# An Affective-Taxis Hypothesis for Alignment and Interpretability

arXiv: https://arxiv.org/abs/2505.17024 · HTML: https://mlsanity.com/paper/2505.17024/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 83 references that are in the map.
- First posted on arXiv 3 May 2025.

## Builds on (most cited first, 13 of 13)

- [Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2204.05862/) (2022)
- [dm_control: Software and Tasks for Continuous Control](https://mlsanity.com/paper/2006.12983/) (2020)
- [How to Train Your Energy-Based Models](https://mlsanity.com/paper/2101.03288/) (2021)
- [A Complete Recipe for Stochastic Gradient MCMC](https://mlsanity.com/paper/1506.04696/) (2015)
- [Is Behavior Cloning All You Need? Understanding Horizon in Imitation Learning](https://mlsanity.com/paper/2407.15007/) (2024)
- [On the Expressivity of Markov Reward](https://mlsanity.com/paper/2111.00876/) (2021)
- [Beyond Preferences in AI Alignment](https://mlsanity.com/paper/2408.16984/) (2024)
- [Occam's razor is insufficient to infer the preferences of irrational agents](https://mlsanity.com/paper/1712.05812/) (2017)
- [Compositional Generative Modeling: A Single Model is Not All You Need](https://mlsanity.com/paper/2402.01103/) (2024)
- [Can Forward Gradient Match Backpropagation?](https://mlsanity.com/paper/2306.06968/) (2023)
- [Human-like Affective Cognition in Foundation Models](https://mlsanity.com/paper/2409.11733/) (2024)
- [NeuroAI for AI Safety](https://mlsanity.com/paper/2411.18526/) (2024)
- [Mental Sampling in Multimodal Representations](https://mlsanity.com/paper/1710.05219/) (2017)

## Built on by (most cited first, 1 of 1)

- [On the Variational Costs of Changing Our Minds](https://mlsanity.com/paper/2509.17957/) (2025)

## Abstract (arXiv)

AI alignment is a field of research that aims to develop methods to ensure that agents always behave in a manner aligned with (i.e. consistently with) the goals and values of their human operators, no matter their level of capability. This paper proposes an affectivist approach to the alignment problem, re-framing the concepts of goals and values in terms of affective taxis, and explaining the emergence of affective valence by appealing to recent work in evolutionary-developmental and computational neuroscience. We review the state of the art and, building on this work, we propose a computational model of affect based on taxis navigation. We discuss evidence in a tractable model organism that our model reflects aspects of biological taxis navigation. We conclude with a discussion of the role of affective taxis in AI alignment.