AI and infrastructure news

Paper29

RAG and retrieval

RAG and retrieval Paper
10/08/2618 days ago arxiv.org
LightRetriever cuts the cost of LLM-based retrieval
A post published on March 5, 2026 reports query encoding 1,000× faster and 10× higher throughput with LightRetriever, while retaining 95% of benchmark performance.
RAG and retrieval Paper
10/08/2618 days ago github.com
Geometric limits on compression in RAG
A NeurIPS 2026 paper studies compression in RAG through embedding geometry and says a spectral quantity defines a minimum limit for compression.
RAG and retrieval Paper
10/08/2618 days ago arxiv.org
MegaRAG proposes multimodal graphs for RAG
Published on December 25, 2025, the paper describes a method that automatically builds knowledge graphs from visual documents to support retrieval and cross-modal reasoning.
RAG and retrieval Paper
10/08/2618 days ago arxiv.org
RAG: More documents may reduce reliance on larger LLMs
A CMU researchers’ paper, dated January 14, 2026, evaluates expanding the retrieval corpus as an alternative to scaling up the model. According to the post, a medium-sized model with more documents may match a larger model with a smaller corpus.
RAG and retrieval Paper
10/08/2618 days ago arxiv.org
RouteRAG adapts text and graph searches during reasoning
Published on December 15, 2025, the material describes a RAG framework using reinforcement learning to choose searches and penalize unnecessary retrieval.
RAG and retrieval Paper
10/08/2618 days ago arxiv.org
Skill-RAG adapts retrieval to detected knowledge gaps
Published on April 20, 2026, the paper presents a method that detects potential knowledge gaps and routes queries to specialized retrieval strategies. It evaluates the approach on HotpotQA, Natural Questions, and TriviaQA.
RAG and retrieval Paper
10/08/2618 days ago arxiv.org
UniversalRAG routes queries for multimodal retrieval
Published on January 14, 2026, the text describes a framework that routes queries to modality-specific corpora and retrieves knowledge across modalities and levels of granularity.
RAG and retrieval Paper
10/08/2618 days ago arxiv.org
EfficientRAG reduces LLM calls for multi-hop questions
An article published on August 17, 2024 presents a retrieval method that generates queries iteratively without calling an LLM at every step.
RAG and retrieval Paper
10/08/2618 days ago arxiv.org
FACT proposes iterative rewriting to retrieve multiple facts
Published on October 30, 2024, the paper presents a context-rewriting approach for retrieving multiple facts and examines incomplete answers from lengthy contexts.
RAG and retrieval Paper
10/08/2618 days ago arxiv.org
LightRAG combines graphs with two-level retrieval
A description published on October 13, 2024 presents a RAG framework combining graph-based text indexing with low- and high-level retrieval for entity-specific and conceptual information.
RAG and retrieval Paper
10/08/2618 days ago arxiv.org
VideoRAG expands information retrieval to video
On January 14, 2025, KAIST research presented a framework that retrieves videos relevant to queries and combines visual and textual information in multimodal RAG responses.
RAG and retrieval Paper
10/07/2619 days ago arxiv.org
Local-first search: retrieval for sensitive data
A paper published on June 30, 2026 proposes a framework for privacy-focused information retrieval, with indexes, models, and inference on users’ devices.
RAG and retrieval Paper
10/07/2619 days ago arxiv.org
CAMI evaluates RAG indexes under a limited budget
Published on June 30, 2026, the CAMI paper proposes selecting semantic enrichment indexes for ingestion pipelines based on retrieval goals and computational cost.
RAG and retrieval Paper
10/07/2619 days ago arxiv.org
CMDR evaluates multimodal retrieval across document pages
Published on July 8, 2026, the article presents CMDR and CMDR-Bench for retrieving relevant pages from multimodal documents, including queries that depend on context across pages.
RAG and retrieval Paper
10/07/2619 days ago arxiv.org
Comparing RAG approaches for semi-structured data
