全球双榜SOTA！明略科技专有大模型 Mano开启GUI智能操作新时代

2025-09-28

明略科技推出的GUI大模型Mano在Mind2Web和OSWorld两大基准测试中取得了创纪录的SOTA成绩，成功率达到40.1%。通过在线强化学习和自动数据采集，Mano为GUI智能体领域提供了可扩展的新范式，显著提升了复杂任务的执行能力。该技术的突破不仅推动了自动化边界的扩展，也为企业智能化转型提供了强有力的支持

官宣！明略科技推出专有大模型产品线DeepMiner，可信商业数据分析智能体终于能用了！

2025-09-22

明略科技推出专有大模型产品线DeepMiner，以“可信智能体+可信数据”双轮驱动，解决企业智能体落地中幻觉率高、过程不透明等痛点。该产品通过多智能体协同架构、企业级数据整合及全流程透明化设计，降低幻觉率并支持知识沉淀，其自研Mano和Cito模型分别实现精准执行与深度推理，助力企业构建可信生产力。

明略科技 Mano Technical Report

2025-09-18

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.