ParticleGen: A Multi-Agent System for Particle Effects Generation

2026-08-01

AI Summary

This work addresses the challenge that current particle effect authoring requires specialized expertise and lacks direct, high-quality generation from natural language into editable representations. The authors propose a multi-agent framework that decouples planning and parameterization to generate structured particle systems from textual descriptions, incorporating a rendering-in-the-loop feedback mechanism for iterative refinement. A novel diagnostic module is introduced to precisely trace visual artifacts back to their procedural origins, enabling targeted adjustments. This approach establishes, for the first time, a reliable mapping from natural language to editable particle logic. Experiments in Unreal Engine 5 Niagara demonstrate significant improvements in semantic fidelity and visual quality across diverse scenarios—including spells, natural phenomena, and fireworks—substantially lowering the barrier to entry and accelerating the creative iteration process.

Abstract

Particle systems are widely used in digital entertainment to create dynamic scene elements and visual effects. However, authoring high-quality particle effects remains labor-intensive and demands specialized expertise, requiring practitioners to navigate complex procedural rules and high-dimensional parameter spaces. Recent large language models (LLMs) enable users to specify particle effects through natural language, yet reliably translating high-level creative intent into executable procedural logic and low-level parameters remains difficult. In this work, we present a multi-agent framework for the from-scratch synthesis of structured and editable particle systems from natural language descriptions. Given a text prompt, our framework first generates an initial particle configuration through a decoupled planning and parameterization pipeline, and then iteratively improves the result based on rendered feedback. To support precise and targeted adjustments, we further introduce a diagnostic mechanism that links observed visual artifacts to their underlying procedural causes. We validate our approach in Unreal Engine 5's Niagara system across a diverse set of scenarios, including elemental spells, dynamic natural phenomena, and fireworks. Quantitative and qualitative evaluations show that our method achieves high semantic fidelity and visual quality. By directly synthesizing structured particle simulation logic, our framework reduces the technical barrier to particle effect authoring and improves the efficiency of creative iteration.

Problem

• particle systems
• natural language
• procedural generation
• creative authoring
• visual effects

Innovation

• multi-agent system
• particle effects generation
• natural language to procedural logic
• iterative refinement with visual feedback
• structured simulation synthesis