AgentWorldBench

The Qwen-AgentWorld team released a language model trained as a world model for reinforcement learning agents, predicting the next environment state from an observation and action. It serves as a deco…

Alibaba's Qwen team released Qwen-AgentWorld-35B-A3B, a language world model that predicts environment states rather than actions, trained on over 10 million interaction trajectories across seven agen…

Alibaba's Qwen team released Qwen-AgentWorld, a language world model that simulates environment responses to agent actions, outperforming GPT-5.4 and Claude Opus 4.8 on the AgentWorldBench across seve…

Alibaba's Qwen team released Qwen-AgentWorld-35B-A3B and Qwen-AgentWorld-397B-A17B, the first language world models capable of simulating agentic environments across seven domains via long chain-of-th…