RAG without Forgetting: Continual Query-Infused Key Memory

• URL: http://arxiv.org/abs/2602.05152v1
• Date: Thu, 05 Feb 2026 00:12:45 GMT
• Title: RAG without Forgetting: Continual Query-Infused Key Memory
• Authors: Yuntong Hu, Sha Li, Naren Ramakrishnan, Liang Zhao,
• Abstract summary: We propose Evolving Retrieval Memory (ERM), a training-free framework that transforms transient query-time gains into persistent retrieval improvements.<n>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.<n>We show that query and key expansion are theoretically equivalent under standard similarity functions and prove convergence of ERM's selective updates, amortizing optimal query expansion into a stable index with zero inference-time overhead.
• Score: 27.597076561986594
• License: http://creativecommons.org/licenses/by/4.0/
• 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 equivalent under standard similarity functions and prove convergence of ERM's selective updates, amortizing optimal query expansion into a stable index with zero inference-time overhead. Experiments on BEIR and BRIGHT across 13 domains demonstrate consistent gains in retrieval and generation, particularly on reasoning-intensive tasks, at native retrieval speed.

Related papers

• GAM-RAG: Gain-Adaptive Memory for Evolving Retrieval in Retrieval-Augmented Generation [16.737829113782126]
  Retrieval-Augmented Generation (RAG) grounds large language models with external evidence, but many implementations rely on pre-built indices that remain static after construction.<n>Motivated by schema-based learning in cognitive neuroscience, we propose GAM-RAG, a training-free framework that accumulates retrieval experience from recurring or related queries.<n>GAM-RAG builds a lightweight, relation-free hierarchical index whose links capture potential co-occurrence rather than fixed semantic relations.
  arXiv  Detail & Related papers  (2026-03-02T12:09:17Z)
• MEMTS: Internalizing Domain Knowledge via Parameterized Memory for Retrieval-Free Domain Adaptation of Time Series Foundation Models [51.506429027626005]
  Memory for Time Series (MEMTS) is a lightweight and plug-and-play method for retrieval-free domain adaptation in time series forecasting.<n>Key component of MEMTS is a Knowledge Persistence Module (KPM), which internalizes domain-specific temporal dynamics.<n>This paradigm shift enables MEMTS to achieve accurate domain adaptation with constant-time inference and near-zero latency.
  arXiv  Detail & Related papers  (2026-02-14T14:00:06Z)
• Multi-hop Reasoning via Early Knowledge Alignment [68.28168992785896]
  Early Knowledge Alignment (EKA) aims to align Large Language Models with contextually relevant retrieved knowledge.<n>EKA significantly improves retrieval precision, reduces cascading errors, and enhances both performance and efficiency.<n>EKA proves effective as a versatile, training-free inference strategy that scales seamlessly to large models.
  arXiv  Detail & Related papers  (2025-12-23T08:14:44Z)
• Modeling Uncertainty Trends for Timely Retrieval in Dynamic RAG [35.96258615258145]
  We introduce Entropy-Trend Constraint (ETC), a training-free method that determines optimal retrieval timing by modeling the dynamics of token-level uncertainty.<n>ETC consistently outperforms strong baselines while reducing retrieval frequency.<n>It is plug-and-play, model-agnostic, and readily integrable into existing decoding pipelines.
  arXiv  Detail & Related papers  (2025-11-13T05:28:02Z)
• TeaRAG: A Token-Efficient Agentic Retrieval-Augmented Generation Framework [62.66056331998838]
  TeaRAG is a token-efficient agentic RAG framework capable of compressing both retrieval content and reasoning steps.<n>Our reward function evaluates the knowledge sufficiency by a knowledge matching mechanism, while penalizing excessive reasoning steps.
  arXiv  Detail & Related papers  (2025-11-07T16:08:34Z)
• Rethinking On-policy Optimization for Query Augmentation [49.87723664806526]
  We present the first systematic comparison of prompting-based and RL-based query augmentation across diverse benchmarks.<n>We introduce a novel hybrid method, On-policy Pseudo-document Query Expansion (OPQE), which learns to generate a pseudo-document that maximizes retrieval performance.
  arXiv  Detail & Related papers  (2025-10-20T04:16:28Z)
• Enhancing Retrieval-Augmented Generation with Two-Stage Retrieval: FlashRank Reranking and Query Expansion [0.0]
  RAG couples a retriever with a large language model (LLM) to ground generated responses in external evidence.<n>We propose a two-stage retrieval pipeline that integrates LLM-driven query expansion to improve candidate recall.<n>FlashRank is a fast marginal-utility reranker that dynamically selects an optimal subset of evidence under a token budget.
  arXiv  Detail & Related papers  (2025-10-17T15:08:17Z)
• Accelerating LLM Inference with Precomputed Query Storage [0.13048920509133805]
  StorInfer is a storage-assisted large language model (LLM) inference system.<n>When a user query semantically matches a precomputed query, StorInfer bypasses expensive GPU inference and instantly returns the stored response.
  arXiv  Detail & Related papers  (2025-09-30T08:14:04Z)
• Leveraging Approximate Caching for Faster Retrieval-Augmented Generation [6.674782158041247]
  We introduce Proximity, an approximate key-value cache that optimize the RAG workflow by leveraging similarities in user queries.<n>Instead of treating each query independently, Proximity reuses previously retrieved documents when similar queries appear.<n>Our experiments demonstrate that Proximity with our LSH scheme and a realistically-skewed MedRAG workload reduces database calls by 77.2% while maintaining database recall and test accuracy.
  arXiv  Detail & Related papers  (2025-03-07T15:54:04Z)
• Chain-of-Retrieval Augmented Generation [91.02950964802454]
  This paper introduces an approach for training o1-like RAG models that retrieve and reason over relevant information step by step before generating the final answer.<n>Our proposed method, CoRAG, allows the model to dynamically reformulate the query based on the evolving state.
  arXiv  Detail & Related papers  (2025-01-24T09:12:52Z)
• Corrective Retrieval Augmented Generation [36.04062963574603]
  Retrieval-augmented generation (RAG) relies heavily on relevance of retrieved documents, raising concerns about how the model behaves if retrieval goes wrong. We propose the Corrective Retrieval Augmented Generation (CRAG) to improve the robustness of generation. CRAG is plug-and-play and can be seamlessly coupled with various RAG-based approaches.
  arXiv  Detail & Related papers  (2024-01-29T04:36:39Z)
• Noise-Robust Dense Retrieval via Contrastive Alignment Post Training [89.29256833403167]
  Contrastive Alignment POst Training (CAPOT) is a highly efficient finetuning method that improves model robustness without requiring index regeneration. CAPOT enables robust retrieval by freezing the document encoder while the query encoder learns to align noisy queries with their unaltered root. We evaluate CAPOT noisy variants of MSMARCO, Natural Questions, and Trivia QA passage retrieval, finding CAPOT has a similar impact as data augmentation with none of its overhead.
  arXiv  Detail & Related papers  (2023-04-06T22:16:53Z)
• Generation-Augmented Retrieval for Open-domain Question Answering [134.27768711201202]
  Generation-Augmented Retrieval (GAR) for answering open-domain questions. We show that generating diverse contexts for a query is beneficial as fusing their results consistently yields better retrieval accuracy. GAR achieves state-of-the-art performance on Natural Questions and TriviaQA datasets under the extractive QA setup when equipped with an extractive reader.
  arXiv  Detail & Related papers  (2020-09-17T23:08:01Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.