# Goal-Directedness is in the Eye of the Beholder

arXiv: https://arxiv.org/abs/2508.13247 · HTML: https://mlsanity.com/paper/2508.13247/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 34 references that are in the map.
- First posted on arXiv 18 Aug 2025.

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

- [The Mythos of Model Interpretability](https://mlsanity.com/paper/1606.03490/) (2016)
- [Function Vectors in Large Language Models](https://mlsanity.com/paper/2310.15213/) (2023)
- [Frontier Models are Capable of In-context Scheming](https://mlsanity.com/paper/2412.04984/) (2024)
- [Multi-Agent Risks from Advanced AI](https://mlsanity.com/paper/2502.14143/) (2025)
- [Cooperate or Collapse: Emergence of Sustainable Cooperation in a Society of LLM Agents](https://mlsanity.com/paper/2404.16698/) (2024)
- [Agent Incentives: A Causal Perspective](https://mlsanity.com/paper/2102.01685/) (2021)
- [Agents and Devices: A Relative Definition of Agency](https://mlsanity.com/paper/1805.12387/) (2018)
- [Evaluating the Goal-Directedness of Large Language Models](https://mlsanity.com/paper/2504.11844/) (2025)
- [Modeling AGI Safety Frameworks with Causal Influence Diagrams](https://mlsanity.com/paper/1906.08663/) (2019)
- [Towards Measuring Goal-Directedness in AI Systems](https://mlsanity.com/paper/2410.04683/) (2024)
- [Measuring Goal-Directedness](https://mlsanity.com/paper/2412.04758/) (2024)
- [On Imperfect Recall in Multi-Agent Influence Diagrams](https://mlsanity.com/paper/2307.05059/) (2023)

## Built on by (most cited first, 3 of 3)

- [A Behavioural and Representational Evaluation of Goal-Directedness in Language Model Agents](https://mlsanity.com/paper/2602.08964/) (2026)
- [Causal Foundations of Collective Agency](https://mlsanity.com/paper/2605.00248/) (2026)
- [An Investigation of the NeurIPS and ICML 2025 Position Tracks](https://mlsanity.com/paper/2608.16894/) (2026)

## Abstract (arXiv)

Our ability to predict the behavior of complex agents turns on the attribution of goals. Probing for goal-directed behavior comes in two flavors: Behavioral and mechanistic. The former proposes that goal-directedness can be estimated through behavioral observation, whereas the latter attempts to probe for goals in internal model states. We work through the assumptions behind both approaches, identifying technical and conceptual problems that arise from formalizing goals in agent systems. We arrive at the perhaps surprising position that goal-directedness cannot be measured objectively. We outline new directions for modeling goal-directedness as an emergent property of dynamic, multi-agent systems.