Scalable, Symbiotic, AI and Non-AI Agent Based Parallel Discrete Event Simulations

TL;DR

This paper presents a scalable parallel discrete event simulation framework that combines AI and non-AI agents to improve accuracy and enforce correctness through a causal, rule-based approach, enabling trustworthy and scalable multi-agent AI systems.

Contribution

It introduces a novel PDES-based methodology for integrating AI and non-AI agents with dynamic constraints and verification, enhancing scalability and accuracy in multi-agent simulations.

Findings

Achieved 68% accuracy with the combined approach versus less than 23% with AI alone.

Enabled scalable simulations with hundreds of agents in a compute cluster.

Demonstrated improved problem-solving accuracy across four diverse domains.

Abstract

To fully leverage the potential of artificial intelligence (AI) systems in a trustworthy manner, it is desirable to couple multiple AI and non-AI systems together seamlessly for constraining and ensuring correctness of the output. This paper introduces a novel parallel discrete event simulation (PDES) based methodology to combine multiple AI and non-AI agents in a causal, rule-based way. Our approach tightly integrates the concept of passage of time, with each agent considered as an entity in the PDES framework and responding to prior requests from other agents. Such coupling mechanism enables the agents to work in a co-operative environment towards a common goal while many tasks run in parallel throughout the simulation. It further enables setting up boundaries to the outputs of the AI agents by applying necessary dynamic constraints using non-AI agents while allowing for scalability through deployment of hundreds of such agents in a larger compute cluster. Distributing smaller AI agents can enable extremely scalable simulations in the future, addressing local memory bottlenecks for model parameter storage. Within a PDES involving both AI and non-AI agents, we break down the problem at hand into structured steps, when necessary, providing a set of multiple choices to the AI agents, and then progressively solve these steps towards a final goal. At each step, the non-AI agents act as unbiased auditors, verifying each action by the AI agents so that certain rules of engagement are followed. We evaluate our approach by solving four problems from four different domains and comparing the results with those from AI models alone. Our results show greater accuracy in solving problems from various domains where the AI models struggle to solve the problems solely by themselves. Results show that overall accuracy of our approach is 68% where as the accuracy of vanilla models is less than 23%.