REVA: Reusable Evidence View Aggregation for Context-Efficient RAG Serving

Excerpt

arXiv:2609.11209v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) improves knowledge-intensive large language model (LLM) applications by conditioning generation on retrieved documents, but longer contexts increase latency, key-value (KV) cache memory, and token cost. Post-retrieval compression can reduce this cost, yet existing compressors often operate independently for each query, rely on auxiliary models or rewriting, and introduce online overhead that can offset the ben