Ontology layer for agents boosts GPT-5.5 by 26.7 points on DDR-Bench

omarsar0 · x · 2026-09-22

A paper on self-evolving ontologies for agents. Data agents normally inspect tables and files via generic tools one call at a time, or rely on a hand-written semantic layer pasted into the prompt — which doesn't scale across many sources.

EvoOntology builds the ontology with a dedicated agent and serves it as an MCP server with schema, content, and tool layers that the data agent queries at runtime. The ontology is edited in small typed steps, with each edit kept only if a paired evaluation on the same backbone shows gains. GPT-5.5 gains 26.7 points on DDR-Bench, with accuracy rising across six backbones.

Related event: RUC Team Proposes EvoOntology to Close the Agent-Data Gap(2 posts)→

Original post →

More from coding & agent

coding & agent channel →