研究：持久化检索子代理让多轮对话节省 43% token
Persistent Retrieval for Conversational Agents: A Study of Retrieval Efficiency
研究团队测了三种检索架构，持久化子代理在多轮对话里省了近一半 token 和成本，做 agent 的可以参考这些数字。
arXiv 论文对比了对话智能体的三种检索设计：主智能体内技能式检索、非持久化检索子代理、以及持久化检索子代理。持久化方案在多轮间保留检索历史，直接把证据返回给主智能体使用。在五个多轮测试场景中，该方案比技能式检索少用 43.3% 的 agent-model token，估算 API 成本降低 45.0%，平均响应时间缩短 9.1%。相比非持久化子代理，每个问题响应时间快 15.6 秒，但 token 多用 65.1%、成本高 29.1%。
Persistent Retrieval for Conversational Agents: A Study of Retrieval Efficiency
Conversational agents can retrieve information directly or delegate retrieval to a subagent. This design choice affects how retrieval history is maintained, what context each model call receives, and what information must be re-retrieved in follow-up questions. We compare three designs: skill-based retrieval in the main agent, a non-persistent retrieval subagent that generates a findings response, and our persistent retrieval subagent, which maintains retrieval history across turns and returns retrieved evidence directly to the main agent. Our approach also allows the main agent to request corrections from the same subagent. We evaluate the three designs on enterprise questions posed independently, within shared conversations, and as dependent follow-ups. Across five multi-turn settings, our approach uses 43.3% fewer recorded agent-model tokens and incurs 45.0% lower estimated API cost than skill-based retrieval, while reducing average response time by 9.1%. Compared with non-persistent retrieval, it reduces response time by 15.6 seconds per question, while using 65.1% more tokens and incurring 29.1% higher estimated API cost. Our approach shifts the retrieval subagent from producing synthesized responses to maintaining retrieval state and supplying evidence that the main agent can directly evaluate and use for answer generation.
