# Agents and Devices: A Relative Definition of Agency

arXiv: https://arxiv.org/abs/1805.12387 · HTML: https://mlsanity.com/paper/1805.12387/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 May 2018.

## Built on by (most cited first, 16 of 16)

- [Harms from Increasingly Agentic Algorithmic Systems](https://mlsanity.com/paper/2302.10329/) (2023)
- [Goal Misgeneralization: Why Correct Specifications Aren't Enough For Correct Goals](https://mlsanity.com/paper/2210.01790/) (2022)
- [Goal Misgeneralization in Deep Reinforcement Learning](https://mlsanity.com/paper/2105.14111/) (2021)
- [Discovering Agents](https://mlsanity.com/paper/2208.08345/) (2022)
- [Evaluating the Goal-Directedness of Large Language Models](https://mlsanity.com/paper/2504.11844/) (2025)
- [Evaluating AI Evaluation: Perils and Prospects](https://mlsanity.com/paper/2407.09221/) (2024)
- [Aligned with Whom? Direct and social goals for AI systems](https://mlsanity.com/paper/2205.04279/) (2022)
- [Interpreting systems as solving POMDPs: a step towards a formal understanding of agency](https://mlsanity.com/paper/2209.01619/) (2022)
- [Towards Measuring Goal-Directedness in AI Systems](https://mlsanity.com/paper/2410.04683/) (2024)
- [Measuring Goal-Directedness](https://mlsanity.com/paper/2412.04758/) (2024)
- [Interpreting Dynamical Systems as Bayesian Reasoners](https://mlsanity.com/paper/2112.13523/) (2021)
- [Dynamic Normativity: Necessary and Sufficient Conditions for Value Alignment](https://mlsanity.com/paper/2406.11039/) (2024)
- [Goal-Directedness is in the Eye of the Beholder](https://mlsanity.com/paper/2508.13247/) (2025)
- [Technical Report: Evaluating Goal Drift in Language Model Agents](https://mlsanity.com/paper/2505.02709/) (2025)
- [Causal Foundations of Collective Agency](https://mlsanity.com/paper/2605.00248/) (2026)
- [Can AI systems have free will?](https://mlsanity.com/paper/2609.15407/) (2026)

## Abstract (arXiv)

According to Dennett, the same system may be described using a `physical' (mechanical) explanatory stance, or using an `intentional' (belief- and goal-based) explanatory stance. Humans tend to find the physical stance more helpful for certain systems, such as planets orbiting a star, and the intentional stance for others, such as living animals. We define a formal counterpart of physical and intentional stances within computational theory: a description of a system as either a device, or an agent, with the key difference being that `devices' are directly described in terms of an input-output mapping, while `agents' are described in terms of the function they optimise. Bayes' rule can then be applied to calculate the subjective probability of a system being a device or an agent, based only on its behaviour. We illustrate this using the trajectories of an object in a toy grid-world domain.