Infinite Worlds with Versatile Interactions
Summary
This paper introduces LingBot-World 2.0, an advanced world modeling system with unbounded interaction horizons, real-time 720p 60fps video generation, diverse interactive elements (e.g., attacking, spell-casting), and novel multi-agent behavior control via pilot and director agents, along with a shared multi-player interface.
View Cached Full Text
Cached at: 07/09/26, 07:51 AM
Paper page - Infinite Worlds with Versatile Interactions
Source: https://huggingface.co/papers/2607.07534 Published on Jul 8
#3 Paper of the day Authors:
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
,
Abstract
An advanced world modeling system with extended interaction capabilities, real-time processing, diverse interactive elements, and multi-agent behavior control for collaborative virtual environments.
We present LingBot-World 2.0 (also known as LingBot-World-Infinity), an advanced iteration of LingBot-World featuring four distinct upgrades. (1) Our model achieves an unbounded interaction horizon while maintaining consistent output quality, benefiting from a carefully craftedcausal pretraining paradigm. (2) Through distilling areal-time variantfrom the base model, our system guarantees rapid response time, sufficient to drive 720p video streams at 60 fps. (3) Compared to the previous version, this update introduces highly diverseinteractive elements, comprising a broader spectrum of actions (e.g., attacking, archery, spell-casting, and shooting) alongside a richer variety oftext-driven events. (4) We pioneer the integration of anagentic harnesswithin the domain ofworld modeling, wherein apilot agentis tasked with planning and executing character behaviors, while adirector agentis responsible for synthesizing novel environmental elements as the scene progresses. Additionally, to facilitate ashared experience, we develop an interface that permits multiple players to simultaneously immerse themselves in this vivid world simulator. We pair our primary 14B model with a lightweight 1.3B counterpart, which supports effortless deployment on a single GPU.
View arXiv pageView PDFProject pageGitHub50Add to collection
Get this paper in your agent:
hf papers read 2607\.07534
Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash
Models citing this paper0
No model linking this paper
Cite arxiv.org/abs/2607.07534 in a model README.md to link it from this page.
Datasets citing this paper1
#### cy0307/awesome-egocentric-atlas Viewer• Updatedabout 1 hour ago • 816 • 1.21k • 5
Spaces citing this paper0
No Space linking this paper
Cite arxiv.org/abs/2607.07534 in a Space README.md to link it from this page.
Collections including this paper0
No Collection including this paper
Add this paper to acollectionto link it from this page.
Similar Articles
LingBot World Infinity, Real-Time Exploration of Infinite Worlds
LingBot World Infinity enables real-time exploration of infinite virtual worlds, likely powered by an AI bot assistant.
MultiWorld: Scalable Multi-Agent Multi-View Video World Models
MultiWorld is a unified framework for multi-agent multi-view video world modeling that achieves accurate control of multiple agents while maintaining multi-view consistency through a Multi-Agent Condition Module and Global State Encoder.
@aigclink: Robbyant, Ant Group's embodied AI company, open-sourced the world model LingBot-World 2.0—capable of running continuously for over an hour with no noticeable degradation in image quality, and equipped with a brain-cerebellum-like agentic harness that allows the world to unfold persistently in response to user actions. The previous world…
Robbyant under Ant Group open-sourced the world model LingBot-World 2.0, supporting continuous operation for over an hour with no quality degradation, featuring a brain-cerebellum-like agentic harness, multiplayer support, and multiple interaction actions. Weights and code are open-sourced.
Multi-Agent World Models (3 minute read)
γ-World is a generative multi-agent world model that supports independently controllable, permutation-symmetric agents using Simplex Rotary Agent Encoding and Sparse Hub Attention, achieving real-time 24 FPS rollouts and zero-shot generalization from two to four players.
SimWorlds: A Multi-Agent System for Dynamic 3D Scene Creation
SimWorlds is a multi-agent framework that generates dynamic, editable 4D scenes from natural language, using Blender-specific procedural knowledge and a planner-coder-reviewer workflow, outperforming prior baselines.