Tag
Qwen released a new large language model, Qwen-AgentWorld-397B-A17B, as detailed on HuggingFace and the Qwen blog.
Qwen-AgentWorld releases an open 35B total / 3B active MoE world model with 256K context, along with a 7-domain benchmark, achieving state-of-the-art performance on AgentWorldBench.