Mano Technical Report
This work addresses the problem of automating complex GUI interactions for users and developers, representing an incremental advancement by combining existing methods like VLMs and reinforcement learning with domain-specific optimizations.
The authors tackled the challenge of automating GUI interactions by proposing Mano, a robust GUI agent that integrates a multi-modal foundation model with a novel simulated environment and a three-stage training pipeline, achieving state-of-the-art performance on benchmarks like Mind2Web and OSWorld with significant improvements in success rate and operational accuracy.
Graphical user interfaces (GUIs) are the primary medium for human-computer interaction, yet automating GUI interactions remains challenging due to the complexity of visual elements, dynamic environments, and the need for multi-step reasoning. Existing methods based on vision-language models (VLMs) often suffer from limited resolution, domain mismatch, and insufficient sequential decisionmaking capability. To address these issues, we propose Mano, a robust GUI agent built upon a multi-modal foundation model pre-trained on extensive web and computer system data. Our approach integrates a novel simulated environment for high-fidelity data generation, a three-stage training pipeline (supervised fine-tuning, offline reinforcement learning, and online reinforcement learning), and a verification module for error recovery. Mano demonstrates state-of-the-art performance on multiple GUI benchmarks, including Mind2Web and OSWorld, achieving significant improvements in success rate and operational accuracy. Our work provides new insights into the effective integration of reinforcement learning with VLMs for practical GUI agent deployment, highlighting the importance of domain-specific data, iterative training, and holistic reward design.