# Robust agents learn causal world models

arXiv: https://arxiv.org/abs/2402.10877 · HTML: https://mlsanity.com/paper/2402.10877/

## Key facts

- Cited by 81 papers in the map (data through 14 Oct 2026).
- Placed in World models for language agents, one of 11 directions in World models.
- Builds on 46 of its 83 references that are in the map.
- First posted on arXiv 16 Feb 2024.

## Placed in

- World models / [World models for language agents](https://mlsanity.com/wm/world-models-for-language-agents/)
- LLM reasoning / [Causal reasoning in LLMs](https://mlsanity.com/lr/causal-reasoning-in-llms/)

## Builds on (most cited first, 30 of 46)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Benchmarking Neural Network Robustness to Common Corruptions and Perturbations](https://mlsanity.com/paper/1903.12261/) (2019)
- [Invariant Risk Minimization](https://mlsanity.com/paper/1907.02893/) (2019)
- [Relational inductive biases, deep learning, and graph networks](https://mlsanity.com/paper/1806.01261/) (2018)
- [On the Spectral Bias of Neural Networks](https://mlsanity.com/paper/1806.08734/) (2018)
- [Group Equivariant Convolutional Networks](https://mlsanity.com/paper/1602.07576/) (2016)
- [A Comprehensive Survey on Transfer Learning](https://mlsanity.com/paper/1911.02685/) (2019)
- [Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPR](https://mlsanity.com/paper/1711.00399/) (2017)
- [A Generalist Agent](https://mlsanity.com/paper/2205.06175/) (2022)
- [Counterfactual Fairness](https://mlsanity.com/paper/1703.06856/) (2017)
- [Generalizing to Unseen Domains: A Survey on Domain Generalization](https://mlsanity.com/paper/2103.03097/) (2021)
- [Domain Generalization: A Survey](https://mlsanity.com/paper/2103.02503/) (2021)
- [Sim-to-Real Transfer of Robotic Control with Dynamics Randomization](https://mlsanity.com/paper/1710.06537/) (2017)
- [Zero-Shot Learning -- A Comprehensive Evaluation of the Good, the Bad and the Ugly](https://mlsanity.com/paper/1707.00600/) (2017)
- [Towards Out-Of-Distribution Generalization: A Survey](https://mlsanity.com/paper/2108.13624/) (2021)
- [Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Task](https://mlsanity.com/paper/2210.13382/) (2022)
- [A Survey of Unsupervised Deep Domain Adaptation](https://mlsanity.com/paper/1812.02849/) (2018)
- [Causal Reasoning and Large Language Models: Opening a New Frontier for Causality](https://mlsanity.com/paper/2305.00050/) (2023)
- [In Search of the Real Inductive Bias: On the Role of Implicit Regularization in Deep Learning](https://mlsanity.com/paper/1412.6614/) (2014)
- [Language Models Represent Space and Time](https://mlsanity.com/paper/2310.02207/) (2023)
- [A Brief Review of Domain Adaptation](https://mlsanity.com/paper/2010.03978/) (2020)
- [Inductive Biases for Deep Learning of Higher-Level Cognition](https://mlsanity.com/paper/2011.15091/) (2020)
- [D'ya like DAGs? A Survey on Structure Learning and Causal Discovery](https://mlsanity.com/paper/2103.02582/) (2021)
- [Why do deep convolutional networks generalize so poorly to small image transformations?](https://mlsanity.com/paper/1805.12177/) (2018)
- [Causality matters in medical imaging](https://mlsanity.com/paper/1912.08142/) (2019)
- [Maximum Entropy RL (Provably) Solves Some Robust RL Problems](https://mlsanity.com/paper/2103.06257/) (2021)
- [A Survey of Zero-shot Generalisation in Deep Reinforcement Learning](https://mlsanity.com/paper/2111.09794/) (2021)
- [Causal Parrots: Large Language Models May Talk Causality But Are Not Causal](https://mlsanity.com/paper/2308.13067/) (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)

