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
Full article192 words · extracted from huggingface.co · click to collapse
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., column names and file paths) only through generic tools. Existing approaches either let agents directly explore raw data sources or inject manually constructed semantic layers into prompts. However, neither scales well to large heterogeneous data sources nor adapts to different agent behaviors. In this paper, we introduce EvoOntology, a self-evolving ontology layer for data agents. EvoOntology encapsulates the ontology as an MCP server comprising a schema layer, a content layer, and a tool layer, enabling agents to actively query and interact with the ontology at runtime. To this end, we introduce a builder agent for autonomous ontology construction and a self-evolution loop that continuously refines the ontology through attribution-guided typed edits that are accepted only after a backbone-conditional paired evaluation. Experiments on three well-adopted data-agent benchmarks with four LLM backbones demonstrate that EvoOntology consistently outperforms strong baselines and existing semantic-layer approaches, effectively bridging the agent-data gap and enabling more effective interaction with heterogeneous data. Code: https://github.com/ruc-datalab/EvoOntology
Text extracted automatically; images, tables and formatting may be missing. Original: https://huggingface.co/papers/2609.15779