Title: A Communication-Focused 6G-LLM Framework for Expanding Tactical Autonomous Defense Vehicle Networks

Abstract:

The convergence of Artificial Intelligence (AI) and next-generation 6G networks creates fresh possibilities for achieving scalable coordination within tactical autonomous vehicle systems. This study introduces a hierarchical, communication-driven architecture for Tactical Autonomous Defense Vehicle Networks (TADVNs), which integrates edge-supported Large Language Model (LLM) reasoning with 6G connectivity and semantic communication protocols. The proposed framework aims to boost coordination efficiency, minimize communication burden, and strengthen resilience against latency issues as fleet operations scale up. In contrast to traditional task-oriented AI pipelines that depend on rule-based coordination and structured feature processing, this approach embeds context-aware decision support and semantic abstraction into a layered edge-cloud communication structure.

We assessed communication and coordination metrics through Monte Carlo simulations involving fleets ranging from 5 to 30 vehicles operating under contested network conditions. The data reveals significant advantages at the 30-vehicle scale: the 6G-LLM setup delivered a 75.2% decrease in latency (dropping from 117.5 ms to 29.1 ms), an 88.6% cut in communication overhead, and a 68.7 percentage point surge in mission success rates (rising from 14.2% to 82.9%) when compared to a conventional AI baseline powered by 5G. These outcomes highlight the tangible improvements in both communication and coordination that result from pairing semantic reasoning with the low-latency capabilities of 6G networks.

Source: arXiv Generated at: 2026-06-02 00:00:00 UTC