# The evolutionary advantage of guilt: co-evolution of social and non-social guilt in structured populations

arXiv: https://arxiv.org/abs/2302.09859 · HTML: https://mlsanity.com/paper/2302.09859/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 6 of its 96 references that are in the map.
- First posted on arXiv 20 Feb 2023.

## Builds on (most cited first, 6 of 6)

- [Artificial Intelligence, Values and Alignment](https://mlsanity.com/paper/2001.09768/) (2020)
- [Statistical physics of human cooperation](https://mlsanity.com/paper/1705.07161/) (2017)
- [When to (or not to) trust intelligent machines: Insights from an evolutionary game theory analysis of trust in repeated games](https://mlsanity.com/paper/2007.11338/) (2020)
- [Social Diversity Reduces the Complexity and Cost of Fostering Fairness](https://mlsanity.com/paper/2211.10517/) (2022)
- [Evolution of Coordination in Pairwise and Multi-player Interactions via Prior Commitments](https://mlsanity.com/paper/2009.11727/) (2020)
- [Counterfactual thinking in cooperation dynamics](https://mlsanity.com/paper/1912.08946/) (2019)

## Abstract (arXiv)

Building ethical machines may involve bestowing upon them the emotional capacity to self-evaluate and repent on their actions. While apologies represent potential strategic interactions, the explicit evolution of guilt as a behavioural trait remains poorly understood. Our study delves into the co-evolution of two forms of emotional guilt: social guilt entails a cost, requiring agents to exert efforts to understand others' internal states and behaviours; and non-social guilt, which only involves awareness of one's own state, incurs no social cost. Resorting to methods from evolutionary game theory, we study analytically, and through extensive numerical and agent-based simulations, whether and how guilt can evolve and deploy, depending on the underlying structure of the systems of agents. Our findings reveal that in lattice and scale-free networks, strategies favouring emotional guilt dominate a broader range of guilt and social costs compared to non-structured well-mixed populations, so leading to higher levels of cooperation. In structured populations, both social and non-social guilt can thrive through clustering with emotionally inclined strategies, thereby providing protection against exploiters, particularly for less costly non-social strategies. These insights shed light on the complex interplay of guilt and cooperation, enhancing our understanding of ethical artificial intelligence.