Papers

Managing Context and Communication in Distributed Agentic UAV Swarms

This accepted IEEE CCNC 2027 paper presents a fully distributed UAV swarm architecture in which each drone runs an independent Small Language Model, a bounded context manager, and a deterministic interest-aware gossip engine. In 10-UAV simulated search-and-rescue trials, it completes 100% of runs, whereas unrestricted flooding completes 70–85% and SLM-delegated forwarding completes 0%, while cutting inference tokens roughly in half and transmitting under 0.5 MB per mission versus 6–7 MB. This matters because it shows edge-deployed language-model agents can control swarms without central connectivity, context rot, or bandwidth blowup.