EvoOntology: A Self-Evolving Ontology Layer for Data Agents
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: ruc-datalab/EvoOntology
Comments: Code: ruc-datalab/EvoOntology
GitHub - ruc-datalab/EvoOntology: EvoOntology: A Self-Evolving Ontology Layer for Data Agents :gear: EvoOntology插件为Claude Code/Codex 建立&进化本体层
@taozi0929 Thanks for sharing our work EvoOntology!
For anyone interested, the code and more details are available on GitHub: ruc-datalab/EvoOntology
Feel free to check it out, and we’d be happy to hear any feedback or thoughts!
1 like · 7 views
@NFTCPS Thanks for sharing our work EvoOntology!
For anyone interested, the code and more details are available on GitHub: ruc-datalab/EvoOntology
Feel free to check it out, and we’d be happy to hear any feedback or thoughts!
1 like · 3 views
@jfcarpio Claro, Atomic-server pone los grafos y ruc-datalab/EvoOntology define las categorías de la data y sus conexiones.
Se puede usar un algoritmo local si llamadas de IA para un modelo de decisiones sencillo y allí que se hablen por MCP.
1 like · 28 views
まるッと揃っているという点ではぱっと扱いやすそう
ruc-datalab/EvoOntology
2 likes · 111 views
EvoOntology: A Self-Evolving Ontology Layer for Data Agents
EvoOntology is the first self-evolving ontology layer for data agents, aiming to bridge the agent-data gap over heterogeneous tables, files, and databases.
ruc-datalab/EvoOntology
EvoOntology: A Self-Evolving Ontology Layer for Data Agents
EvoOntology is the first self-evolving ontology layer for data agents, aiming to bridge the agent-data gap over heterogeneous tables, files, and databases.
ruc-datalab/EvoOntology
13 likes · 1 repost · 1,276 views
Mentions
EvoOntology: A Self-Evolving Ontology Layer for Data Agents 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: ruc-datalab/EvoOntology Comments: Code: ruc-datalab/EvoOntology
GitHub - ruc-datalab/EvoOntology: EvoOntology: A Self-Evolving Ontology Layer for Data Agents :gear: EvoOntology插件为Claude Code/Codex 建立&进化本体层
@taozi0929 Thanks for sharing our work EvoOntology! For anyone interested, the code and more details are available on GitHub: ruc-datalab/EvoOntology Feel free to check it out, and we’d be happy to hear any feedback or thoughts!
@NFTCPS Thanks for sharing our work EvoOntology! For anyone interested, the code and more details are available on GitHub: ruc-datalab/EvoOntology Feel free to check it out, and we’d be happy to hear any feedback or thoughts!
@jfcarpio Claro, Atomic-server pone los grafos y ruc-datalab/EvoOntology define las categorías de la data y sus conexiones. Se puede usar un algoritmo local si llamadas de IA para un modelo de decisiones sencillo y allí que se hablen por MCP.
まるッと揃っているという点ではぱっと扱いやすそう ruc-datalab/EvoOntology
EvoOntology: A Self-Evolving Ontology Layer for Data Agents EvoOntology is the first self-evolving ontology layer for data agents, aiming to bridge the agent-data gap over heterogeneous tables, files, and databases. ruc-datalab/EvoOntology
EvoOntology: A Self-Evolving Ontology Layer for Data Agents EvoOntology is the first self-evolving ontology layer for data agents, aiming to bridge the agent-data gap over heterogeneous tables, files, and databases. ruc-datalab/EvoOntology