智能体
x.com ·
@omarsar0
EvoOntology：面向数据 Agent 的自演化本体层论文
一篇 arXiv 论文提出 EvoOntology，用专用 agent 构建本体并以 MCP server 形式提供 schema、内容与工具三层，供数据 agent 运行时查询；本体以小型类型化步骤编辑，仅保留经同 backbone 配对评估证明有效的修改。论文称在 DDR-Bench 上六个 backbone 平均准确率提升 17.8 点（GPT-5.5 提升 26.7 点），BIRD 执行准确率提升 7.4 点，工具层编辑贡献 57% 增益。
AI推荐理由 该帖介绍 arXiv 论文 EvoOntology，给出具体实验数字：在 DDR-Bench 上六个 backbone 平均准确率提升 17.8 点，GPT-5.5 提升 26.7 点，BIRD 执行准确率提升 7.4 点，工具层编辑贡献 57% 增益，并附论文链接。信息密度高、有可查证来源，对数据 Agent 的语义层设计有实际参考价值；但数据来自论文自述，尚未经独立复现。
80
浏览 46,830
点赞 747
评论 38
转发 80
正文
Banger paper on self-evolving ontologies for agents.
You just can't go wrong with implementing an ontology layer for your agents.
This paper shows exactly why.
The show that GPT-5.5 gains 26.7 points on DDR-Bench when the data agent can query an ontology of the data it works with.
Why is this useful?
Data agents normally see tables, files and databases through generic tools, reading column names and file paths one call at a time.
The alternative is a hand-written semantic layer pasted into the prompt, which does not scale to many sources.
EvoOntology builds the ontology with a dedicated agent and serves it as an MCP server with schema, content and tool layers.
The data agent queries it at runtime.
The ontology is then edited in small typed steps, and each edit is kept only if a paired evaluation on the same backbone shows it helps.
Across six backbones on DDR-Bench, accuracy rises 17.8 points on average, from 4.8 on Qwen3.5-Flash to 26.7 on GPT-5.5. On BIRD, execution accuracy rises 7.4 points. Edits to the tool layer account for 57% of the gain from evolution.
Paper: https://arxiv.org/abs/2609.15779
Chat with Paper: https://academy.dair.ai/papers/evoontology-a-self-evolving-ontology-layer-for-data-agents-2609.15779