HighlightSnowflake

Semantic views put business metrics and entities in the database

Snowflake overview of Semantic Views: schema-level objects that define metrics, entities, and relationships for consistent business meaning and Cortex Agents.

A Semantic View is a schema-level Snowflake object that stores business metrics, entities, and relationships as metadata atop physical data. It supplies consistent definitions across applications, is queryable with SELECT, usable by Cortex Agents, and shareable via listings. The docs argue this layer fixes the gap between business language and opaque column names and stops inconsistent metric calculations across reports.

Based on: Overview of semantic views | Snowflake Documentation · Snowflake

HighlightAnthropic

Anthropic open-sources MCP as a universal AI-to-data connection standard

Anthropic announces the Model Context Protocol for two-way links between AI tools and data sources via servers and clients.

On 25 Nov 2024 Anthropic open-sourced MCP to connect AI assistants to content repos, business tools, and development environments under one protocol instead of per-source integrations. Release includes the spec and SDKs, local server support in Claude Desktop, an open-source server repo, and pre-built servers for systems such as Google Drive, Slack, GitHub, Git, Postgres, and Puppeteer.

Based on: Introducing the Model Context Protocol · Anthropic

HighlightSnowflake

Cortex Analyst: managed text-to-SQL over Snowflake structure via REST

Snowflake docs on Cortex Analyst—an LLM feature for natural-language questions on structured data, exposed as a REST API.

Cortex Analyst is a fully managed Snowflake Cortex feature that answers business questions on structured Snowflake data in natural language without users writing SQL. It ships as a REST API for embedding in apps and aims to produce accurate text-to-SQL without teams building custom RAG stacks or managing GPUs. Snowflake recommends transitioning to Cortex Agents, which includes Analyst capabilities.

Based on: Cortex Analyst | Snowflake Documentation · Snowflake

HighlightCube Dev

Cube’s semantic layer as the shared surface for BI, embed, and AI agents

Cube docs: agentic analytics on an open-source semantic layer for internal BI and embedded analytics.

Cube is positioned as an agentic analytics platform on a semantic layer for internal BI and embedded analytics. Cube Core centralizes metrics, joins, access rules, and caching upstream of BI tools, apps, and agents. Agents query via Semantic SQL through the semantic layer runtime with validation and access policies, not by writing free-form warehouse SQL.

Based on: Introduction - Cube Documentation · Cube Dev

HighlightarXiv

Increasing the LLM Accuracy for Question Answering: Ontologies to the Rescue!

Paper on improving question answering systems with large language models using ontologies.

This paper presents an approach to improve the accuracy of question answering systems with large language models by leveraging ontologies. The authors propose a method that consists of ontology-based query check and LLM repair, which increases the overall accuracy to 72%. The results provide further evidence that investing knowledge graphs, namely the ontology, provides higher accuracy for LLM-powered question-answering systems.

Based on: Increasing the LLM Accuracy for Question Answering: Ontologies to the Rescue! · arxiv.org

HighlightarXiv

Skill Retrieval Augmentation for Agentic AI

A paper proposing a paradigm for dynamically retrieving and incorporating skills in large language models.

The authors introduce Skill Retrieval Augmentation (SRA), a method for agents to retrieve relevant skills from external corpora on demand. They construct a benchmark, SRA-Bench, to evaluate the full SRA pipeline. The paper shows that retrieval-based skill augmentation can improve agent performance and highlights the need for more efficient skill incorporation.

Based on: Skill Retrieval Augmentation for Agentic AI · arXiv

HighlightarXiv

Separating Semantic Competition from Context Length in RAG Reading

Paper on evaluating Retrieval-Augmented Generation (RAG) systems.

The authors introduce a matched-control protocol to isolate the effect of semantic competition on RAG reading performance. They apply this protocol to two compact open models on SQuAD and report improvements in F1, answer inclusion, and exact match scores. The results suggest that the competition effect is distinct from context length.

Based on: Separating Semantic Competition from Context Length in RAG Reading · arXiv

HighlightarXiv

An Agent-Oriented Pluggable Experience-RAG Skill for Experience-Driven Retrieval Strategy Orchestration

A paper proposing an agent-oriented pluggable retrieval orchestration layer for experience-driven retrieval strategy selection.

The authors present Experience-RAG Skill, a layer positioned between the agent and retriever pool. It analyzes the scene, consults an experience memory, selects a retrieval strategy, and returns structured evidence to the agent. The proposed skill outperforms fixed single-retriever baselines on various tasks.

Based on: An Agent-Oriented Pluggable Experience-RAG Skill for Experience-Driven Retrieval Strategy Orchestration · arXiv

HighlightarXiv

Uncertainty-Aware Hybrid Retrieval for Long-Document RAG

A training-free hybrid retrieval framework for Retrieval Augmented Generation (RAG).

The authors propose Uncertainty-aware Multi-Granularity RAG (UMG-RAG), a hybrid retrieval framework that treats chunk granularity as query-specific reliability estimation. UMG-RAG uses existing dense and sparse retrievers as complementary experts across multiple chunk granularities, estimating reliability from distribution entropy and fusing candidates according to query-specific semantic, lexical, and granularity confidence.

Based on: Uncertainty-Aware Hybrid Retrieval for Long-Document RAG · arXiv

HighlightarXiv

CheckRLM: Effective Knowledge-Thought Coherence Checking in Retrieval-Augmented Reasoning

A framework for improving the reliability of reasoning language models through error checking and correction.

CheckRLM proposes a framework to improve the reliability of reasoning language models by timely checking and correcting factual errors. It extracts claims from the reasoning chain, identifies inconsistencies, and performs minimal-cost corrections using external knowledge. The framework demonstrates strong capability in mitigating error accumulation in long-horizon reasoning with lower costs.

Based on: CheckRLM: Effective Knowledge-Thought Coherence Checking in Retrieval-Augmented Reasoning · arXiv

HighlightarXiv

DynaKRAG: A Unified Framework for Learnable Evidence Control in Multi-Hop Retrieval-Augmented Generation

A framework for learnable evidence control in multi-hop retrieval-augmented generation.

The paper introduces DynaKRAG, a unified framework that formulates multi-hop evidence acquisition as state-conditioned control over atomic evidence operations. It uses a learned controller to select the next operation and updates the evidence state accordingly. The authors evaluate DynaKRAG on several benchmarks and demonstrate its effectiveness in coordinating retrieval, diagnosis, and gap-directed acquisition.

Based on: DynaKRAG: A Unified Framework for Learnable Evidence Control in Multi-Hop Retrieval-Augmented Generation · arXiv

HighlightIEEE Communications Magazine

Proof of Unlearning for Semantic Knowledge Bases in Large Language Models-Enabled Semantic Communication

A framework for efficiently and verifiably updating large language model-enabled semantic knowledge bases.

The authors propose a proof-of-unlearning framework for updating large language models (LLMs) used in semantic knowledge bases. The framework tracks the evolution of unlearning by measuring drifts in the LoRA adapter subspace. Experimental results demonstrate its effectiveness. This work addresses the challenge of removing outdated, malicious, or privacy-sensitive content from LLMs without retraining.

Based on: Proof of Unlearning for Semantic Knowledge Bases in Large Language Models-Enabled Semantic Communication · IEEE Communications Magazine