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)→
More from coding & agent
- LukeW: using ALT tags to boost relevance of inline AI-generated images — LukeW · 2026-09-22
- Muse Agent negotiates auto insurance, books apartment tours, tracks AI news for its user — Saboo_Shubham_ · 2026-09-22
- SemIf open-sources Jev-style semantic ifs: 4B model runs on a single 3090, browser demo live — Hacubu · 2026-09-22
- Developer shares model-split workflow: Perplexity for research, Claude Code as the coding workhorse — ZabihullahAtal · 2026-09-22
- Fireworks shows two Jev training recipes: GRPO-style reward scoring and offline DPO/SFT filtering — sophiamyang · 2026-09-22
- After a year of building, the end-state agent harness: max-freedom execution backend plus a free-form canvas UI — TheZachMueller · 2026-09-22