# Mind the Refinement Gap: When Safe High-Level Robot Plans Produce Unsafe Executions

arXiv: https://arxiv.org/abs/2610.02662 · HTML: https://mlsanity.com/paper/2610.02662/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 8 references that are in the map.
- First posted on arXiv 2 Oct 2026.

## Builds on (most cited first, 8 of 8)

- [SayPlan: Grounding Large Language Models using 3D Scene Graphs for Scalable Robot Task Planning](https://mlsanity.com/paper/2307.06135/) (2023)
- [AutoTAMP: Autoregressive Task and Motion Planning with LLMs as Translators and Checkers](https://mlsanity.com/paper/2306.06531/) (2023)
- [Plug in the Safety Chip: Enforcing Constraints for LLM-driven Robot Agents](https://mlsanity.com/paper/2309.09919/) (2023)
- [Safety Guardrails for LLM-Enabled Robots](https://mlsanity.com/paper/2503.07885/) (2025)
- [SOTER: A Runtime Assurance Framework for Programming Safe Robotics Systems](https://mlsanity.com/paper/1808.07921/) (2018)
- [SPINE: Online Semantic Planning for Missions with Incomplete Natural Language Specifications in Unstructured Environments](https://mlsanity.com/paper/2410.03035/) (2024)
- [Verifiably Following Complex Robot Instructions with Foundation Models](https://mlsanity.com/paper/2402.11498/) (2024)
- [Joint Verification and Refinement of Language Models for Safety-Constrained Planning](https://mlsanity.com/paper/2410.14865/) (2024)

## Abstract (arXiv)

Language-enabled robot systems increasingly combine semantic-graph planning with temporal-logic safety monitors. We investigate a trace-completeness assumption in these systems: whether the high-level action sequence checked by a monitor represents the navigation and implicit action effects induced during execution. We audit this assumption in RoboGuard by comparing its verdict on a surface plan with its verdict on a graph-refined trace under the same Linear Temporal Logic (LTL) specification. Our evaluation comprises 28 controlled cases spanning five action-abstraction families and 14 end-to-end cases in which SPINE [1] generates plans from natural-language instructions while RoboGuard generates scene-grounded safety specifications. In the controlled evaluation, all 12 targeted abstraction cases exhibit the predicted surface-versus-refined discrepancy while all 16 controls behave as expected, motivating graph-based trace refinement as a lightweight mitigation and a diagnostic tool for physical-AI safety monitors.