When Knowledge Is Not Free: Cost-Aware Evidence Selection in Retrieval-Augmented Generation
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.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Familiarity-Aware Evidence Compression for Retrieval-Augmented Generation
Retrieval-augmented generation (RAG) improves large language models (LMs) by incorporating non-parametric knowledge through evidence retrieved from external sources. However, it often struggles to cope with inconsistent …
RAGRetrievalRetrieval-augmented GenerationCostly Evidence and Discretionary Disclosure
A sender flexibly acquires evidence--which she may pay a third party to certify--to disclose to a receiver. When evidence acquisition is overt, the receiver observes the evidence gathering process irrespective of whether…
A2RAG: Adaptive Agentic Graph Retrieval for Cost-Aware and Reliable Reasoning
Graph Retrieval-Augmented Generation (Graph-RAG) enhances multihop question answering by organizing corpora into knowledge graphs and routing evidence through relational structure. However, practical deployments face two…
Question AnsweringKnowledge GraphsNeural Bayesian Sequential Routing
Human decision-making is sequential and uncertainty-aware, yet standard neural networks often rely on static, dense forward computation with limited visibility into evidence acquisition, uncertainty evolution, or when co…
Medical DiagnosisVaseMuseum: Digital Intelligent Museum for Ancient Greek Pottery
Vision-language models (VLMs) have made interactive digital museums increasingly feasible by connecting 3D digitization with natural-language artifact exploration. However, in cultural heritage domains such as ancient Gr…