# Contrastive explanations of BDI agents

arXiv: https://arxiv.org/abs/2602.13323 · HTML: https://mlsanity.com/paper/2602.13323/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 50 references that are in the map.
- First posted on arXiv 10 Feb 2026.

## Builds on (most cited first, 12 of 12)

- [Explanation in Artificial Intelligence: Insights from the Social Sciences](https://mlsanity.com/paper/1706.07269/) (2017)
- [Questioning the AI: Informing Design Practices for Explainable AI User Experiences](https://mlsanity.com/paper/2001.02478/) (2020)
- [Proxy Tasks and Subjective Measures Can Be Misleading in Evaluating Explainable AI Systems](https://mlsanity.com/paper/2001.08298/) (2020)
- [Contrastive Explanations of Plans Through Model Restrictions](https://mlsanity.com/paper/2103.15575/) (2021)
- [Towards Explainable AI Planning as a Service](https://mlsanity.com/paper/1908.05059/) (2019)
- [Explaining Reinforcement Learning Agents Through Counterfactual Action Outcomes](https://mlsanity.com/paper/2312.11118/) (2023)
- [Towards Providing Explanations for AI Planner Decisions](https://mlsanity.com/paper/1810.06338/) (2018)
- [A Human-Centric Method for Generating Causal Explanations in Natural Language for Autonomous Vehicle Motion Planning](https://mlsanity.com/paper/2206.08783/) (2022)
- [Towards Transparent Robotic Planning via Contrastive Explanations](https://mlsanity.com/paper/2003.07425/) (2020)
- [Generating Context-Aware Contrastive Explanations in Rule-based Systems](https://mlsanity.com/paper/2402.13000/) (2024)
- [Intention-aware policy graphs: answering what, how, and why in opaque agents](https://mlsanity.com/paper/2409.19038/) (2024)
- [WHY: Natural Explanations from a Robot Navigator](https://mlsanity.com/paper/1709.09741/) (2017)

## Abstract (arXiv)

The ability of autonomous systems to provide explanations is important for supporting transparency and aiding the development of (appropriate) trust. Prior work has defined a mechanism for Belief-Desire-Intention (BDI) agents to be able to answer questions of the form ``why did you do action X?''. However, we know that we ask contrastive questions (``why did you do X instead of F?''). We therefore extend previous work to be able to answer such questions. A computational evaluation shows that using contrastive questions yields a significant reduction in explanation length. A human subject evaluation was conducted to assess whether such contrastive answers are preferred, and how well they support trust development and transparency. We found some evidence for contrastive answers being preferred, and some evidence that they led to higher trust, perceived understanding, and confidence in the system's correctness. We also evaluated the benefit of providing explanations at all. Surprisingly, there was not a clear benefit, and in some situations we found evidence that providing a (full) explanation was worse than not providing any explanation.