# K-OPSD: Verifiable On-Policy Self-Distillation for Post-Training Vision-Language Models on AEC Drawings

arXiv: https://arxiv.org/abs/2609.34082 · HTML: https://mlsanity.com/paper/2609.34082/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Chart understanding and anomaly detection, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 10 of its 16 references that are in the map.
- First posted on arXiv 28 Sep 2026.

## Placed in

- Multimodal LLMs / vision-language models / [Chart understanding and anomaly detection](https://mlsanity.com/mllm/chart-understanding-and-anomaly-detection/)
- Knowledge distillation / [Multimodal distillation](https://mlsanity.com/distill/multimodal-distillation/)

## Builds on (most cited first, 10 of 10)

- [On-Policy Distillation of Language Models: Learning from Self-Generated Mistakes](https://mlsanity.com/paper/2306.13649/) (2023)
- [Reinforced Self-Training (ReST) for Language Modeling](https://mlsanity.com/paper/2308.08998/) (2023)
- [Scaling Relationship on Learning Mathematical Reasoning with Large Language Models](https://mlsanity.com/paper/2308.01825/) (2023)
- [Beyond Human Data: Scaling Self-Training for Problem-Solving with Language Models](https://mlsanity.com/paper/2312.06585/) (2023)
- [Large Language Model-Driven Code Compliance Checking in Building Information Modeling](https://mlsanity.com/paper/2506.20551/) (2025)
- [Text2BIM: Generating Building Models Using a Large Language Model-based Multi-Agent Framework](https://mlsanity.com/paper/2408.08054/) (2024)
- [Using Large Language Models for the Interpretation of Building Regulations](https://mlsanity.com/paper/2407.21060/) (2024)
- [CEQuest: Benchmarking Large Language Models for Construction Estimation](https://mlsanity.com/paper/2508.16081/) (2025)
- [Large Language Models in Fire Engineering: An Examination of Technical Questions Against Domain Knowledge](https://mlsanity.com/paper/2403.04795/) (2024)
- [FloorplanVLM: A Vision-Language Model for Floorplan Vectorization](https://mlsanity.com/paper/2602.06507/) (2026)

## Abstract (arXiv)

Interpreting architecture, engineering, and construction (AEC) drawings is hard for general Multimodal Large Language Models (MLLMs) and vision-language models (VLMs). We introduce K-OPSD, a VLM post-training methodology for improving AEC drawing understanding. Building on On-Policy Self-Distillation (OPSD) with verifiable supervision, we construct a teacher from the model's own best-of-N generations, certified by a process-level verifier, and rescue failed prompts by resampling under a hint that exposes the verified answer. We then perform an on-policy model update by training on verified completions with a cross-entropy inner-loss, outperforming the bounded token-wise generalized Jensen-Shannon divergence (JSD) used by on-policy distillation. Using K-OPSD, we fine-tune Qwen3-VL models on the AECV-Bench dataset. The resulting models attain the top average judge score (0.819) and combined accuracy (0.738), achieving competitive results against open-source baseline models. The recipe transfers to the out-of-domain ArchCAD dataset, where the 8B model gains most. We present the verifier suite and the continual learning and self-improving pipeline, our results provide preliminary evidence that verifier-guided self-distillation is a promising route toward more reliable machine reading of architecture drawings.