RUC Team Proposes EvoOntology to Close the Agent-Data Gap

RUC-DataLab's EvoOntology paper proposes a self-evolving ontology layer that lets data agents build reusable semantic understanding of heterogeneous data, boosting GPT-5.5 by 26.7 points on DDR-Bench.

2026-09-21 ~ 2026-09-22 · 2 related posts

• EvoOntology: a self-evolving ontology layer bridges the agent-data gap — RUC-DataLab · 2026-09-21
• Ontology layer for agents boosts GPT-5.5 by 26.7 points on DDR-Bench — omarsar0 · 2026-09-22