A paper published on June 25, 2026 presents a framework for comparing four RAG approaches across nine standardized scenarios.
RAG and retrieval Paper
10/07/2619 days ago arxiv.org
How to allocate capacity in hierarchical search agents
An article published on July 9, 2026 examines delegation and execution roles in hierarchical search agents and identifies task decomposition as the main performance bottleneck.
RAG and retrieval Paper
10/07/2619 days ago arxiv.org
Diffusion-GR2 speeds up reasoning-based reranking
A post dated July 2, 2026 reports that Diffusion-GR2 achieves ranking accuracy close to an autoregressive model, with decoding 2.4–3.5 times faster.
RAG and retrieval Paper
10/07/2619 days ago arxiv.org
Relevance embeddings for candidate retrieval
A Yandex paper published on July 7, 2026 describes query and item embeddings to retrieve candidates efficiently when relevance scoring is costly.
RAG and retrieval Paper
10/07/2619 days ago arxiv.org
GraphRAG for questions across document collections
A paper published on September 24, 2026 presents an approach to answering global questions about a corpus, which standard retrieval of individual passages may not handle well.
RAG and retrieval Paper
10/07/2619 days ago arxiv.org
KbSD proposes calibrating search decisions in agents
Published on June 30, 2026, the paper describes a self-distillation method to guide search agents in choosing between model memory, retrieved evidence, or abstention.
RAG and retrieval Paper
10/07/2619 days ago arxiv.org
MaxSim and the capacity to represent inner products
An article dated July 8, 2026, shows that MaxSim can exactly replicate inner products between nonnegative k-sparse vectors, providing a theoretical basis for late-interaction retrieval systems.
RAG and retrieval Paper
10/07/2619 days ago arxiv.org
NapMem proposes active navigation of conversational memory
An article published on July 8, 2026 presents NapMem, a framework that organizes a user's history into a linked memory pyramid with multiple levels of granularity.
RAG and retrieval Paper
10/07/2619 days ago arxiv.org
Hard negatives for two-tower retrieval
A paper published on July 2, 2026 proposes using LLM-derived item clusters to generate hard negatives in real time for two-tower recommendation models.
RAG and retrieval Paper
10/07/2619 days ago arxiv.org
Production RAG: evaluating retrieval improvements
A paper published on June 30, 2026, evaluates RAG retrieval strategies and whether their benefits hold across collections with varied formats.
RAG and retrieval Paper
10/07/2619 days ago arxiv.org
In-context retrieval: study tests scale up to one million tokens
A paper published on July 6, 2026, examines language models as retrievers over one-million-token corpora. Its 0.6-billion-parameter BlockSearch generalizes up to 10 times beyond its training length, according to the study.
RAG and retrieval Paper
10/07/2619 days ago arxiv.org
SearchEyes connects simulated worlds to agent training
The SearchEyes paper describes a simulated search world built on a typed knowledge graph for training multimodal agents. Published on July 8, 2026, it addresses gaps among training data, search environments, and reward signals in multi-hop reasoning.
RAG and retrieval Paper
10/07/2619 days ago arxiv.org
SHIFT proposes gates for knowledge conflicts in RAG
Published on June 29, 2026, the paper presents an intervention in FFN activations to balance retrieved evidence and a model’s internal knowledge.
RAG and retrieval Paper
10/07/2619 days ago arxiv.org
STEB compares style embeddings across 96 datasets
Published on July 1, 2026, the post presents an open-source benchmark evaluating style embeddings across 96 datasets and seven languages.
RAG and retrieval Paper
10/07/2619 days ago arxiv.org
Trie execution plans may speed up retrieval pipeline experiments
An article published on July 2, 2026 presents a radix trie execution plan for PyTerrier that reuses shared prefixes and reports reductions of up to 26% in experiment time.

Let's assess your project

I reply with scope and a proposal.