Aethon: A Reference-Based Replication Primitive for Constant-Time Instantiation of Stateful AI Agents

ArXi:2604.12129v1 Announce Type: new The transition from stateless model inference to stateful agentic execution is reshaping the systems assumptions underlying modern AI infrastructure. While large language models have made persistent, tool-using, and collaborative agents technically viable, existing runtime architectures remain constrained by materialization-heavy instantiation models that impose significant latency and memory overhead. We present the conceptual framework, system architecture, and memory model underlying Aethon, including layered inheritance and copy-on-write semantics.