NVIDIA releases Auto Ontology open semantic layer for AI agents
NVIDIA released Auto Ontology, an Apache 2.0 library that creates context layers from enterprise metadata to ground AI agents in certified business definitions.
Stories per day · 30 days
Relatedknowledge-representation2llm-agents2ai-agents1appsec1compliance1engineering1enterprise-analytics1grc1memory-systems1nvidia1open-source1personal-assistants1reinforcement-learning1security-architecture1security-guidance1security-metrics1semantic-layer1standards1
10 stories, newest first · one card per story
Stories tagged #ontology
EvoMemState framework evolves memory states for LLM personal agents
EvoMemState augments facts with relational and reasoning states to improve personalized assistance in agents.
AppSec Core ontology makes security guidance actionable
The AppSec Core ontology converts scattered security authorities into typed working sets for code changes and compliance duties.
Paper proposes atomic security concerns as a shared security vocabulary
The contribution is conceptual and does not formalize or evaluate a working cybersecurity language.
Paper proposes a method to elicit security metrics for compliance checks
An ontology-based data model aims to give metrics a comparable abstraction so they can be combined across a standard.
AgentOnto: Ontology-Guided LLM Agents for Enterprise Data Analytics
AgentOnto guides enterprise LLM analytics with an ontology that is built, used, and updated from feedback.
An ontology for cross-sectoral crisis management: core and public health modules
ECMO, a modular OWL ontology, standardizes cross-sector crisis data including a SNOMED-aligned public health module.
EvoOntology: A Self-Evolving Ontology Layer for Data Agents
EvoOntology is a self-evolving ontology MCP server that lets data agents query schema, content, and tool layers at runtime to bridge the agent-data gap.
Involving before Evolving: A Vision for Trustworthy Enterprise Digital Twin Engineering
Vision paper proposes 'involving before evolving' staged approach for trustworthy enterprise digital twins, validated via an ongoing Michelin prototype.
Fortunate Recall: Ontology-Driven Memory Lifecycle Management for Persistent Coherence in LLMs
Fortunate Recall introduces ontology-based lifecycle policies for LLM memory, cutting confabulation roughly in half (e.g., 45.1% to 22.4%) versus Mem0.