One paper or post a day, read all the way through.
All reads
Showing 9 of 9-
Toward Effective and Reliable LLM Agents via Dynamic Ontology
OaK constructs and iteratively repairs task-specific schemas and typed graph-reasoning functions, improving aggregate agent performance across three benchmarks while making evidence use and execution failures more inspectable.
-
Maintaining an organizational knowledge graph with an LLM and event sourcing
Planet Arkency turns unstructured organizational content into a typed knowledge graph using a closed ontology, hybrid identity resolution, reviewable change proposals, conflict detection, and event-sourced provenance.
ontologyOriginal ↗ -
How Genie Ontology powers product development at Databricks
Genie Ontology combines governed business definitions, learned context, authority-ranked sources, and permission-aware live analysis to support recurring adoption reviews and reusable product-management agents.
ontologyOriginal ↗ -
An Agentic Hybrid Top-Down and Bottom-Up Approach to Knowledge Graph Generation
A five-stage hybrid pipeline anchors multilingual skill declarations to Wikidata while curating, deduplicating, and recovering specialized concepts, with deployment-scale normalization results but incomplete end-to-end validation.
-
Quipu: A Governed Bitemporal Knowledge Graph Store
Quipu combines post-state write gates, bitemporal governance, conservative trust composition, and signed audit evidence to govern agent-written knowledge graphs while exposing the limits of policy compliance and historical replay.
-
Graph Engineering in the Era of LLM Agents: From Individual Intelligence to System Intelligence
This survey explains how explicit task, agent, and runtime-state graphs, grounded in shared ontology, can organize reliable agent systems and inform the design of a governed context platform.
-
EvoOntology: A Self-Evolving Ontology Layer for Data Agents
EvoOntology builds an evidence-grounded, tool-accessible ontology over heterogeneous data and improves it through trajectory-guided edits accepted by paired validation.
-
HySparse2: Hybrid Sparse Attention with Two-Level KV Sharing
HySparse2 shares attention memory across and within decoder blocks so long-context agents can prefill with less computation and KV-cache storage while improving retrieval.
-
Skill-Based Agentic Evaluation for Real-Time Data Science Tasks
A first-principles, interactive guide to grading agents when the right answer keeps changing.