# SpatialOPSD: Self-Distilling Spatial Intelligence from Verified Coding Agent Traces

arXiv: https://arxiv.org/abs/2610.11366 · HTML: https://mlsanity.com/paper/2610.11366/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning.
- Builds on 29 of its 50 references that are in the map.
- First posted on arXiv 8 Oct 2026.

## Placed in

- LLM reasoning / [Spatial and embodied reasoning](https://mlsanity.com/lr/spatial-and-embodied-reasoning/)
- Multimodal LLMs / vision-language models / [Embodied and 3D vision-language models](https://mlsanity.com/mllm/embodied-and-3d-vision-language-models/)
- LLM agents and tool use / [Multimodal and embodied agents](https://mlsanity.com/agents/multimodal-and-embodied-agents/)

## Builds on (most cited first, 29 of 29)

- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [Qwen3-VL Technical Report](https://mlsanity.com/paper/2511.21631/) (2025)
- [InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency](https://mlsanity.com/paper/2508.18265/) (2025)
- [OpenAI GPT-5 System Card](https://mlsanity.com/paper/2601.03267/) (2025)
- [Depth Anything 3: Recovering the Visual Space from Any Views](https://mlsanity.com/paper/2511.10647/) (2025)
- [Neural Text Generation with Unlikelihood Training](https://mlsanity.com/paper/1908.04319/) (2019)
- [Self-Distilled Reasoner: On-Policy Self-Distillation for Large Language Models](https://mlsanity.com/paper/2601.18734/) (2026)
- [Reinforcement Learning via Self-Distillation](https://mlsanity.com/paper/2601.20802/) (2026)
- [Self-Distilled RLVR](https://mlsanity.com/paper/2604.03128/) (2026)
- [Vision-OPD: Learning to See Fine Details for Multimodal LLMs via On-Policy Self-Distillation](https://mlsanity.com/paper/2605.18740/) (2026)
- [Think3D: Thinking with Space for Spatial Reasoning](https://mlsanity.com/paper/2601.13029/) (2026)
- [SpaceVista: All-Scale Visual Spatial Reasoning from mm to km](https://mlsanity.com/paper/2510.09606/) (2025)
- [SpatialClaw: Rethinking Action Interface for Agentic Spatial Reasoning](https://mlsanity.com/paper/2606.13673/) (2026)
- [Visual-OPSD: Cross-Modal On-Policy Self-Distillation for Efficient Unified Multimodal Reasoning](https://mlsanity.com/paper/2606.18974/) (2026)
- [pySpatial: Generating 3D Visual Programs for Zero-Shot Spatial Reasoning](https://mlsanity.com/paper/2603.00905/) (2026)
- [ViCuR: Visual Cues as Recoverable Privilege for Multimodal On-Policy Distillation](https://mlsanity.com/paper/2606.05718/) (2026)
- [S-Agent: Spatial Tool-Use Elicits Reasoning for Spatial Intelligence](https://mlsanity.com/paper/2606.20515/) (2026)
- [Thinking Without Images: Internalizing Visual Manipulation with On-Policy Self-Distillation](https://mlsanity.com/paper/2606.08719/) (2026)
- [Is More Privileged Information Better? From Solution Traces to Problem-Solving Structure in Self-Distilled Reasoning](https://mlsanity.com/paper/2608.01589/) (2026)
- [Holi-Spatial: Evolving Video Streams into Holistic 3D Spatial Intelligence](https://mlsanity.com/paper/2603.07660/) (2026)
- [OpenSpatial: A Principled Data Engine for Empowering Spatial Intelligence](https://mlsanity.com/paper/2604.07296/) (2026)
- [OmniOPSD: Rationale-Privileged On-Policy Self-Distillation for Affective Computing](https://mlsanity.com/paper/2606.15920/) (2026)
- [RP-OPSD: Resolution-Privileged On-Policy Self-Distillation for Multimodal Large Language Models](https://mlsanity.com/paper/2607.24447/) (2026)
- [ViSRA: A Video-based Spatial Reasoning Agent for Multi-modal Large Language Models](https://mlsanity.com/paper/2605.10106/) (2026)
- [Seeing Before Reasoning: Decoupling Perception and Reasoning for Shortcut-Resilient Multimodal On-Policy Self-Distillation](https://mlsanity.com/paper/2606.19120/) (2026)
- [ProSR: Process-Shaped Spatial Reasoning for Reliable Chain-of-Thought in VLMs](https://mlsanity.com/paper/2605.25524/) (2026)
- [DAPD: Dual-Anchored Policy Distillation](https://mlsanity.com/paper/2608.01735/) (2026)
- [Copy Less, Ground More: Overcoming Repetitive Copying in Long-Context Reasoning via Evidence-Aware Reinforcement Learning](https://mlsanity.com/paper/2607.19345/) (2026)

## Abstract (arXiv)

Spatial coding agents significantly improve spatial reasoning in Multimodal Large Language Models (MLLMs) by using external tools to generate verified execution traces. However, this paradigm inherently suffers from prohibitive inference-time overhead and external dependencies. In this paper, we explore whether an MLLM can internalize this agentic capability to operate entirely tool-free. We begin with a simple observation: prompting an MLLM with summarized execution traces of a spatial coding agent naturally unlocks the model's internal spatial Chain-of-Thought (CoT). Motivated by this, we introduce SpatialOPSD, an on-policy self-distillation framework that internalizes spatial reasoning into a standalone MLLM by formulating verified agent traces as privileged information. To mitigate privileged-information leakage during distillation, we introduce Repetition-Aware Distillation, which combines repetition masking with unlikelihood regularization. Experiments across multiple benchmarks demonstrate that self-distilling SpatialOPSD achieves higher average accuracy than SFT and GRPO on both spatial and OOD datasets, exhibiting superior performance and generalization.