None defined yet.
GUI-CIDER: Mid-training GUI Agents via Causal Internalization and Density-aware Exemplar Reselection
Learning to Act under Noise: Enhancing Agent Robustness via Noisy Environments
【New】: https://huggingface.co/meituan-longcat/LongCat-2.0
LongCat-2.0, is a 1.6T-parameter MoE language model with approximately 48B active parameters per token. It is designed for long-context reasoning, agentic coding, repository-level understanding, automated task execution, and complex tool-use workflows. Deeply adapted to popular agent harnesses such as Claude Code, Openclaw, Hermes.
Open foundation models for long-context reasoning, agentic coding, and scalable AI systems. Home of LongCat-2.0.
LongCat is a large language model family built by Meituan. We're working on making AI more useful in the physical world — one small step at a time. We continuously release LLMs, multimodal models, and other AI projects here. Feel free to visit LongCat and enjoy our latest models!
