Persistent Retrieval Subagent Cuts Token Use and Cost in Conversational Agents
This paper compares three retrieval designs for conversational agents: skill-based retrieval, non-persistent subagent, and a persistent retrieval subagent that maintains history across turns. The persistent approach reduces token usage by 43.3% and API cost by 45.0% versus skill-based retrieval, while also cutting response time by 9.1%. It shifts the subagent's role from synthesizing answers to maintaining state and supplying evidence for the main agent.
Why it matters: Provides concrete efficiency gains for a common agent architecture, offering actionable design insights for developers building conversational AI systems.