# Learning of Robot Safety Policies via Adversarial Synthetic Scenarios

arXiv: https://arxiv.org/abs/2606.05952 · HTML: https://mlsanity.com/paper/2606.05952/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Agent threats, guardrails and governance, one of 16 directions in LLM agents and tool use.
- Builds on 10 of its 13 references that are in the map.
- First posted on arXiv 4 Jun 2026.

## Placed in

- LLM agents and tool use / [Agent threats, guardrails and governance](https://mlsanity.com/agents/agent-threats-guardrails-and-governance/)

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

- [Keypoint Action Tokens Enable In-Context Imitation Learning in Robotics](https://mlsanity.com/paper/2403.19578/) (2024)
- [Plug in the Safety Chip: Enforcing Constraints for LLM-driven Robot Agents](https://mlsanity.com/paper/2309.09919/) (2023)
- [SELP: Generating Safe and Efficient Task Plans for Robot Agents with Large Language Models](https://mlsanity.com/paper/2409.19471/) (2024)
- [MimicDroid: In-Context Learning for Humanoid Robot Manipulation from Human Play Videos](https://mlsanity.com/paper/2509.09769/) (2025)
- [SafeEmbodAI: a Safety Framework for Mobile Robots in Embodied AI Systems](https://mlsanity.com/paper/2409.01630/) (2024)
- [LongSafety: Evaluating Long-Context Safety of Large Language Models](https://mlsanity.com/paper/2502.16971/) (2025)
- [InCoRo: In-Context Learning for Robotics Control with Feedback Loops](https://mlsanity.com/paper/2402.05188/) (2024)
- [Safe Learning for Contact-Rich Robot Tasks: A Survey from Classical Learning-Based Methods to Safe Foundation Models](https://mlsanity.com/paper/2512.11908/) (2025)
- [RoboMorph: In-Context Meta-Learning for Robot Dynamics Modeling](https://mlsanity.com/paper/2409.11815/) (2024)
- [Safe In-Context Reinforcement Learning](https://mlsanity.com/paper/2509.25582/) (2025)

## Built on by (most cited first, 1 of 1)

- [Ensuring Safe Physical AI in Urban Mobility via Hazard-Informed Synthesized Envelopes](https://mlsanity.com/paper/2608.14481/) (2026)

## Abstract (arXiv)

In this work, we propose an agentic gamification framework for hazard-informed learning of robot safety policies through synthetic scenarios. We model scenario generation as an adversarial game between two agents: a Red Team that explores the space of potential failures by constructing hazardous situations, and a Blue Team that incrementally refines safety policies to prevent them. This iterative process enables efficient discovery of high-risk edge cases that are unlikely to be captured through random simulation or manual enumeration. By combining classical risk modeling with adversarial scenario generation and modern learning paradigms, this work provides a scalable pathway for embedding safety into Physical AI systems operating in complex real-world environments. The paper describes ongoing work. The contribution is a problem formulation and a proposed solution architecture.