vstash: Local-First Hybrid Retrieval with Adaptive Fusion for LLM Agents

• URL: http://arxiv.org/abs/2604.15484v1
• Date: Thu, 16 Apr 2026 19:22:58 GMT
• Title: vstash: Local-First Hybrid Retrieval with Adaptive Fusion for LLM Agents
• Abstract summary: We present **vstash**, a local-first document memory system that combines vector similarity search with fulltext keyword matching.<n>All data resides in a single file using sqlite-vec for approximate nearest neighbor search and FTS5 for keyword matching.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We present **vstash**, a local-first document memory system that combines vector similarity search with full-text keyword matching via Reciprocal Rank Fusion (RRF) and adaptive per-query IDF weighting. All data resides in a single SQLite file using sqlite-vec for approximate nearest neighbor search and FTS5 for keyword matching. We make four primary contributions. **(1)** Self-supervised embedding refinement via hybrid retrieval disagreement: across 753 BEIR queries on SciFact, NFCorpus, and FiQA, 74.5% produce top-10 disagreement between vector-heavy (vec=0.95, fts=0.05) and FTS-heavy (vec=0.05, fts=0.95) search (per-dataset rates 63.4% / 73.4% / 86.7%, Section 5.2), providing a free training signal without human labels. Fine-tuning BGE-small (33M params) with MultipleNegativesRankingLoss on 76K disagreement triples improves NDCG@10 on all 5 BEIR datasets (up to +19.5% on NFCorpus vs. BGE-small base RRF, Table 6). On 3 of 5 datasets, under different preprocessing, the tuned 33M-parameter pipeline matches or exceeds published ColBERTv2 results (110M params) and an untrained BGE-base (110M); on FiQA and ArguAna it underperforms ColBERTv2 (Section 5.5). **(2)** Adaptive RRF with per-query IDF weighting improves NDCG@10 on all 5 BEIR datasets versus fixed weights (up to +21.4% on ArguAna), achieving 0.7263 on SciFact with BGE-small. **(3)** A negative result on post-RRF scoring: frequency+decay, history-augmented recall, and cross-encoder reranking all failed to improve NDCG. **(4)** A production-grade substrate with integrity checking, schema versioning, ranking diagnostics, and a distance-based relevance signal validated on 50,425 relevance-judged queries across the 5 BEIR datasets. Search latency remains 20.9 ms median at 50K chunks with stable NDCG. The fine-tuned model is published as `Stffens/bge-small-rrf-v2` on HuggingFace. All code, data, and experiments are open-source.

Related papers

• Your Retriever Already Knows: Distribution-Shape QPP for RAG Retrieval Sufficiency [0.0]
  Motivated by a Czech nuclear-regulator deployment, we compare three Query Performance Prediction (QPP) paradigms for retrieval sufficiency in RAG.<n>Our 24 non-lexical features reach a weighted-average AUROC of 0.856 at 2 ms per query, ahead of a classic-QPP literature pool.<n>Adding the LLM judgment as one feature (hybrid) matches S1 on ViDoRe (0.863) but gains a statistically significant edge on SJB.
  arXiv  Detail & Related papers  (2026-09-10T14:52:16Z)
• On the Design of Qwen3.8-Next Architecture: Evaluation, Efficiency, and Training Stability [57.03393882933515]
  We describe the architecture and ablations of Qwen3.8-Flash-Next, a sparse mixture-of-experts model with 125B parameters, 6B activated per token, and 51B parameters of n-gram embedding tables held off the accelerator.<n>On fourteen pre-training benchmarks the model leads the 397B-A17B predecessor on eight and trails it on the rest by at most 2.6 points, at 1/3 the activated parameters, 1/3 the training tokens, and roughly 1/9 the training FLOPs.
  arXiv  Detail & Related papers  (2026-08-31T06:35:07Z)
• Sparse Mutual Information Graph Averaging for Improving Random Indexing Embeddings [0.0]
  Sparse word embedding pipelines can avoid dense co-occurrence matrix materialization, dense factorization, and gradient training while still relying on sparse global corpus statistics.<n>This paper studies Random Indexing (RI) vectors refined by weighted averaging on a sparse Positive Pointwise Mutual Information (PPMI) graph.
