SOURCE-LINKED INTELLIGENCE

LiteRAG: Cost-Efficient Graph-Based Retrieval-Augmented Generation

arXiv · AI, language, vision and robotics · article · Sep 9, 2026 · UTC

Graph-based retrieval can improve multi-hop question answering, but existing approaches often incur high query-time costs and produce diffuse, oversized contexts that reduce generation efficiency. We present LiteRAG, a graph-based retrieval method that replaces expensive retrieval-time LLM control with query-conditioned algorithmic exploration and reasoning-chain context construction. On DistComp, a benchmark for multi-hop retrieval over distributed-systems papers, LiteRAG attains the highest overall quality among the evaluated methods (0.798) while reducing per-query latency by over 100$\time

Read original source ↗ Open in workspace

recordType

paper

region

Global