A Dynamic Retrieval-Augmented Generation System with Selective Memory and Remembrance

• URL: http://arxiv.org/abs/2601.02428v1
• Date: Sun, 04 Jan 2026 21:51:41 GMT
• Title: A Dynamic Retrieval-Augmented Generation System with Selective Memory and Remembrance
• Abstract summary: We introduce emph Adaptive RAG Memory (ARM), a retrieval-augmented generation (RAG) framework that replaces a static vector index with a emphdynamic memory substrate.<n>ARM reaches near state-of-the-art performance on a lightweight retrieval benchmark.<n>ARM yields competitive accuracy, self-regularizing memory growth, and interpretable retention dynamics without retraining the generatorcolorblack and provides practical trade-off between quality, latency and memory efficiency for production and research RAG system.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: We introduce \emph{Adaptive RAG Memory} (ARM), a retrieval-augmented generation (RAG) framework that replaces a static vector index with a \emph{dynamic} memory substrate governed by selective remembrance and decay. Frequently retrieved items are consolidated and protected from forgetting, while rarely used items gradually decay, inspired by cognitive consolidation and forgetting principles. On a lightweight retrieval benchmark, ARM reaches near state-of-the-art performance (e.g., NDCG@5 $\approx$ 0.940, Recall@5 $=1.000$) with only $\sim$22M parameters in the embedding layer, achieving the best efficiency among ultra-efficient models ($<$25M parameters). In addition, we compare static vs. dynamic RAG combinations across Llama 3.1 and GPT-4o. Llama 3.1 with static RAG achieves the highest key-term coverage (67.2\%) at moderate latency, while GPT-4o with a dynamic selective retrieval policy attains the fastest responses (8.2s on average) with competitive coverage (58.7\%). We further present an engineering optimization of the DynamicRAG implementation, making embedding weights configurable, adjustable at runtime, and robust to invalid settings. ARM yields competitive accuracy, self-regularizing memory growth, and interpretable retention dynamics without retraining the generator\color{black} and provides practical trade-off between quality, latency and memory efficiency for production and research RAG system.

