None defined yet.
DiagEvo: Diagnosis-Guided Self-Evolution via Hierarchical Error Memory
Beyond Final Scores: A Systematic Evaluation of Agents for Long-Horizon AI Research and Development
γNewγ LongCat-DeepResearch
LongCat-DeepResearch combines a LongCat model enhanced for deep research with a research harness for open-ended investigation and evidence-grounded report generation. The system outperforms the evaluated deep-research offerings from ChatGPT, Claude, and Gemini across DeepResearchBench, DeepResearchBench II, and ResearchRubrics. These model improvements are intended to be incorporated into the next general-purpose LongCat model release.
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 β 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!
