让大模型在预算内智能选知识，避免付费墙浪费资源
When Knowledge Is Not Free: Cost-Aware Evidence Selection in Retrieval-Augmented Generation
- 引入代价感知检索机制，给知识源分等级收费
- 固定策略无效，大预算也不一定提升回答质量
- 用智能代理动态决策何时查、查哪级，适应性强
检索增强生成（RAG）通常假设外部知识免费获取，但许多高质量数据源需付费或受限制。本文提出代价感知RAG，为检索证据设置访问成本层级，系统需在明确的预算内作答。通过在MS MARCO v2.1上增加访问摩擦层级，评估通用与领域特定问答任务中的预算约束证据选择。结果表明：静态选择策略脆弱，无通用最优方案；即使高成本证据与领域匹配，更大预算也未必提升质量。随后研究基于代理的代价感知RAG，由大模型自主决定是否检索、选择哪个层级、何时停止。代理展现作为自适应证据获取控制器的巨大潜力，但行为高度依赖模型与任务。这些发现表明，代价感知证据获取是下一代RAG系统的核心挑战。所有代码与数据已开源。
原文摘要 · Abstract (English)
Retrieval-Augmented Generation (RAG) typically assumes that external knowledge is free, but many high-quality sources are paywalled, licensed, restricted, or otherwise costly to access. We introduce cost-aware RAG, a setting where retrieved evidence is assigned access-cost tiers and systems must answer under an explicit evidence-access budget. We instantiate this setting by augmenting MS MARCO v2.1 with access-friction tiers and evaluate budgeted evidence selection across general-domain and domain-specific QA benchmarks. Our results show that static selection is brittle: no fixed selector uniformly dominates, and larger budgets do not reliably improve answer quality, even when costly evidence is domain-matched. We then study agentic cost-aware RAG, where an LLM decides when to retrieve, which tier to access, and when to stop. Agents show strong promise as adaptive evidence-acquisition controllers, but their behavior remains highly model- and task-dependent. These findings suggest that cost-aware evidence acquisition is a central challenge for the next generation of RAG systems. All code and data are available at https://github.com/Mignonmy/Cost-Aware.
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。