RAG Without Forgetting: Continual Query-infused Key Memory

Abstract

Retrieval-augmented generation (RAG) systems commonly improve robustness via query-time adaptations such as query expansion and iterative retrieval. While effective, these approaches are inherently stateless: adaptations are recomputed for each query and discarded thereafter, precluding cumulative learning and repeatedly incurring inference-time cost. Index-side approaches like key expansion introduce persistence but rely on offline preprocessing or heuristic updates that are weakly aligned with downstream task utility, leading to semantic drift and noise accumulation. We propose Evolving Retrieval Memory (ERM), a training-free framework that transforms transient query-time gains into persistent retrieval improvements. ERM updates the retrieval index through correctness-gated feedback, selectively attributes atomic expansion signals to the document keys they benefit, and progressively evolves keys via stable, norm-bounded updates. We show that query and key expansion are theoretically

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyhu2026rag

Related papers

• A Dynamic Retrieval-augmented Generation System With Selective Memory And Remembrance (2026)0.00
• HASH-RAG: Bridging Deep Hashing With Retriever For Efficient, Fine Retrieval And Augmented Generation (2025)0.00
• Domain-aware RAG: Mol-enhanced RL For Efficient Training And Scalable Retrieval (2025)0.00
• Hetarag: Hybrid Deep Retrieval-augmented Generation Across Heterogeneous Data Stores (2025)3.27
• Frustratingly Simple Retrieval Improves Challenging, Reasoning-intensive Benchmarks (2025)0.00
• Optimizing Retrieval For RAG Via Reinforcement Learning (2025)0.00
• Slimrag: Retrieval Without Graphs Via Entity-aware Context Selection (2025)1.91
• Edgerag: Online-indexed RAG For Edge Devices (2024)0.00