# Explainability Framework for Policy-Aware Autonomous Agents

arXiv: https://arxiv.org/abs/2607.21209 · HTML: https://mlsanity.com/paper/2607.21209/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 23 references that are in the map.
- First posted on arXiv 23 Jul 2026.

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

- [Explanation in Artificial Intelligence: Insights from the Social Sciences](https://mlsanity.com/paper/1706.07269/) (2017)
- [APIA: An Architecture for Policy-Aware Intentional Agents](https://mlsanity.com/paper/2109.08287/) (2021)
- [Metric Temporal Equilibrium Logic over Timed Traces](https://mlsanity.com/paper/2304.14778/) (2023)
- [Founded World Views with Autoepistemic Equilibrium Logic](https://mlsanity.com/paper/1902.07741/) (2019)
- [An ASP Framework for the Refinement of Authorization and Obligation Policies](https://mlsanity.com/paper/2305.13190/) (2023)
- [An Application of ASP in Nuclear Engineering: Explaining the Three Mile Island Nuclear Accident Scenario](https://mlsanity.com/paper/2008.01253/) (2020)
- [The ASP-based Nurse Scheduling System at the University of Yamanashi Hospital](https://mlsanity.com/paper/2506.13600/) (2025)
- [Autonomous Agents and Policy Compliance: A Framework for Reasoning About Penalties](https://mlsanity.com/paper/2512.03931/) (2025)

## Abstract (arXiv)

In the field of Artificial Intelligence, an agent is a system which is able to autonomously make decisions in order to reach a desired goal. As these systems grow more prevalent in our day-to-day lives, there has been an increased need to add explainability features which can provide an account for an agent's behavior. We therefore propose a framework that outlines how to produce comprehensible explanations for policy-aware agents, or agents which have rule-enforcing policies incorporated in their decision-making framework. This framework is designed using insights from the social sciences on how to produce good explanations. It is implemented in the Answer Set Programming language while using Python to assist with information extraction and natural-language translation. Because these agents incur penalties when violating policies, we are able to leverage these penalties to detect undesirable events in scenarios that are counterfactual to the agents' original actions. This lends itself to creating contrastive explanations (e.g., "the agent performed this action because, had it not, undesirable event X would have occurred."), which formulate the core component for our explainability framework. The framework is evaluated using a survey wherein human participants provide feedback on our program-generated explanations.