Meituan released LongCat-2.5 on November 2, adding stronger visual understanding and coding capabilities to its AI model lineup. The model has 1.6 trillion total parameters, with approximately 48 billion activated for each token, and is designed for tasks requiring sustained execution by AI agents.
The company said it expanded training on long task sequences and used large-scale reinforcement learning to improve work on complex codebases and complete software projects. It also converts failures encountered by real agents into reproducible training tasks to address gaps in model performance.
LongCat-2.5 processes visual and text inputs within a unified token framework, supporting visual coding, creative design, and 3D tasks. The model is available through Meituan’s online chat service and API platform, with GitHub and Hugging Face releases planned to follow. [IT Home, in Chinese]