## Built on by (most cited first, 30 of 81)

- [Mechanistic Interpretability for AI Safety -- A Review](https://mlsanity.com/paper/2404.14082/) (2024)
- [The Platonic Representation Hypothesis](https://mlsanity.com/paper/2405.07987/) (2024)
- [AI Agents vs. Agentic AI: A Conceptual Taxonomy, Applications and Challenges](https://mlsanity.com/paper/2505.10468/) (2025)
- [Making Large Language Models into World Models with Precondition and Effect Knowledge](https://mlsanity.com/paper/2409.12278/) (2024)
- [Agentic AI Needs a Systems Theory](https://mlsanity.com/paper/2503.00237/) (2025)
- [A Survey on Large Language Models for Automated Planning](https://mlsanity.com/paper/2502.12435/) (2025)
- [General agents contain world models](https://mlsanity.com/paper/2506.01622/) (2025)
- [Identifiable Exchangeable Mechanisms for Causal Structure and Representation Learning](https://mlsanity.com/paper/2406.14302/) (2024)
- [A Step Toward World Models: A Survey on Robotic Manipulation](https://mlsanity.com/paper/2511.02097/) (2025)
- [CLEAR: Can Language Models Really Understand Causal Graphs?](https://mlsanity.com/paper/2406.16605/) (2024)
- [Three Dogmas of Reinforcement Learning](https://mlsanity.com/paper/2407.10583/) (2024)
- [Towards Interpretable Deep Generative Models via Causal Representation Learning](https://mlsanity.com/paper/2504.11609/) (2025)
- [How Causal Abstraction Underpins Computational Explanation](https://mlsanity.com/paper/2508.11214/) (2025)
- [SPARTAN: A Sparse Transformer World Model Attending to What Matters](https://mlsanity.com/paper/2411.06890/) (2024)
- [Language Agents Meet Causality -- Bridging LLMs and Causal World Models](https://mlsanity.com/paper/2410.19923/) (2024)
- [When and How Does CLIP Enable Domain and Compositional Generalization?](https://mlsanity.com/paper/2502.09507/) (2025)
- [When Do Neural Networks Learn World Models?](https://mlsanity.com/paper/2502.09297/) (2025)
- [Measuring Goal-Directedness](https://mlsanity.com/paper/2412.04758/) (2024)
- [Collaborate, Deliberate, Evaluate: How LLM Alignment Affects Coordinated Multi-Agent Outcomes](https://mlsanity.com/paper/2509.05882/) (2025)
- [Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models](https://mlsanity.com/paper/2608.09696/) (2026)
- [A Mathematical Philosophy of Explanations in Mechanistic Interpretability -- The Strange Science Part I.i](https://mlsanity.com/paper/2505.00808/) (2025)
- [Linear Spatial World Models Emerge in Large Language Models](https://mlsanity.com/paper/2506.02996/) (2025)
- [Preference Learning for AI Alignment: a Causal Perspective](https://mlsanity.com/paper/2506.05967/) (2025)
- [Overcoming Statistical Bias in Action-Controllable World Models](https://mlsanity.com/paper/2608.04653/) (2026)
- [Causality from Bottom to Top: A Survey](https://mlsanity.com/paper/2403.11219/) (2024)
- [Are Biological Systems More Intelligent Than Artificial Intelligence?](https://mlsanity.com/paper/2405.02325/) (2024)
- [Towards Empowerment Gain through Causal Structure Learning in Model-Based RL](https://mlsanity.com/paper/2502.10077/) (2025)
- [Enhancing LLM Agent Safety via Causal Influence Prompting](https://mlsanity.com/paper/2507.00979/) (2025)
- [CausalMan: A physics-based simulator for large-scale causality](https://mlsanity.com/paper/2502.12707/) (2025)
- [Curious Causality-Seeking Agents Learn Meta Causal World](https://mlsanity.com/paper/2506.23068/) (2025)

## Abstract (arXiv)

It has long been hypothesised that causal reasoning plays a fundamental role in robust and general intelligence. However, it is not known if agents must learn causal models in order to generalise to new domains, or if other inductive biases are sufficient. We answer this question, showing that any agent capable of satisfying a regret bound under a large set of distributional shifts must have learned an approximate causal model of the data generating process, which converges to the true causal model for optimal agents. We discuss the implications of this result for several research areas including transfer learning and causal inference.