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.
EvoOntology packages the ontology as an MCP server with schema, content, and tool layers so agents can actively query it during execution. A builder agent autonomously constructs the ontology, and a self-evolution loop refines it via attribution-guided typed edits accepted only after backbone-conditional paired evaluation. Experiments across three data-agent benchmarks and four LLM backbones show consistent outperformance of strong baselines and existing semantic-layer approaches.
- Ontology exposed as MCP server with schema, content, tool layers
- Builder agent plus self-evolution loop refines ontology at runtime
- Outperforms baselines across three benchmarks and four LLM backbones
From the original article
1 min read at huggingface.co
Data agents aim to fulfill natural-language instructions over heterogeneous data, including tables, files, and databases. However, data agents face a challenging agent-data gap: heterogeneous data resides outside the agent, while the agent can access it (e. g.
By Meiduo Chong, Shaolei Zhang, Ju Fan · huggingface.co
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.