arXiv AI August 25, 2026 By Ryuki Hyodo

Minimal Local Simulation Foundations for LLM- and VLM-Driven Agents in 2D and 3D Environments

The paper introduces two minimal simulation foundations—SD-AgentFoundry-2D and SD-AgentFoundry-3D—for educational and rapid prototyping use with large language models (LLMs) and vision-language models (VLMs). SD-AgentFoundry-2D offers a 2D multi‑agent environment where LLM agents move, communicate, and react to local events such as fire, while SD-AgentFoundry-3D provides a 3D digital‑twin setting where a VLM interprets first‑person images to generate natural‑language movement instructions. Both frameworks run locally on macOS, Windows, and Linux, are intentionally lightweight, and are open for modification rather than being finished applications.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Hugging Face Trending Papers

Aug 24

Minimal Local Simulation Foundations for LLM- and VLM-Driven Agents in 2D and 3D Environments

Large language models (LLMs) and vision-language models (VLMs) are expanding the range of behaviors that can be represented in agent-based simulations, but many contemporary platforms are difficult to...

llms agents multimodal

arXiv AI

Jul 2

SenseWalk: Agent-Based Semantic Trajectory Simulation Powered by Large Language Models in Zoned Environments

arXiv:2607. 00989v1 Announce Type: cross Abstract: Semantic trajectory analysis has recently emerged as an approach for modeling human movement by capturing implicit patterns and behaviors through semantic information (e.

By Ziyue Lin, Xinhang Xie, Kangyi Wang, Siming Chen

llms agents

arXiv AI

Jul 24

GS-Agent: Creating 4D Physical Worlds With Generative Simulation

arXiv:2607. 21522v1 Announce Type: cross Abstract: Creating dynamic and physically realistic 4D worlds from natural language descriptions is both fascinating and challenging.

By Hongxin Zhang, Chunru Lin, Junyan Li, Zhou Xian, Tsun-Hsuan Wang, Chuang Gan

agents robotics fine-tuning multimodal

arXiv AI

Jun 10

TinyTroupe: An LLM-powered Multiagent Persona Simulation Toolkit

arXiv:2507. 09788v3 Announce Type: replace-cross Abstract: Recent advances in Large Language Models (LLM) have led to a new class of autonomous agents, renewing and expanding interest in the area.

By Paulo Salem, Robert Sim, Christopher Olsen, Prerit Saxena, Rafael Barcelos, Yi Ding

llms agents

arXiv AI

Jun 2

Coding Agent Is Good As World Simulator

arXiv:2605. 14398v2 Announce Type: replace Abstract: World models have emerged as a powerful paradigm for building interactive simulation environments, with recent video-based approaches demonstrating impressive progress in generating visually plausible dynamics.

By Hongyu Wang, Jingquan Wang, Bocheng Zou, Radu Serban, Dan Negrut

agents robotics

Hugging Face Trending Papers

Jul 2

SimWorlds: A Multi-Agent System for Dynamic 3D Scene Creation

LLM agents are increasingly used to translate natural language into 3D scenes in a procedural way, but existing systems focus on static output. Dynamic 4D scenes from text alone, in which liquids flow, particles emit, rigid bodies cascade, and articulated mechanisms move, remain largely unexplored despite their value as editable content and as physics-grounded training data for video generation and embodied AI.

llms agents diffusion robotics benchmarks

One email a morning, machine-written

Related stories

Minimal Local Simulation Foundations for LLM- and VLM-Driven Agents in 2D and 3D Environments

SenseWalk: Agent-Based Semantic Trajectory Simulation Powered by Large Language Models in Zoned Environments

GS-Agent: Creating 4D Physical Worlds With Generative Simulation

TinyTroupe: An LLM-powered Multiagent Persona Simulation Toolkit

Coding Agent Is Good As World Simulator

SimWorlds: A Multi-Agent System for Dynamic 3D Scene Creation