EvoOntology：面向数据智能体的自进化本体层

View PDF HTML (experimental)

Abstract: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: this https URL

Comments:	Code: this https URL
Subjects:	Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Databases (cs.DB)
Cite as:	arXiv:2609.15779 [cs.AI]
	(or arXiv:2609.15779v2 [cs.AI] for this version)
	https://doi.org/10.48550/arXiv.2609.15779 arXiv-issued DOI via DataCite

Submission history

From: Shaolei Zhang [view email]
[v1] Mon, 14 Sep 2026 15:59:24 UTC (1,320 KB)
[v2] Mon, 2 Nov 2026 14:07:23 UTC (1,320 KB)