Meituan LongCat releases the LongCat-2.5 native multimodal model, with 1.6T parameters targeting long-horizon agent tasks
Meituan LongCat has released its native multimodal model LongCat-2.5, with a total parameter count of 1.6 trillion and approximately 48 billion parameters activated per token, strengthening native visual understanding and agentic coding capabilities on the basis of LongCat-2.0. The model incorporates more long-horizon trajectory data into long-sequence training and, through large-scale long-horizon reinforcement learning, improves end-to-end engineering capabilities such as complex codebase development and complete project construction. LongCat-2.5 represents visual signals as multi-level discrete tokens, enabling the backbone model to process visual and textual inputs in a unified token form and supporting tasks such as creative design and 3D.
Why read this
AI score 67
The original text provides the 1.6T parameter and activation scale, and explains how long-horizon reinforcement learning serves complex codebases and project-building tasks.
Topics
Body · AI translation
Meituan Longcat Releases LongCat-2.5 Native Multimodal AI Model: 1.6T Parameters, Targeting Long-Horizon Agent Tasks IT Home Download the Client App Exclusive First Look November 02, 2026 09:18:38 From Shandong Updated November 02, 2026 09:28:45
IT Home, November 2 news: Meituan Longcat today released LongCat-2.5, a native multimodal model targeting long-horizon agent tasks. The model has a total parameter count of 1.6 trillion, with approximately 48 billion parameters activated per token, further strengthening native visual understanding and agentic coding capabilities on the basis of LongCat-2.0.
According to the introduction, Longcat added more long-horizon trajectory data to long-sequence training and, through large-scale long-horizon reinforcement learning, improved the model's end-to-end engineering capabilities in tasks such as complex codebase development and complete project construction. Around data synthesis, environment construction, and cross-Harness mixed training, the official team continues to expand this training pipeline. In addition, Longcat converts real Agent failure trajectories into reproducible and verifiable training tasks, continuously supplementing training data for the model's capability shortcomings.
At the same time, LongCat-2.5 represents visual signals as multi-level discrete tokens, enabling the backbone model to process visual and text inputs in a unified token form. The combination of native visual understanding and agentic coding capabilities gives the model outstanding performance on Visual Coding and supports tasks such as creative design and 3D.
The official team stated that these upgrades are supported by continuously evolving infrastructure: optimizing long-context training and W4A4 inference on domestic computing power, and through training-inference numerical consistency and long-context rollout optimization, supporting the efficient operation of large-scale long-horizon RL.
IT Home attaches the evaluation results:
"Special Statement: The above content (including videos, pictures, or audio if any) is uploaded and published by users of 'Dafeng Hao,' a self-media platform under Phoenix Net. This platform only provides information storage space services.
Notice: The content above (including the videos, pictures and audios if any) is uploaded and posted by the user of Dafeng Hao, which is a social media platform and merely provides information storage space services."