), a novel gradient-free multi-agent framework that enables dynamic, step-wise experience sharing and execution-time prompt evolution. Unlike traditional action-reflection architectures that depend on costly, post-hoc self-reflection, MAPLE enables agents to cross-reference and distribute runtime insights in real time at each operational step. This dynamic exchange reduces context bloat and reasoning overhead while providing precise guidance. Extensive evaluations on the AndroidWorld and MobileWorld benchmarks demonstrate that MAPLE achieves state-of-the-art performance on complex, long-horizon mobile tasks, while proving scalable and adaptable across novel environments.