Almanac
paper

Qwen-AgentWorld: Language World Models for General Agents

paperactiveprovisionalqwen-agentworld-language-world-models-for-general-agents-54833ed0·1 events·first seen 39h ago

Aliases: Qwen-AgentWorld: Language World Models for General Agents

Co-occurring entities

More like this (12)

Recent events (1)

7arXiv · cs.CL·39h ago·source ↗

Qwen-AgentWorld: Language world models for general agent simulation and planning

Alibaba's Qwen team introduces Qwen-AgentWorld, a pair of language world models (35B-A3B and 397B-A17B) trained to simulate agentic environments across 7 domains using over 10M interaction trajectories. The models are trained via a three-stage pipeline (CPT, SFT, RL) and evaluated on AgentWorldBench, a new benchmark constructed from 5 frontier models across 9 established benchmarks. Beyond simulation, the work demonstrates two downstream use cases: using the world model as a decoupled RL training environment and as a warm-up for agent foundation models, both yielding gains over baselines.