**摘要**
Modern retrieval agents expose many configuration choices -- LLM, retriever, number of documents, number of hops, and synthesis strategy -- each shaping both answer quality and serving cost. Today, these pipelines are typically hand-tuned once per workload, leaving substantial per-query optimization untapped. We formulate the problem: given a natural-language query and either an accuracy or a budg
👤 作者: Melissa Z. Pan, Negar Arabzadeh, Mathew Jacob, Fiodar Kazhamiaka, Esha Choukse, Matei Zaharia

---
🔗 **[Natural Language Query to Configuration for Retrieval Agents](https://arxiv.org/abs/2605.27361v1)**

> Natural Language Query to Configuration for Retrieval Agents
🏷️ 来源: ArXiv cs.AI
⏱️ 2026-05-28 08:01