arXiv AI September 3, 2026 By Przemys{\l}aw Stok{\l}osa, Janusz A. Starzyk, Pawe{\l} Raif

SSAKG 2.0: An Open-Source Package for Structural Associative Sequence Memory and Context-Based Retrieval

SSAKG 2.0 is an open‑source Python package that builds and operates Structural Sequential Associative Knowledge Graphs, representing objects as graph vertices and sequences as ordered structural patterns. The new version introduces memory‑efficient algorithms that use individual bits of computer memory to accelerate graph connection searches, with performance‑critical operations coded in C and exposed via a Python interface. Experiments on random numerical sequences, NLTK sentences, and mRNA data show the package can store and reconstruct sequences from partial, unordered contexts, and allow evaluation of graph density, sequence length, and memory size effects on retrieval performance.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv AI

Jun 2

MemGraphRAG: Memory-based Multi-Agent System for Graph Retrieval-Augmented Generation

arXiv:2606. 00610v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) has become an essential method for mitigating hallucinations in Large Language Models (LLMs) by leveraging external knowledge.

By Chuanjie Wu, Zhishang Xiang, Yunbo Tang, Zerui Chen, Qinggang Zhang, Jinsong Su

llms rag agents benchmarks safety

arXiv Machine Learning

Sep 11

Enabling Knowledge Graph Understanding at Scale with the EXplore Your Graphs ENgine (EXYGEN)

The paper introduces EXYGEN, a framework that enables conversational access to large knowledge graphs by combining VoID descriptions, ShEx schemas, retrieved triples, and example question‑query pairs in a retrieval‑augmented generation pipeline. On the SciQA benchmark, this approach achieves an exact‑match score of 0.419 without fine‑tuning any large language model, and shows that larger general‑purpose LLMs can outperform smaller code‑specialized ones when provided sufficient context. To scale metadata generation for very large KGs, the authors propose a predicate‑coverage‑aware parallel graph sampling strategy that preserves structural diversity, reduces runtime by over 80× on OpenCitations Meta and GESIS, and is the only tractable method for obtaining complete metadata on ORKG.

By Harshdeep Singh, Yurui Zhu, Giovanni Colavizza, Matteo Romanello

llms rag fine-tuning benchmarks

arXiv AI

Jul 21

GRIP: In-Parameter Graph Reasoning through Fine-Tuning Large Language Models

arXiv:2511. 07457v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) have demonstrated remarkable capabilities in modeling sequential textual data and generalizing across diverse tasks.

By Jiarui Feng, Donghong Cai, Yixin Chen, Muhan Zhang

llms fine-tuning safety

arXiv AI

Jun 30

Query-Aware Spreading Activation for Multi-Hop Retrieval over Knowledge Graphs

arXiv:2606. 30133v1 Announce Type: cross Abstract: Retrieval-augmented generation built on knowledge graphs (Graph RAG) outperforms flat passage retrieval on multi-hop question answering by leveraging graph structure.

By Illia Makarov, Mykola Glybovets

rag diffusion nlp benchmarks

arXiv AI

Aug 12

GraFine: Retrieval-Time Refinement for Efficient Graph RAG over Corpus Graphs

arXiv:2601. 18579v2 Announce Type: replace-cross Abstract: Graph RAG on corpus graphs enhances retrieval by leveraging intermediate node content as contextual clues to uncover unretrieved oracle nodes.

By Seonho An, Chaejeong Hyun, Min-Soo Kim

rag efficiency

arXiv AI

Jun 15

Knowledge Graph Enhanced Memory-Augmented Retrieval for Long Context Modeling

arXiv:2606. 14047v1 Announce Type: cross Abstract: Long-context language modeling requires not only extending context windows but maintaining coherent understanding of entity states and relationships across thousands of tokens -- a challenge that semantic similarity alone cannot address.

By Ghadir Alselwi, Basem Suleiman, Hao Xue, Shoaib Jameel, Hakim Hacid, Flora D. Salim, Imran Razzak

llms rag

One email a morning, machine-written

Related stories

MemGraphRAG: Memory-based Multi-Agent System for Graph Retrieval-Augmented Generation

Enabling Knowledge Graph Understanding at Scale with the EXplore Your Graphs ENgine (EXYGEN)

GRIP: In-Parameter Graph Reasoning through Fine-Tuning Large Language Models

Query-Aware Spreading Activation for Multi-Hop Retrieval over Knowledge Graphs

GraFine: Retrieval-Time Refinement for Efficient Graph RAG over Corpus Graphs

Knowledge Graph Enhanced Memory-Augmented Retrieval for Long Context Modeling