arXiv AI
Jul 24
GRADRAG: Cross-Component Prompt Adaptation for Coordinated Multi-Agent RAG
arXiv:2607. 21324v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) systems increasingly employ multiple LLM agents.
A corrective agentic hybrid RAG and an operations-grounded evaluation for a scientific facility
arXiv:2607. 24663v1 Announce Type: cross Abstract: Scientific user facilities accumulate decades of operational knowledge that no single search index covers: electronic logbooks, technical documents, internal wikis, operations chat messages, maintenance records, and live control-system data.
Related stories
arXiv AI
Sep 3
Hybrid Retrieval-Augmented Generation with Knowledge Graph Expansion, RRF Fusion, and Per-Chunk Grounded Evaluation for Enterprise Document Search
Hybrid Retrieval-Augmented Generation with Knowledge Graph Expansion, RRF Fusion, and Per-Chunk Grounded Evaluation for Enterprise Document Search describes DocuSearch, an offline multi‑agent system designed for telecom network operations. The system combines semantic vector search, BM25 full‑text search, and knowledge‑graph neighbor expansion, merges the results via Reciprocal Rank Fusion, and reranks with a cross‑encoder before pruning with Maximal Marginal Relevance. A per‑chunk evaluation loop ensures only grounded answers are returned, achieving Precision@10 of 0.69, Recall@10 of 0.79, and an 89.6% grounding rate—improvements of 15, 16, and 18.4 percentage points over a dense‑only baseline.
arXiv AI
Jun 10
Agentic Hybrid RAG for Evidence-Grounded Muon Collider Analysis
arXiv:2606. 10381v1 Announce Type: cross Abstract: Muon collider research spans accelerator physics, detector instrumentation, and high-energy phenomenology, with relevant evidence scattered across a rapidly expanding and heterogeneous body of scientific literature.
arXiv AI
Jun 30
ARMOR: Adaptive Retriever Optimization for Low-Resource Telecom Question Answering
arXiv:2606. 29706v1 Announce Type: cross Abstract: Telecom question answering (QA) is a challenging setting for retrieval-augmented generation (RAG): evidence is fragmented across standards, papers, encyclopedic resources, and web documents, and answers often hinge on technical tables, equations, and specialized protocol language.
arXiv Computation and Language
Sep 7
BIT.UA at BioASQ 14B: Modular Retrieval with pg_textsearch and Qdrant, and Agent-Based Answer Generation
The BIT.UA team from the University of Aveiro participated in the 14th BioASQ Task B challenge, presenting a refactored modular pipeline for biomedical question answering. They replaced the PyTerrier PISA index with PostgreSQL-based pg_textsearch for BM25 retrieval and adopted Qdrant for dense embedding indexing, while also exploring HyDE-based query expansion and a Context-1 retrieval strategy. For answer generation, they introduced an LLM-as-a-judge framework and an agent quorum mechanism that allows multiple agents with diverse prompts to debate and converge on a consensus answer, achieving competitive MAP ranks of 5 in Phase A batches.
arXiv AI
Jul 24
AISE-Bench: A Full-Cycle Curated Benchmark for Information Seeking on Academic Knowledge Graphs
arXiv:2607. 20498v1 Announce Type: new Abstract: Large language models (LLMs) augmented with tools are emerging as autonomous agents capable of using Web engine, APIs, and code to solve complex, long-horizon tasks.
Hugging Face Trending Papers
Jul 23
GRADRAG: Cross-Component Prompt Adaptation for Coordinated Multi-Agent RAG
Retrieval-Augmented Generation (RAG) systems increasingly employ multiple LLM agents. Yet, most prior work optimizes components in isolation rather than coordinating improvements across the pipeline.
arXiv AI
Jul 29
Multimodal Hybrid Retrieval-Augmented Generation for Scientific Document Understanding using Open-Source SLMs
arXiv:2607. 24799v1 Announce Type: cross Abstract: Large Language Models tend to hallucinate when answering domain-specific ques tions from scientific documents without prior fine-tuning.
arXiv Computation and Language
Aug 25
Industrial-Instruction: An End-to-End Framework for Building Instruction-Tuning and Benchmark Datasets from Industrial Technical Reports
arXiv:2608.22817v1 Announce Type: new Abstract: Industrial technical reports contain high-value knowledge for maintenance, troubleshooting, and product engineering, but their heterogeneous structure...
arXiv Computation and Language
Aug 27
Corpus2Skill: Distilling Enterprise Knowledge into Navigable Agent Skills for QA and RAG
Corpus2Skill is a retrieval architecture that transforms an enterprise knowledge base into a hierarchical skill directory, enabling an LLM agent to navigate from high-level summaries to specific documents and backtrack when necessary. On an enterprise customer‑support benchmark, it outperforms single‑shot dense, hybrid, hierarchical‑retrieval, and agentic RAG baselines in answer quality and grounding, with a moderate cost tradeoff. An eleven‑dataset study shows that corpus navigation excels on single‑domain corpora with a recoverable topical taxonomy but is less effective on open‑domain factoid pools or homogeneous‑tabular corpora, providing a design guideline for knowledge‑grounded systems.
arXiv AI
3d ago
Re-ranking and Late Interaction Drive Retrieval Quality: A Controlled Comparison of RAG Strategies for Scientific Question Answering
The paper presents a controlled comparison of six retrieval-augmented generation (RAG) strategies for scientific question answering on a large arXiv corpus. All pipelines use the same LLM generator and evaluation protocol, differing only in retrieval design—ranging from classic dense retrieval to late‑interaction methods like ColBERTv2. The authors also release a synthetic question dataset and code to enable reproducible, large‑scale evaluation of RAG trade‑offs.
Hugging Face Trending Papers
Sep 8
Q2D-Web: A Large-Scale Benchmark for Retrieval in Agentic RAG Systems
Q2D-Web is a new large‑scale benchmark for agentic Retrieval‑Augmented Generation (RAG) systems, featuring a 190 million‑document web corpus and 70 k machine‑reformulated search queries in ten languages. It supplies three sets of relevance judgments—agent citations, production rankings, and a combined set enriched with LLM‑based labels—to evaluate first‑stage retrievers. Experiments on 13 retrievers show consistent ranking across judgment sets but significant variation across domains, languages, and query types, and demonstrate that a carefully sampled sub‑corpus can approximate full‑corpus evaluation with minimal loss in Recall@1000.