  arXiv  Detail & Related papers  (2026-08-06T08:07:18Z)
• Trust Before Fusion: QIMG-7 and Source-Aware Resolution for Polluted Multimodal RAG [45.88028371034407]
  Multimodal retrieval-augmented generation (RAG) is often evaluated with clean evidence, yet real retrieval can return topically relevant but unreliable content.<n>We introduce QIMG-7, a benchmark for multimodal retrieval pollution in multi-sentence factual QA.<n>We propose source-aware trust resolution (SATR), a training-free approach that compares Parametric, Text-only, and Full-MM candidate answers.
  arXiv  Detail & Related papers  (2026-07-12T15:13:09Z)
• How Far Do On-Prem Open LLMs Get on Text-to-SQL? A Cross-Family Size x Technique Frontier on BIRD [0.0]
  We evaluate three open model families across two generations -- Qwen2.5-Coder (7B/14B/32B), CodeLlama-Instruct (7B/13B/34B), and Llama-3.x (8B, 70B)<n>We find that Qwen2.5-Coder dominates the older CodeLlama at matched size (39.1 vs 20.9 at 7B), but a modern non-Qwen model (Llama-3.3-70B, 49.2 on a matched serving) is competitive, so CodeLlama's weakness reflects its 2023 generation, not "non-Qwen = weak"
  arXiv  Detail & Related papers  (2026-06-29T03:15:38Z)
• Querit-Reranker: Training Compact Multilingual Rerankers via Efficient Label-Free Distribution Adaptation [43.66118282567413]
  We present Querit-Reranker, a family of multilingual cross-encoder rerankers trained with a data-centric pipeline.<n>Our pipeline first learns general relevance modeling from large-scale ranking-oriented data, then adapts to target distributions.<n>Querit-Reranker-A0.4B improves average nDCG@10 from 54.11 to 59.28 on BEIR and from 59.87 to 67.70 on MIRACL.
  arXiv  Detail & Related papers  (2026-06-17T13:06:47Z)
• Transfer Learning for FHIR Questionnaire Terminology Binding [0.0]
  Given a Questionnaire item's text, find the correct LOINC code in a pool of 97,314 active codes.<n>We compare six methods (TF-IDF, frozen MiniLM, BioBERT, BioLORD, contrastively fine-tuned MiniLM, and a TF-IDF+GPT reranker) on a 54-item evaluation set spanning three query styles.
  arXiv  Detail & Related papers  (2026-06-13T19:46:44Z)
• More Is Not Always Better: Cross-Component Interference in LLM Agent Scaffolding [4.738949927143789]
  LLM agent systems are built by stacking components (planning, tools, memory, self-reflection, retrieval)<n>We run a full factorial experiment over all 25=32 subsets of five components on HotpotQA and GSM8K with Llama-3.1-8B/70B conditions.<n>The All-In system is consistently suboptimal: on HotpotQA, a single-tool agent surpasses All-In by 32% (F1 0.233 vs 0.177, p23)<n>Our findings suggest maximally-equipped agent should be replaced by subset selection via interaction-aware analysis.
  arXiv  Detail & Related papers  (2026-05-07T06:01:43Z)
• Delta-Based Neural Architecture Search: LLM Fine-Tuning via Code Diffs [48.83701310501069]
  Large language models (LLMs) show strong potential for neural architecture generation.<n>Existing approaches produce complete model implementations from scratch.<n>We propose Delta-Code Generation, where fine-tuned LLMs generate compact unified diffs.
  arXiv  Detail & Related papers  (2026-05-06T13:32:05Z)
• Hybrid Retrieval for COVID-19 Literature: Comparing Rank Fusion and Projection Fusion with Diversity Reranking [0.0]
  We present a hybrid retrieval system for COVID-19 scientific literature, evaluated on the TREC-COVID benchmark.<n>The system implements six retrieval configurations spanning sparse (SPLADE), dense (BGE), rank-level fusion (RRF) and a projection-based vector fusion (B5) approach.<n>RRF fusion achieves the best relevance (nDCG@10 = 0.828), outperforming dense-only by 6.1% and sparse-only by 14.9%.
