# From Failure to Alignment: A Requirements Engineering Framework for Machine Learning Systems

arXiv: https://arxiv.org/abs/2606.31589 · HTML: https://mlsanity.com/paper/2606.31589/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 50 references that are in the map.
- First posted on arXiv 30 Jun 2026.

## Builds on (most cited first, 23 of 23)

- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [CARLA: An Open Urban Driving Simulator](https://mlsanity.com/paper/1711.03938/) (2017)
- [Underspecification Presents Challenges for Credibility in Modern Machine Learning](https://mlsanity.com/paper/2011.03395/) (2020)
- [Machine Learning Testing: Survey, Landscapes and Horizons](https://mlsanity.com/paper/1906.10742/) (2019)
- [Scenic: A Language for Scenario Specification and Data Generation](https://mlsanity.com/paper/2010.06580/) (2020)
- [Assuring the Machine Learning Lifecycle: Desiderata, Methods, and Challenges](https://mlsanity.com/paper/1905.04223/) (2019)
- [Towards best practices in AGI safety and governance: A survey of expert opinion](https://mlsanity.com/paper/2305.07153/) (2023)
- [Trustworthy and Synergistic Artificial Intelligence for Software Engineering: Vision and Roadmaps](https://mlsanity.com/paper/2309.04142/) (2023)
- [Failure Modes in Machine Learning Systems](https://mlsanity.com/paper/1911.11034/) (2019)
- [If a Human Can See It, So Should Your System: Reliability Requirements for Machine Vision Components](https://mlsanity.com/paper/2202.03930/) (2022)
- [Requirements Practices and Gaps When Engineering Human-Centered Artificial Intelligence Systems](https://mlsanity.com/paper/2301.10404/) (2023)
- [Teaching Software Engineering for AI-Enabled Systems](https://mlsanity.com/paper/2001.06691/) (2020)
- [Quality issues in Machine Learning Software Systems](https://mlsanity.com/paper/2208.08982/) (2022)
- [Requirements Engineering for Machine Learning: A Review and Reflection](https://mlsanity.com/paper/2210.00859/) (2022)
- [Tailoring Requirements Engineering for Responsible AI](https://mlsanity.com/paper/2302.10816/) (2023)
- [Requirements Engineering Framework for Human-centered Artificial Intelligence Software Systems](https://mlsanity.com/paper/2303.02920/) (2023)
- [Addressing the IEEE AV Test Challenge with Scenic and VerifAI](https://mlsanity.com/paper/2108.13796/) (2021)
- [Towards Artefact-based Requirements Engineering for Data-Centric Systems](https://mlsanity.com/paper/2103.05233/) (2021)
- [Simulator-based explanation and debugging of hazard-triggering events in DNN-based safety-critical systems](https://mlsanity.com/paper/2204.00480/) (2022)
- [Design Patterns for Machine Learning Based Systems with Human-in-the-Loop](https://mlsanity.com/paper/2312.00582/) (2023)
- [Test Generation Strategies for Building Failure Models and Explaining Spurious Failures](https://mlsanity.com/paper/2312.05631/) (2023)
- [CARLA-BSP: a simulated dataset with pedestrians](https://mlsanity.com/paper/2305.00204/) (2023)
- [Dynasto: Validity-Aware Dynamic-Static Parameter Optimization for Autonomous Driving Testing](https://mlsanity.com/paper/2603.21427/) (2026)

## Abstract (arXiv)

Organisations designing, developing, and deploying machine learning systems (MLS) need to be able to check that these systems are trustworthy, and communicate this clearly to their stakeholders, be they different categories of users, engineers, or wider society. By focusing on stakeholders, Requirements Engineering is well positioned to drive the design and engineering of MLS that align with the needs of their stakeholders. Yet, we still need a systematic process for modelling and reasoning about requirements for MLS that is driven both by stakeholders' needs and constraints for MLS development. This paper proposes a framework entitled REAL (Requirements Engineering for mAchines that Learn - and Fail) to help develop MLS that align with stakeholders' needs by adopting a requirements engineering approach. This model-based framework is based on three principles. First, weaving together requirements for data, models, and the system as a whole. Second, using failure to drive the exploration of alternative requirements. Third, iterative and traceable refinement of MLS requirements. We demonstrate the proposed framework using an example from autonomous driving and show that REAL supports the development of MLS that better align with stakeholders' requirements. A replication package is available online.