PPAI: Enabling Personalized LLM Agent Interoperability for Collaborative Edge Intelligence

TL;DR

PPAI is a system that enables personalized LLM agents on edge devices to collaborate via P2P networks, improving task coverage and load balancing through novel matchmaking and game-theoretic strategies.

Contribution

It introduces PPAI, the first system for personalized LLM agent interoperability, with scalable query-agent matching and load balancing mechanisms for dynamic P2P environments.

Findings

Achieves up to 7.96% accuracy improvement across tasks.

Reduces latency by 16.34% compared to baseline.

Broadens task range for personalized LLM agents.

Abstract

Deploying large language model (LLM) on edge device enables personalized LLM agents for various users. The growing availability of diverse personalized agents presents a unique opportunity for peer-to-peer (P2P) collaboration, wherein each user can delegate tasks beyond the local agent's expertise to remote agents more suited for the specific query. This paper introduces PPAI, the first personalized LLM agent interoperability system, which enables users to collaborate with each other based on agent specialization. However, the ever-changing pool of agents and their interchangeable capacity introduce new challenges when it comes to matching queries to agents and balancing loads, compared with existing P2P systems. Therefore, we propose a scalable query-agent pair scoring mechanism based on prototypes to identify suitable agents within a P2P network with churn. Moreover, we propose a multi-agent interoperability Bayesian game to balance local demand and global efficiency, when changes in remote agent load occur too quickly to be observed. Finally, we implement a prototype of PPAI and demonstrate that it substantially broadens the range of tasks that could be carried out while maintaining load balance. On average, it achieves an accuracy improvement of up to 7.96% across multiple tasks, while reducing latency by 16.34% compared to the baseline.