Improving Layout Representation Learning Across Inconsistently Annotated Datasets via Agentic Harmonization

ArXi:2604.11042v1 Announce Type: new Fine-tuning object detection (OD) models on combined datasets assumes annotation compatibility, yet datasets often encode conflicting spatial definitions for semantically equivalent categories. We propose an agentic label harmonization workflow that uses a vision-language model to reconcile both category semantics and bounding box granularity across heterogeneous sources before