Qwen-AgentWorld: Language World Models for General Agents
1–10 of 65 posts
Re: Qwen-AgentWorld: Language World Models for General Agents
#235B model from the qwen-3.5 line
Re: Qwen-AgentWorld: Language World Models for General Agents
#3[dead]
Re: Qwen-AgentWorld: Language World Models for General Agents
#4The labels of the very first chart (figure 1, bottom left) are obviously wrong which casts a doubt on the entire paper.
Re: Qwen-AgentWorld: Language World Models for General Agents
#535B model from the qwen-3.5 line https://github.com/QwenLM/Qwen-AgentWorld https://huggingface.co/Qwen/Qwen-AgentWorld-35B-A3B
unsloth, activate!
Re: Qwen-AgentWorld: Language World Models for General Agents
#6Eli5? What is this compared to a regular llm assistant model like the base qwen?
Re: Qwen-AgentWorld: Language World Models for General Agents
#7The labels of the very first chart (figure 1, bottom left) are obviously wrong which casts a doubt on the entire paper.
This label?
> Figure 1: Overview of Qwen-AgentWorld. Top: Qwen-AgentWorld is a unified native language world model across seven domains. Bottom: We explore two complementary strategies for applying world modeling to enhance language agents (mainly using the 35B-A3B model as agent): Decouple and Unify , where the world model serves as the environment simulator and agent foundation model, respectively.
Where is the mistake?
Re: Qwen-AgentWorld: Language World Models for General Agents
#8Eli5? What is this compared to a regular llm assistant model like the base qwen?
A regular LLM acts as a "policy," mapping a current state to a specific action (states → actions). Their new LLM acts as a "world model," mapping a current state and a chosen action to a predicted future state ((states, actions) → subsequent states). Instead of deciding "what to do," its explicit objective is to predict the exact environment observation that will result from the interaction history and the agent's current action.
I assumed at first that it was trained on synthetic data, but they actually went and deployed real physical hosts and virtual machines (e.g. Ubuntu, macOS, and Android) and browsers. They ran agentic systems on these continuously and recorded the actual, real-world interactions.
So it's an LLM that infers next state, or outcome,as structured data e.g. literal HTML code, UI view hierarchies, or accessibility trees.
Re: Qwen-AgentWorld: Language World Models for General Agents
#9I'm a fan of this direction. For me the most interesting use case for these world models isn't even training, it's verification. If this thing or some idealized version of it can actually reliably simulate state transitions, could you use it to verify an agent's execution path against hard constraints and replace/eclipse LLMs-as-a-judge?
Re: Qwen-AgentWorld: Language World Models for General Agents
#10This might be pretty big. One of my biggest frustrations with smaller models (especially MoE) is their failure to track workflow state at a high level. I'm constantly reminding them what we decided on or asking them to revisit, and reminding them eats context.
Seems like this might make that a lot less painful. And if not off the bat, with some minimal tuning or even just good prompting.