Hugging Face (Twitter)

RT @Meituan_LongCat: 🚀 Introducing LongCat-Flash-Thinking-2601 — A version built for deep and general agentic thinking.

✨ Highlights:
🤖 Top Tier Agent Capabilities
🔹 Performance: Top tier benchmark results (TIR / Agentic Search / Agentic Tool Use) ; superb generalization ability, outperforming Claude in complex, random tasks
🔹 Env Scaling: Multiple automaticly constructed high-quality environments; dense dependency graph
🔹 Multi-Env RL: Extended DORA (our RL infra), supporting large-scale multi-environment agentic training

🛡️ Real-World Robustness
🔹 Performance: Solid performance in messy, uncertain scenarios (Vita-Noise & Tau^2-Noise)
🔹 Noise Analysis: Systematically analyzed real-world noise in agentic scenarios
🔹 Curriculum RL: Increasing noise type & intensity while training

🎯 Heavy Thinking Mode
​🔹 Parallel Thinking: Expands breadth via multiple independent reasoning tracks
🔹 Iterative Summarization: Enhances depth by using a summary...

Перейти на оригинальный пост