New framework uses LLM and GNN for natural language crowd simulation control

Researchers have developed CrowdDirector, a novel framework designed to orchestrate crowd simulations in real-time using natural language directives. This system employs a large language model (LLM) to interpret user instructions and translate them into structured commands. A scene validator then ensures these commands are compatible with the current simulation environment. CrowdDirector utilizes a graph neural network to select actions for individual agents based on active instructions and the simulation state, offering a practical balance between rigid rule-based systems and continuous LLM control. AI

IMPACT Enables more intuitive and flexible control over complex virtual environments, potentially impacting game development and simulation design.

RANK_REASON The cluster describes a research paper detailing a new framework for crowd simulation. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.MA (Multiagent) →

• arXiv
• CrowdDirector
• graph neural network
• large language model
• LLM
• Unity Technologies

• paper
• product

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →