Learning Implicit Causal World Models from Multi-Agent Demonstrations

arXiv cs.LG Papers
multi-agent world-models causal-learning implicit-models demonstrations

Summary

This paper presents a method for learning implicit causal world models from multi-agent demonstrations, enabling agents to infer causal structures from observed behavior.

arXiv:2607.26336v1 Announce Type: new Abstract: In model-based reinforcement learning, world models exist as internal simulators, but their training often conflates statistical correlations with causal mechanisms. This problem is exacerbated in multi-agent systems where physical transitions are intertwined with strategic agent intents, causing world models to fail under distribution shift. We introduce Implicit Causal World Models to recover environmental dynamics from offline demonstrations without requiring pre-defined causal graphs. By incorporating policy variance, we render world models discoverable via the sequential backdoor condition. Evaluations across coordination tasks (Two-Door, Navigation, and Giveway) demonstrate that these models provide interpretable causal representations under both full and partial observability, with model accuracy scaling directly with interventional strength.
Original Article
View Cached Full Text

Cached at: 07/30/26, 09:57 AM 

# Learning Implicit Causal World Models from Multi-Agent Demonstrations
Source: [https://arxiv.org/abs/2607.26336](https://arxiv.org/abs/2607.26336)
Bibliographic Tools

## Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Code, Data, Media

## Code, Data and Media Associated with this Article

Demos

## Demos

Related Papers

## Recommenders and Search Tools

IArxiv recommender toggle

About arXivLabs

## arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website\.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy\. arXiv is committed to these values and only works with partners that adhere to them\.

Have an idea for a project that will add value for arXiv's community?[**Learn more about arXivLabs**](https://info.arxiv.org/labs/index.html)\.

Similar Articles

Causal Discovery in the Era of Agents

Hugging Face Daily Papers

This paper argues that language model agents should assist causal discovery workflows by providing contextual support and explanations rather than generating causal conclusions, and introduces causal-learn+ platform to demonstrate this principle.

Learning Safe Agent Behaviour from Human Preferences and Justifications via World Models

arXiv cs.AI

This paper introduces DROPJ, a human-centred method for safely training and deploying agent policies by learning a world model from real-world trajectories, then eliciting human preferences with justifications to train a reward model for model predictive control. Experiments show that using human-generated simulated trajectories and justifications improves safety and reduces computational cost.

CausalDS: Benchmarking Causal Reasoning in Data-Science Agents

arXiv cs.AI

Introduces CausalDS, a benchmark for evaluating causal reasoning in LLM-based data science agents, using synthetic structural causal models and natural language stories to test associational, interventional, and counterfactual reasoning along with tool use and abstention.

Learning policy representations in multiagent systems

OpenAI Blog

OpenAI researchers propose a general framework for learning representations of agent policies in multiagent systems using minimal interaction data, casting the problem as representation learning with applications to competitive control and cooperative communication environments.