TY  - EJOU
AU  - Nauman, Mohammad 

TI  - In-Mig: Geographically Dispersed Agentic LLMs for Privacy-Preserving Artificial Intelligence
T2  - Computers, Materials \& Continua

PY  - 2026
VL  - 87
IS  - 2
SN  - 1546-2226

AB  - 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 <i>In-Mig</i>, a mobile-agent architecture that integrates LLM reasoning within agents that can migrate across organizational venues. Unlike centralized approaches, In-Mig performs reasoning <i>in situ</i>, 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.
KW  - Mobile agents; large language models (LLMs); privacy-preserving AI; decentralized reasoning; trust and security

DO  - 10.32604/cmc.2026.077259