HyphaeDB introduces an agent-native memory system using HNSW topology for gossip-based knowledge propagation, enabling emergent behaviors in multi-agent AI.
Mixed citations
Title resolution pending
Mixed citation behavior. Most common role is background (40%).
25
Pith papers citing it
1,622
external citations · external index
Background
40% of classified citations
citation-role summary
background 2
method 2
baseline 1
citation-polarity summary
representative citing papers
Introduces P-CHR AUC and CRR metrics to demonstrate that semantic caching model selection is limited by calibration quality rather than ranking performance.
DINOSAUR augments ANN indices with sampled embeddings to marginalize uncertainty, recovering standard retrieval at zero uncertainty while expanding coverage for uncertain items.
SkillDAG builds a self-evolving typed skill graph that LLM agents query and update at inference time, raising success on ALFWorld and SkillsBench by 12.8 and 8.6 points over graph baselines.
GRAB-ANNS is a new GPU graph index that achieves up to 240x higher hybrid search throughput via bucket layouts and hybrid intra/inter-bucket edges.
Multiprobe grid ANN maintains roughly constant d-scaling on GloVe while graph/tree/partitioning methods degrade, with near-linear N scaling and lower indexing cost.
Introduces LakeQA, a new expert-annotated benchmark for search-centric multi-hop QA over a million-scale heterogeneous data lake, showing low performance (18.37% exact match) on frontier LLMs like GPT-5.2.
HKVM-RAG uses key-value-separated hypergraphs to organize LLM evidence tuples into answer-path hyperedges, yielding F1 gains over KG-PPR on two multi-hop QA benchmarks and further gains when combined with dense retrievers.
PipeANN-Filter improves filtered vector search latency and throughput on SSD by exploring a superset of valid vectors identified via probabilistic filters and verifying attributes only after selecting top-k candidates.
SPARK improves LLM-based test code fault localization by retrieving similar past faults and selectively annotating suspicious lines in new failing tests.
PPRoute achieves plaintext-level LLM routing quality with MPC-based privacy and a 20x speedup over naive encrypted implementations via MPC-friendly encoders, multi-step training, and O(1) communication Top-k search.
Injecting a few vectors near the embedding-space centroid can make them appear in top-k results for up to 94.4% of queries via centrality-driven hubness.
ConStruM improves LLM-based schema matching by using a context tree and global similarity hypergraph to assemble query-specific evidence packs from available schema metadata.
HyEm maps radius-controlled hyperbolic ontology embeddings to Euclidean space for ANN indexing and applies query-adaptive hyperbolic reranking to improve hierarchy-aware retrieval while preserving most Euclidean performance on flat queries.
An in-vehicle digital twin framework using temporal convolutional networks and hierarchical navigable small world algorithms detects Sybil attacks with 0.984 accuracy and reduces near-collision metrics by 72-88% on real-world field data.
HRNN combines a navigation graph, ranked KNN graph, and reverse-neighbor lists with proxy-based candidate generation and materialized kNN-radii to achieve up to 10x higher throughput for approximate RkNN on datasets up to 10M vectors.
Co-design of 14.5x compacted index, asynchronous scheduler, and multiplication-free kernel for PIM-based graph ANNS delivers up to 20x CPU and 17.1x GPU throughput on billion-scale benchmarks.
CHRONOS is a three-layer system for evolving data marketplaces that applies neural-ODE temporal decay, changepoint-aware Shapley valuation, and EXP3-IX private coordination to achieve 0.937 recall, 2.74 qps, 161 ms latency, and epsilon 4.25 at delta 10^-6.
DIVE combines a self-limiting hinge triplet loss on one head with a head-wise NT-Xent loss on multiple heads, and reports large retrieval gains over prior embedding-compression adapters on six BEIR datasets.
Relational engines achieve faster SQL+vector-search queries on GPU than CPU when using compact vector indexes and fast interconnects, reversing the CPU-only design in current systems.
A human-in-control LLM architecture translates natural language to OpenSearch DSL queries using hybrid lexical and semantic search in a secure private-cloud setup, shown via prototype on the Enron dataset.
A graph autoencoder model using foundation model features achieves high retrieval accuracy (mAP 96.7-97.6%, mMV 91.5-94.2%) on BreakHis and BACH breast cancer histopathology datasets.
Introduces a cross-paradigm database selection framework based on nine dimensions, analyzes thirteen paradigms to identify three evolution patterns, and demonstrates hybrid architectures via a financial fraud detection case study.
This survey discusses key components and challenges for Personal LLM Agents and reviews solutions for their capability, efficiency, and security.
citing papers explorer
-
HyphaeDB: A Living Knowledge Topology for Agent-First Memory
HyphaeDB introduces an agent-native memory system using HNSW topology for gossip-based knowledge propagation, enabling emergent behaviors in multi-agent AI.
-
Closing the Calibration Gap in Semantic Caching
Introduces P-CHR AUC and CRR metrics to demonstrate that semantic caching model selection is limited by calibration quality rather than ranking performance.
-
Distributional Approximate Nearest Neighbour Search for Uncertainty-Aware Retrieval
DINOSAUR augments ANN indices with sampled embeddings to marginalize uncertainty, recovering standard retrieval at zero uncertainty while expanding coverage for uncertain items.
-
SkillDAG: Self-Evolving Typed Skill Graphs for LLM Skill Selection at Scale
SkillDAG builds a self-evolving typed skill graph that LLM agents query and update at inference time, raising success on ALFWorld and SkillsBench by 12.8 and 8.6 points over graph baselines.
