Trade-offs in Decentralized Agentic AI Discovery Across the Compute Continuum
For researchers designing decentralized agentic AI systems, this work provides a comparative analysis of structured overlays for discovery, though it is an incremental evaluation rather than a novel solution.
This paper evaluates three DHT-based overlays (Chord, Pastry, Kademlia) for decentralized agent discovery across cloud-edge environments, finding that each offers distinct trade-offs in reliability, startup behavior, and overhead under churn and stationary conditions on a 4096-node benchmark.
Agentic systems deployed across the compute continuum need discovery mechanisms that remain effective across cloud, edge, and intermittently connected domains. In some emerging agentic architectures, decentralized discovery is already an active design direction, placing DHT-based lookup on the path toward agent directories. This paper studies the trade-offs among major structured-overlay families for agent discovery, comparing Chord, Pastry, and Kademlia as candidate indexing substrates within a shared control-plane framework. Using a benchmark subset centered on a 4096-node stationary comparison and a representative 4096-node churn benchmark, the paper characterizes how discovery reliability, startup behavior, and control-plane overhead vary across these overlays. The goal is to clarify the operating points they expose for agent discovery across edge-to-cloud environments.