  arXiv  Detail & Related papers  (2026-04-15T11:05:46Z)
• BRIDGE and TCH-Net: Heterogeneous Benchmark and Multi-Branch Baseline for Cross-Domain IoT Botnet Detection [1.2019888796331233]
  IoT botnet detection has advanced, yet most published systems are validated on a single dataset and rarely generalise across environments.<n>We introduce BRIDGE, the first formally specified heterogeneous multi-dataset benchmark for IoT intrusion detection.<n>We establish the first community generalisation baseline at mean LODO F1 = 0.5577, a result that shifts the agenda from single-benchmark optimisation to cross-environment generalisation.
  arXiv  Detail & Related papers  (2026-04-13T11:25:39Z)
• Reproduction Beyond Benchmarks: ConstBERT and ColBERT-v2 Across Backends and Query Distributions [3.976291254896486]
  We evaluate ColBERT-v2 and ConstBERT across five dimensions.<n>While ConstBERT reproduces within 0.05% MRR@10 on MS-MARCO, both models show a drop of 86-97% on long, narrative queries.
  arXiv  Detail & Related papers  (2026-04-11T01:36:33Z)
• Resource-Efficient Iterative LLM-Based NAS with Feedback Memory [49.44875022114861]
  Neural Architecture Search (NAS) automates network design, but conventional methods demand substantial computational resources.<n>We propose a closed-loop pipeline leveraging large language models (LLMs) to iteratively generate, evaluate, and refine convolutional neural network architectures.
  arXiv  Detail & Related papers  (2026-03-12T16:00:22Z)
• Diffusion Language Models are Super Data Learners [61.721441061210896]
  When unique data is limited, diffusion language models (DLMs) consistently surpass autoregressive (AR) models by training for more epochs.<n>We attribute the gains to three compounding factors: (1) any-order modeling, (2) super-dense compute from iterative bidirectional denoising, and (3) built-in Monte Carlo augmentation.
  arXiv  Detail & Related papers  (2025-11-05T08:17:42Z)
• Adaptive Split-MMD Training for Small-Sample Cross-Dataset P300 EEG Classification [12.103074826558531]
  Cross-dataset shift occurs when trying to boost a small target set with a large source dataset.<n>We introduce Adaptive Split Maximum Mean Discrepancy Training (AS-MMD)<n>AS-MMD combines a target-weighted loss with warm-up tied to the square root of the source/target size ratio.<n>It outperforms target-only and pooled training.
  arXiv  Detail & Related papers  (2025-10-24T18:48:21Z)
• LLM Robustness Against Misinformation in Biomedical Question Answering [50.98256373698759]
  The retrieval-augmented generation (RAG) approach is used to reduce the confabulation of large language models (LLMs) for question answering. We evaluate the effectiveness and robustness of four LLMs against misinformation in answering biomedical questions.
  arXiv  Detail & Related papers  (2024-10-27T16:23:26Z)
• Detection Transformer with Stable Matching [48.963171068785435]
  We show that the most important design is to use and only use positional metrics to supervise classification scores of positive examples. Under the principle, we propose two simple yet effective modifications by integrating positional metrics to DETR's classification loss and matching cost. We achieve 50.4 and 51.5 AP on the COCO detection benchmark using ResNet-50 backbones under 12 epochs and 24 epochs training settings.
  arXiv  Detail & Related papers  (2023-04-10T17:55:37Z)
• IRLI: Iterative Re-partitioning for Learning to Index [104.72641345738425]
  Methods have to trade between obtaining high accuracy while maintaining load balance and scalability in distributed settings. We propose a novel approach called IRLI, which iteratively partitions the items by learning the relevant buckets directly from the query-item relevance data. We mathematically show that IRLI retrieves the correct item with high probability under very natural assumptions and provides superior load balancing.
  arXiv  Detail & Related papers  (2021-03-17T23:13:25Z)
• TACRED Revisited: A Thorough Evaluation of the TACRED Relation Extraction Task [80.38130122127882]
  TACRED is one of the largest, most widely used crowdsourced datasets in Relation Extraction (RE) In this paper, we investigate the questions: Have we reached a performance ceiling or is there still room for improvement? We find that label errors account for 8% absolute F1 test error, and that more than 50% of the examples need to be relabeled.
  arXiv  Detail & Related papers  (2020-04-30T15:07:37Z)

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.