paper-with-me

홈 › Papers

When Knowledge Is Not Free: Cost-Aware Evidence Selection in Retrieval-Augmented Generation

2026-06-01 · Mingyan Wu, Han Yang, Omer Ben-Porat, Yftah Ziser arxiv

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.

📄 PDF Abstract BibTeX arXiv:2606.02245

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Familiarity-Aware Evidence Compression for Retrieval-Augmented Generation

2024-09-19 · Dongwon Jung, Qin Liu, Tenghao Huang, Ben Zhou 외

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 Generation

Costly Evidence and Discretionary Disclosure

2022-08-09 · Mark Whitmeyer, Kun Zhang

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

2026-01-29 · Jiate Liu, Zebin Chen, Shaobo Qiao, Mingchen Ju 외 arxiv

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 Graphs

Neural Bayesian Sequential Routing

2026-05-22 · Yongchao Huang arxiv

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 Diagnosis

VaseMuseum: Digital Intelligent Museum for Ancient Greek Pottery

2026-07-07 · Jiazi Wang, Nonghai Zhang, Qiushi Xie, Zeyu Zhang 외 arxiv

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…