EvoOntology：自进化本体层让数据智能体 DDR-Bench 平均涨 17.8 分
Banger paper on self-evolving ontologies for agents. You just can't go wrong with implementing an o...
给数据智能体挂个会自进化的本体层，GPT-5.5 在 DDR-Bench 多拿 26.7 分，做法可直接抄。
论文提出 EvoOntology，用专门的智能体为数据源构建本体，并以 MCP server 形式提供 schema、内容和工具三层，供数据智能体在运行时查询。本体按小步类型化编辑演进，每次编辑只有在同一骨干模型上的配对评估显示有效时才保留。在 DDR-Bench 上，六个骨干模型平均提升 17.8 分，其中 GPT-5.5 达到 26.7 分，Qwen3.5-Flash 为 4.8 分。在 BIRD 基准上执行准确率提升 7.4 分，工具层的编辑贡献了进化总收益的 57%。
Banger paper on self-evolving ontologies for agents. You just can't go wrong with implementing an o...
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: arxiv.org/abs/2609.15779 Chat with Paper: academy.dair.ai/papers/evoonto… 💬 11 🔄 7 ❤️ 44 👀 3273 📊 25 ⚡
