In-Mig:Geographically Dispersed Agentic LLMs for Privacy-Preserving Artificial IntelligenceOA
Large LanguageModels(LLMs)are increasingly utilized for semantic understanding and reasoning,yet their use in sensitive settings is limited by privacy concerns.This paper presents In-Mig,a mobile-agent architecture that integrates LLM reasoning within agents that can migrate across organizational venues.Unlike centralized approaches,In-Mig performs reasoning in situ,ensuring that raw data remains within institutional boundaries while allowing for cross-venue synthesis.The architecture features a policy-scoped memory model,utility-driven route planning,and cryptographic trust enforcement.Aprototype using JADE for mobility and quantizedMistral-7B demonstrates practical feasibility.Evaluation across various scenarios shows that In-Mig achieves 92%similarity to centralized baselines,confirming its utility and strong privacy guarantees.These results suggest that migrating,privacy-preserving LLM agents can effectively support decentralized reasoning in trust-sensitive domains.
Mohammad Nauman
Department of Computer Science,Effat College of Engineering,Effat University,Jeddah,22332,Saudi Arabia
信息技术与安全科学
Mobile agentslarge language models(LLMs)privacy-preserving AIdecentralized reasoningtrust and security
《Computers, Materials & Continua》 2026 (5)
P.1101-1115,15
评论