让检索代理根据查询动态选最优配置，省成本又提效果。
Natural Language Query to Configuration for Retrieval Agents
- 用大模型分析查询特征，预测每种配置的答对概率
- 在预算与准确率间权衡，实测成本降89%仍保持最佳精度
- 适合需高效推理的智能客服、金融问答等场景
现代检索代理存在大量可配置项——如大模型选择、检索器、文档数量、跳数和合成策略——这些参数同时影响回答质量与服务成本。当前通常针对每个任务手工调参一次，未充分挖掘每查询优化潜力。本文提出**BRANE**，将自然语言查询转化为工作负载特徵，训练轻量级配置预测器以估计各管道的答对可能性。推理时，**BRANE**选择预测正确率最高且成本最低的配置，实现可调的性价比权衡，无需重新训练。在MuSiQue、BrowseComp-Plus和FinanceBench上，**BRANE**持续提升成本-准确率帕累托前沿，以最高89%的成本降低达到最优固定配置的准确率，并优于基于LLM路由、规则和微调Qwen3-4B的基线方法。结果表明，全管道的每查询配置是静态工作负载调优的可行替代方案。
原文摘要 · Abstract (English)
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 budget target, select from a predefined pipeline catalog the configuration that minimizes cost or maximizes accuracy at inference time. We propose **BRANE**, which uses an LLM to convert each query into workload-specific characteristics, then trains a lightweight per-configuration predictor that estimates whether the pipeline will answer the query correctly. At inference time, **BRANE** selects the configuration that maximizes predicted correctness penalized by cost, exposing a tunable cost-quality tradeoff without retraining. Across MuSiQue, BrowseComp-Plus, and FinanceBench, **BRANE** consistently pushes the cost-quality Pareto frontier, matches the best fixed configuration's accuracy at up to 89% lower cost, and outperforms LLM-routing, rule-based, and fine-tuned Qwen3-4B baselines. These results show that per-query configuration of the full retrieval pipeline is a practical alternative to static workload-level tuning.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。