Related papers

• HARD-KV: Head-Adaptive Regularization for Decoding-time KV Compression [11.40656413331368]
  Long-context LLM inference faces a fundamental conflict: head-adaptive compression algorithms offer superior accuracy by dynamically fluctuating memory budgets.<n>Yet modern inference engines demand rigid, static memory patterns to leverage Graphs and PagedAttention.<n>We resolve this Static-Dynamic'' mismatch with HARD-KV, a unified framework that bridges dynamic selection with rigid system constraints.
  arXiv  Detail & Related papers  (2026-06-27T09:36:37Z)
• CDS4RAG: Cyclic Dual-Sequential Hyperparameter Optimization for RAG [4.208654120634349]
  We propose CDS4RAG, a framework to optimize the Retrieval-Augmented Generation using given queries.<n>We show that CDS4RAG significantly boosts the vanilla algorithms in 21/24 cases while significantly outperforming state-of-the-art algorithms in all cases with up to 1.54x improvements of generation quality and better speedup.
  arXiv  Detail & Related papers  (2026-05-08T17:58:11Z)
• MEMTIER: Tiered Memory Architecture and Retrieval Bottleneck Analysis for Long-Running Autonomous AI Agents [6.8552591401084015]
  We present MEMTIER, a tripartite memory architecture for the OpenClaw agent.<n>On the full LongMemEval-S benchmark, MEMTIER achieves Acc.382, F1=.412 with Qwen2.5-7B on a consumer 6GB GPU.<n>With DeepSeek-V4-Flash fact pre-population, single-session recall reaches 0.686-0.714, exceeding the paper's RAG GPT-4o on those categories.
  arXiv  Detail & Related papers  (2026-05-05T12:14:10Z)
• Auto-FlexSwitch: Efficient Dynamic Model Merging via Learnable Task Vector Compression [54.12624130407679]
  We propose T-Switch, which decomposes task vectors into three compact components.<n>We then introduce Auto-Switch, a training-free merging scheme that automatically composes task vectors.<n>We present Auto-FlexSwitch, a dynamic model merging approach that supports highly efficient task vector compression.
  arXiv  Detail & Related papers  (2026-04-30T16:58:05Z)
• AdaFuse: Accelerating Dynamic Adapter Inference via Token-Level Pre-Gating and Fused Kernel Optimization [84.25316984309725]
  Integration of dynamic, sparse structures with parameter-efficient adapters (e.g., LoRA) is a powerful technique for enhancing Large Language Models (LLMs)<n>Despite minimal increases in computational load, the computation latency often skyrockets, leading to decoding speeds slowing by over 2.5 times.<n>AdaFuse is a framework built on a tight co-design between the algorithm and the underlying hardware system to enable efficient dynamic adapter execution.
  arXiv  Detail & Related papers  (2026-03-12T12:46:42Z)
• LoGeR: Long-Context Geometric Reconstruction with Hybrid Memory [97.14005794889134]
  We present LoGeR, a novel architecture that scales dense 3D reconstruction to extremely long sequences without post-optimization.<n>LoGeR processes video streams in chunks, leveraging strong bidirectional priors for high-fidelity intra-chunk reasoning.<n>This memory architecture enables LoGeR to be trained on sequences of 128 frames, and generalize up to thousands of frames during inference.
  arXiv  Detail & Related papers  (2026-03-03T18:55:37Z)
• SimpleMem: Efficient Lifelong Memory for LLM Agents [73.74399447715052]
  We introduce SimpleMem, an efficient memory framework based on semantic lossless compression.<n>We propose a three-stage pipeline designed to maximize information density and token utilization.<n> Experiments on benchmark datasets show that our method consistently outperforms baseline approaches in accuracy, retrieval efficiency, and inference cost.
  arXiv  Detail & Related papers  (2026-01-05T21:02:49Z)
• RAGSmith: A Framework for Finding the Optimal Composition of Retrieval-Augmented Generation Methods Across Datasets [0.0]
  RAGSmith is a framework that treats RAG as an end-to-end architecture search over nine technique families and 46,080 feasible pipeline configurations.<n>We evaluate on six Wikipedia-derived domains (Law, Finance, Medicine, Defense Industry, Computer Science) each with 100 questions spanning design, interpretation, and long-answer types.<n>RAGSmith consistently outperform naive RAG configurations by +3.8% on average (range +1.2% to +6.9% across domains), with gains up to +12.5% in retrieval and +7.5% in generation.
  arXiv  Detail & Related papers  (2025-11-03T09:36:27Z)
• HyperAdaLoRA: Accelerating LoRA Rank Allocation During Training via Hypernetworks without Sacrificing Performance [27.391727025825546]
  Low-Rank Adaptation (LoRA) has emerged as a promising approach to fine-tuning large language models.<n>We propose HyperAdaLoRA, a novel framework that accelerates the convergence of AdaLoRA by leveraging a hypernetwork.<n>Our method achieves faster convergence without sacrificing performance.
  arXiv  Detail & Related papers  (2025-10-03T00:15:59Z)
• TempSamp-R1: Effective Temporal Sampling with Reinforcement Fine-Tuning for Video LLMs [67.55973229034319]
  This paper introduces TempSamp-R1, a new reinforcement fine-tuning framework designed to improve the effectiveness of adapting multimodal large language models (MLLMs) to video temporal grounding tasks.<n>We show that TempSamp-R1 outperforms GRPO-based baselines, establishing new state-of-the-art performance on benchmark datasets.
  arXiv  Detail & Related papers  (2025-09-22T17:30:15Z)
• ProfilingAgent: Profiling-Guided Agentic Reasoning for Adaptive Model Optimization [7.64805011214817]
  Profiling tools expose per-layer latency, memory, and compute cost, yet are rarely integrated into automated pipelines.<n>We propose ProfilingAgent, a profiling-guided, agentic approach that uses large language models (LLMs) to automate compression via structured pruning and post-training dynamic quantization.
  arXiv  Detail & Related papers  (2025-09-06T04:02:04Z)
• Low-rank Momentum Factorization for Memory Efficient Training [13.464518325870444]
  Momentum Factorized (MoFaSGD) maintains a dynamically updated low-rank SVD representation of the first-order momentum.<n>We demonstrate MoFaSGD's effectiveness on large language model benchmarks, achieving a competitive trade-off between memory reduction (e.g. LoRA) and performance.
  arXiv  Detail & Related papers  (2025-07-10T18:04:52Z)
• Deep Reinforcement Learning-Based DRAM Equalizer Parameter Optimization Using Latent Representations [4.189643331553922]
  This paper introduces a data-driven framework employing learned latent signal representations for efficient signal integrity evaluation.<n>Applying to industry-standard Dynamic Random Access Memory waveforms, the method achieved significant eye-opening window area improvements.
  arXiv  Detail & Related papers  (2025-07-03T06:53:51Z)
• EoRA: Fine-tuning-free Compensation for Compressed LLM with Eigenspace Low-Rank Approximation [84.70637613266835]
  EoRA is a fine-tuning-free method that augments compressed Large Language Models with low-rank matrices.<n>EoRA consistently outperforms prior training-free low rank methods in recovering the accuracy of compressed LLMs.
  arXiv  Detail & Related papers  (2024-10-28T17:59:03Z)
• HiRE: High Recall Approximate Top-$k$ Estimation for Efficient LLM Inference [68.59839755875252]
  HiRE comprises of two novel components: (i) a compression scheme to cheaply predict top-$k$ rows/columns with high recall, followed by full computation restricted to the predicted subset, and (ii) DA-TOP-$k$: an efficient multi-device approximate top-$k$ operator. We demonstrate that on a one billion parameter model, HiRE applied to both the softmax as well as feedforward layers, achieves almost matching pretraining and downstream accuracy, and speeds up inference latency by $1.47times$ on a single TPUv5e device.
  arXiv  Detail & Related papers  (2024-02-14T18:04:36Z)
• Bridging Models to Defend: A Population-Based Strategy for Robust Adversarial Defense [70.39517230717126]
  Adrial robustness is a critical measure of a neural network's ability to withstand adversarial attacks at inference time.<n>We propose a novel Robust Mode Connectivity (RMC)-oriented adversarial defense framework.<n>We show that our methods significantly improve robustness against $ell_infty$, $ell$, and hybrid attacks.
  arXiv  Detail & Related papers  (2023-03-17T19:49:10Z)

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.