paper
Qwen-AgentWorld: Language World Models for General Agents
paperactiveprovisional
qwen-agentworld-language-world-models-for-general-agents-54833ed0·1 events·first seen 39h agoAliases: Qwen-AgentWorld: Language World Models for General Agents
Co-occurring entities
More like this (12)
Qwen-AgentWorld-35B-A3BWorld-In-AgentSelf-Compacting Language Model AgentsQwen-Agenttool-augmented language agentsModel-Generated Agent Skills (paper)large language model agentsEnhancing Decision-Making with Large Language Models through Multi-Agent Fictitious Playlanguage agentswshobson/agentsSemantic AgentAgentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Application
Recent events (1)
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.