AITOPAI热报
PapersSelected

EvoOntology for self-evolving agent ontologies

Banger paper on self-evolving ontologies for agents. You just can't go wrong with implementing an o...

elvis@omarsar0
Post
View the post
Why we picked it

Developers can implement EvoOntology to improve their data agents' performance without hand-coding semantic layers that don't scale.

EvoOntology improves data agent performance by 26.7 points on DDR-Bench when using GPT-5.5. The system builds an ontology layer with a dedicated agent and serves it as an MCP server with schema, content and tool layers. 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.

Original · elvis

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 ⚡

#EvoOntology#GPT-5.5#Qwen3.5-Flash#DDR-Bench#agents

Keep reading

Recent stories with the same tag or section
ModelsBuildersSelected10:41
EvoOntology for Data Agents

EvoOntology solves the critical challenge of semantic drift in data agents by creating a versioned, evolvable knowledge layer that accumulates evidence from real workloads. For developers working with heterogeneous data systems, this approach provides a practical method to maintain semantic accuracy without constant manual intervention or context window limitations.

#EvoOntology#Data Agent#MCP#semantic layer
shao__meng@shao__mengSource
PapersBuildersSelected03:53
Yann LeCun Explains Why JEPA Research Papers Differ From Meta Models

The thread lays out a taxonomy of SSL methods — predictor presence, anti-collapse criterion, augmentation scheme — that helps readers place any new 'JEPA' paper in the right context. Researchers deciding which papers to cite or reproduce will find it a concise map of what academic work can and cannot demonstrate. The core distinction between method discovery and resource-heavy scaling applies far beyond the JEPA family.

#JEPA#DINO#V-JEPA#Meta-FAIR
官方账号Yann LeCun@ylecunSource
PapersBuildersSelected02:51
Oxford paper finds frontier LLM agents fail cross-vendor coordination

The practical implication is that agent interoperability breaks down not from capability gaps but from unstated conventions, so inter-agent protocols may need explicit shared norms rather than smarter models. Teams building multi-agent systems that span different vendors should add instructions telling agents to avoid unstated conventions and prefer actions any partner can read correctly. The finding applies to anyone chaining GPT-5.2 and Gemini 3 Pro agents together today.

#GPT-5.2#Gemini 3 Pro#agents#AI safety
rohanpaul_ai@rohanpaul_aiSource