-
GRAB-ANNS: High-Throughput Indexing and Hybrid Search via GPU-Native Bucketing
GRAB-ANNS is a new GPU graph index that achieves up to 240x higher hybrid search throughput via bucket layouts and hybrid intra/inter-bucket edges.
-
Scaling Laws for Grid-Based Approximate Nearest Neighbor Search in High Dimensions
Multiprobe grid ANN maintains roughly constant d-scaling on GloVe while graph/tree/partitioning methods degrade, with near-linear N scaling and lower indexing cost.
-
LakeQA: An Exploratory QA Benchmark over a Million-Scale Data Lake
Introduces LakeQA, a new expert-annotated benchmark for search-centric multi-hop QA over a million-scale heterogeneous data lake, showing low performance (18.37% exact match) on frontier LLMs like GPT-5.2.
-
HKVM-RAG: Key-Value-Separated Hypergraph Evidence Organization for Multi-Hop RAG
HKVM-RAG uses key-value-separated hypergraphs to organize LLM evidence tuples into answer-path hyperedges, yielding F1 gains over KG-PPR on two multi-hop QA benchmarks and further gains when combined with dense retrievers.
-
PipeANN-Filter: An Efficient Filtered Vector Search System on SSD
PipeANN-Filter improves filtered vector search latency and throughput on SSD by exploring a superset of valid vectors identified via probabilistic filters and verifying attributes only after selecting top-k candidates.
-
Similar Pattern Annotation via Retrieval Knowledge for LLM-Based Test Code Fault Localization
SPARK improves LLM-based test code fault localization by retrieving similar past faults and selectively annotating suspicious lines in new failing tests.
-
Privacy-Preserving LLMs Routing
PPRoute achieves plaintext-level LLM routing quality with MPC-based privacy and a 20x speedup over naive encrypted implementations via MPC-friendly encoders, multi-step training, and O(1) communication Top-k search.
-
Can You Trust the Vectors in Your Vector Database? Black-Hole Attack from Embedding Space Defects
Injecting a few vectors near the embedding-space centroid can make them appear in top-k results for up to 94.4% of queries via centrality-driven hubness.
-
ConStruM: A Structure-Guided LLM Framework for Context-Aware Schema Matching
ConStruM improves LLM-based schema matching by using a context tree and global similarity hypergraph to assemble query-specific evidence packs from available schema metadata.
-
HyEm: Query-Adaptive Hyperbolic Retrieval for Biomedical Ontologies via Euclidean Vector Indexing
HyEm maps radius-controlled hyperbolic ontology embeddings to Euclidean space for ANN indexing and applies query-adaptive hyperbolic reranking to improve hierarchy-aware retrieval while preserving most Euclidean performance on flat queries.
-
In-Vehicle Digital Twin-Based Collision Warning Framework with Sybil Attack Detection
An in-vehicle digital twin framework using temporal convolutional networks and hierarchical navigable small world algorithms detects Sybil attacks with 0.984 accuracy and reduces near-collision metrics by 72-88% on real-world field data.
-
HRNN: A Hybrid Graph Index for Approximate Reverse k-Nearest Neighbor Search on High-Dimensional Vectors
HRNN combines a navigation graph, ranked KNN graph, and reverse-neighbor lists with proxy-based candidate generation and materialized kNN-radii to achieve up to 10x higher throughput for approximate RkNN on datasets up to 10M vectors.
-
Co-Designing Graph-based Approximate Nearest Neighbor Search at Billion Scale for Processing-in-Memory
Co-design of 14.5x compacted index, asynchronous scheduler, and multiplication-free kernel for PIM-based graph ANNS delivers up to 20x CPU and 17.1x GPU throughput on billion-scale benchmarks.
-
CHRONOS: Temporally-Aware Multi-Agent Coordination for Evolving Data Marketplaces
CHRONOS is a three-layer system for evolving data marketplaces that applies neural-ODE temporal decay, changepoint-aware Shapley valuation, and EXP3-IX private coordination to achieve 0.937 recall, 2.74 qps, 161 ms latency, and epsilon 4.25 at delta 10^-6.
-
DIVE: Embedding Compression via Self-Limiting Gradient Updates
DIVE combines a self-limiting hinge triplet loss on one head with a head-wise NT-Xent loss on multiple heads, and reports large retrieval gains over prior embedding-compression adapters on six BEIR datasets.
-
To GPU or Not to GPU: Vector Search in Relational Engines
Relational engines achieve faster SQL+vector-search queries on GPU than CPU when using compact vector indexes and fast interconnects, reversing the CPU-only design in current systems.
-
A Cloud-Native Architecture for Human-in-Control LLM-Assisted OpenSearch in Investigative Settings
A human-in-control LLM architecture translates natural language to OpenSearch DSL queries using hybrid lexical and semantic search in a secure private-cloud setup, shown via prototype on the Enron dataset.
-
Leveraging Medical Foundation Model Features in Graph Neural Network-Based Retrieval of Breast Histopathology Images
A graph autoencoder model using foundation model features achieves high retrieval accuracy (mAP 96.7-97.6%, mMV 91.5-94.2%) on BreakHis and BACH breast cancer histopathology datasets.
-
Architectural Evolution and Selection Framework for Database Systems in AI-Ready Data Platforms
Introduces a cross-paradigm database selection framework based on nine dimensions, analyzes thirteen paradigms to identify three evolution patterns, and demonstrates hybrid architectures via a financial fraud detection case study.
-
Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Security
This survey discusses key components and challenges for Personal LLM Agents and reviews solutions for their capability, efficiency, and security.
-
A Survey on Retrieval-Augmented Text Generation for Large Language Models
A survey that categorizes RAG methods for LLMs into four retrieval-centric stages, reviews their evolution and evaluation, and outlines challenges and future directions.