ScalableRAG: High-Quality RAG with Exact Corpus Operations at Minimal Ingestion Cost
On this page
arXiv:2607.25135v2 Announce Type: replace Abstract: RAG systems face a capability-cost gap: lightweight retrievers locate evidence but expose no operands for exact corpus-level operations (counts, intersections, aggregations), while knowledge ingestion systems obtain them only through expensive ingestion. ScalableRAG closes this gap with a persistent typed-set workspace: an agent builds named document and value sets at query time and composes them through set algebra, typed extraction, aggregation, and diagnostics. Zero-Ingestion ScalableRAG needs no preprocessing, not even a vector index. It matches the leading baseline on four conventional QA benchmarks (74.75 versus 74.64) and on aggregative Hotels-50 beats every evaluated system, scoring 71.74: 36.23 above the leading baseline (SRAG), and 40.22 points above A-RAG. Removing the workspace drops Hotels-50 to 38.4. On Hotels-350, the partition SRAG itself reports on, ScalableRAG leads SRAG by 9.3 points. Limited-Ingestion ScalableRAG adds a lightweight index and is the only evaluated system above 80 judge score at 5M documents, at 13 to 16 seconds per question and under 20 minutes ingestion; at 1M it scores 84.5 to A-RAG’s 80.0 with 16x lower latency and 0.5% of its ingestion time. ScalableRAG combines minimal ingestion, conventional-QA parity, exact corpus operations, and million-document viability; no evaluated alternative provides all four. Our code is available at https://github.com/cohesity/ScalableRAG .
Why It Matters
ScalableRAG addresses the capability–cost gap in retrieval-augmented generation: lightweight retrievers locate evidence but cannot perform exact corpus-level operations like counts, intersections, and aggregations, which usually require expensive ingestion. By letting an agent build typed sets at query time and compose them with set algebra, it achieves strong QA results with zero ingestion—even beating dedicated baselines on aggregative tasks. This matters for making RAG high-quality without heavy preprocessing. See Large Language Models, Inference and Serving, and Agents, Tools, and Agent Frameworks.
Sources
Back to Recent News · Sub-article index.