Loading...
In-Mig: Geographically Dispersed Agentic LLMs for Privacy-Preserving Artificial Intelligence
Type
Supervisor
Subject
Date
2026-03-12
Collections
Files
Loading...
TSP_CMC_77259.pdf
Adobe PDF, 1.13 MB
Research Projects
Organizational Units
Journal Issue
Abstract
Large Language Models (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. A prototype using JADE for mobility and quantized Mistral-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.
Department
Publisher
Sponsor
None
Copyright
Attribution-NonCommercial-NoDerivatives 4.0 International