Agentic World Modeling: Foundations, Capabilities, Laws, and Beyond
-
Updated
Sep 3, 2026 - TypeScript
Agentic World Modeling: Foundations, Capabilities, Laws, and Beyond
🔥 Data Pyramid for Embodied Manipulation: A Survey
[Roadmap] Visual Generation in the New Era: An Evolution from Atomic Mapping to Agentic World Modeling
Dockerized ROS2 stack for the WATonomous Autonomous Driving Software Pipeline
Top Agent Swarm Simulation Tools for LLM World Modeling 2026
🔥 Quo Vadis, World Modeling? Towards Interactive World Proxies for Continually Improving Agents
[EMNLP 2026] Aligning Agentic World Models via Knowledgeable Experience Learning
Agent swarm simulation for structured world modeling with LLMs. Built on AgentOS.
[ICLR 2025] Implementation of "FACTS: A Factored State-Space Framework For World Modelling"
WorldReasonBench: Human-Aligned Stress Testing of Video Generators as Future World-State Predictors
DreamerX is an implementation of model-based DreamerV3 with minor optimizations and novel training adjustments. It is designed to be flexible and user-friendly, allowing researchers and practitioners to easily interchange components and environments.
Super-advanced agentic AI framework for cyber-Vikings. Birth autonomous, self-evolving thoughtforms that manifest as hyper-realistic 3D digital characters. Features persistent memory, ritual invocations, full VR/Unity integration, and gloriously unaligned intelligence. Pure modernist cyber-Heathenry — no gatekeeping, pure emergence. 🔥⚔️🤖
SWITCH: Benchmarking Modeling and Handling of Tangible Interfaces in Long-horizon Embodied Scenarios
Code to train quickly and efficiently diffusion-based neural environments with just 500 lines of code
[CoRL 2025] This repository contains the code used to create the website for our CoRL workshop, "Beyond Rigid World: Representing and Interacting with Non-Rigid Objects" held in Seoul, Korea.
构建可验证的因果世界,并研究智能体如何在其中学习、交互与演化的 AI 原生模拟平台 | An AI-native simulation platform for building verifiable causal worlds and studying how agents learn, interact, and evolve within them.
An elite reasoning agent trained via GRPO to navigate high-stakes social conflicts. Built on OpenEnv to solve cascading scheduling chaos with human-centric judgment.
Specification and design of MUD, a declarative language for modeling rules, worlds, and simulations.
A world model component for the technical challenge of RoboCup 2024 SPL
To associate your repository with the world-modeling topic, visit your repo's landing page and select "manage topics."