7 comments

  • blurbleblurble 47 minutes ago
    This 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.

  • dippogriff 1 hour ago
    I'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?
  • psc007 1 hour ago
    Eli5? What is this compared to a regular llm assistant model like the base qwen?
    • gavmor 1 hour ago
      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.

  • Tepix 2 hours ago
    The labels of the very first chart (figure 1, bottom left) are obviously wrong which casts a doubt on the entire paper.
    • dudisubekti 1 hour ago
      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?

      • Tepix 31 minutes ago
        The deltas are wrong.

        The bars above the label "Infinite Real-World Envs" show growth for example from approx 42 to 55 but the red label says "+7.1". It's wrong for all of them.

  • verdverm 2 hours ago
  • moozechen 5 minutes ago
    [dead]
  • stingraycharles 2 hours ago
    [dead]