# A Local Agentic AI Framework to Generate Edge Case Scenarios for Safety Assurance

arXiv: https://arxiv.org/abs/2610.13479 · HTML: https://mlsanity.com/paper/2610.13479/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Agent threats, guardrails and governance, one of 16 directions in LLM agents and tool use.
- Builds on 17 of its 56 references that are in the map.
- First posted on arXiv 9 Oct 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, 17 of 17)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Unity: A General Platform for Intelligent Agents](https://mlsanity.com/paper/1809.02627/) (2018)
- [Nemotron 3 Nano: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning](https://mlsanity.com/paper/2512.20848/) (2025)
- [The Safety Filter: A Unified View of Safety-Critical Control in Autonomous Systems](https://mlsanity.com/paper/2309.05837/) (2023)
- [Qwen3-Coder-Next Technical Report](https://mlsanity.com/paper/2603.00729/) (2026)
- [Formal Scenario-Based Testing of Autonomous Vehicles: From Simulation to the Real World](https://mlsanity.com/paper/2003.07739/) (2020)
- [LLM-attacker: Enhancing Closed-loop Adversarial Scenario Generation for Autonomous Driving with Large Language Models](https://mlsanity.com/paper/2501.15850/) (2025)
- [Guidance on the Safety Assurance of Autonomous Systems in Complex Environments (SACE)](https://mlsanity.com/paper/2208.00853/) (2022)
- [Adversarial Generation and Collaborative Evolution of Safety-Critical Scenarios for Autonomous Vehicles](https://mlsanity.com/paper/2508.14527/) (2025)
- [From Failures to Fixes: LLM-Driven Scenario Repair for Self-Evolving Autonomous Driving](https://mlsanity.com/paper/2505.22067/) (2025)
- [Bridging Research and Practice in Simulation-based Testing of Industrial Robot Navigation Systems](https://mlsanity.com/paper/2510.09396/) (2025)
- [SCALOFT: An Initial Approach for Situation Coverage-Based Safety Analysis of an Autonomous Aerial Drone in a Mine Environment](https://mlsanity.com/paper/2505.20969/) (2025)
- [Towards Safer Mobile Agents: Scalable Generation and Evaluation of Diverse Scenarios for VLMs](https://mlsanity.com/paper/2601.08470/) (2026)
- [SG-CADVLM: A Context-Aware Decoding Powered Vision Language Model for Safety-Critical Scenario Generation](https://mlsanity.com/paper/2601.18442/) (2026)
- [PlannerForge: LLM Agents for Scenario-Based Testing of Motion Planners in Autonomous Driving](https://mlsanity.com/paper/2609.08965/) (2026)

## Abstract (arXiv)

Generating edge case scenarios is crucial for training, testing and safety assuring autonomous systems. This identifies hazardous failures to increase system reliability and robustness, ensures the system can still function safely on the boundaries of its operational design domain and learns the expected system behaviour for these edge cases. The rapid advancement in the generation and analysis capabilities of language models (LMs) has expanded their applicability and recent work has investigated LM scenario generation. However, many recent approaches rely on human-in-the-loop or rule-based strategies. This restricts the LM's ability to generate diverse and edge case scenarios; the long tail of the distribution. Our work uses local LMs in a laptop-based agentic AI framework for adaptive scenario generation. This is cheap, fully-controlled, ensures data privacy and security. It uses think, act, observe, update, and continue loops with lightweight JSON encoding to generate scenarios. We use the system requirements, system description and environment description as knowledge bases in contextual prompts for an LM to ensure scenario realism. A second, independent LM critiques each scenario using domain specific criteria so it can be refined. The refined scenarios are run in simulation and evaluation metrics collected. These metric scores are analysed and similar scenarios are created for edge cases (exploitation) or novel scenarios are generated to explore the scenario space. Post-hoc clustering using metric scores and thematic-type analysis of the rich-text scenario descriptions produced by the LM pinpoints functional gaps and their triggering conditions. This creates traceable evidence for the safety assurance case. Our work highlights the potential of a flexible and adaptive local agentic AI framework for automating edge case generation and producing traceable safety assurance evidence.