# From monoliths to modules: Decomposing transducers for efficient world modelling

arXiv: https://arxiv.org/abs/2512.02193 · HTML: https://mlsanity.com/paper/2512.02193/

## Key facts

- Cited by 4 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 29 of its 71 references that are in the map.
- First posted on arXiv 1 Dec 2025.

## Placed in

- World models / [World models for language agents](https://mlsanity.com/wm/world-models-for-language-agents/)

## Builds on (most cited first, 29 of 29)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Dream to Control: Learning Behaviors by Latent Imagination](https://mlsanity.com/paper/1912.01603/) (2019)
- [Dota 2 with Large Scale Deep Reinforcement Learning](https://mlsanity.com/paper/1912.06680/) (2019)
- [Genie: Generative Interactive Environments](https://mlsanity.com/paper/2402.15391/) (2024)
- [Learning Complex Dexterous Manipulation with Deep Reinforcement Learning and Demonstrations](https://mlsanity.com/paper/1709.10087/) (2017)
- [TD-MPC2: Scalable, Robust World Models for Continuous Control](https://mlsanity.com/paper/2310.16828/) (2023)
- [Detecting causal associations in large nonlinear time series datasets](https://mlsanity.com/paper/1702.07007/) (2017)
- [The Complexity of Decentralized Control of Markov Decision Processes](https://mlsanity.com/paper/1301.3836/) (2013)
- [Contextual Markov Decision Processes](https://mlsanity.com/paper/1502.02259/) (2015)
- [Recurrent Independent Mechanisms](https://mlsanity.com/paper/1909.10893/) (2019)
- [Understanding World or Predicting Future? A Comprehensive Survey of World Models](https://mlsanity.com/paper/2411.14499/) (2024)
- [Training Agents Inside of Scalable World Models](https://mlsanity.com/paper/2509.24527/) (2025)
- [Towards Guaranteed Safe AI: A Framework for Ensuring Robust and Reliable AI Systems](https://mlsanity.com/paper/2405.06624/) (2024)
- [Transformers represent belief state geometry in their residual stream](https://mlsanity.com/paper/2405.15943/) (2024)
- [A Survey on Interpretable Reinforcement Learning](https://mlsanity.com/paper/2112.13112/) (2021)
- [Connecting the Dots in Trustworthy Artificial Intelligence: From AI Principles, Ethics, and Key Requirements to Responsible AI Systems and Regulation](https://mlsanity.com/paper/2305.02231/) (2023)
- [SOLD: Slot Object-Centric Latent Dynamics Models for Relational Manipulation Learning from Pixels](https://mlsanity.com/paper/2410.08822/) (2024)
- [Learning World Models with Identifiable Factorization](https://mlsanity.com/paper/2306.06561/) (2023)
- [Toward Compositional Generalization in Object-Oriented World Modeling](https://mlsanity.com/paper/2204.13661/) (2022)
- [International Scientific Report on the Safety of Advanced AI (Interim Report)](https://mlsanity.com/paper/2412.05282/) (2024)
- [Learning Dynamic Attribute-factored World Models for Efficient Multi-object Reinforcement Learning](https://mlsanity.com/paper/2307.09205/) (2023)
- [Constrained belief updates explain geometric structures in transformer representations](https://mlsanity.com/paper/2502.01954/) (2025)
- [Inferring Probabilistic Reward Machines from Non-Markovian Reward Processes for Reinforcement Learning](https://mlsanity.com/paper/2107.04633/) (2021)
- [Nearly Maximally Predictive Features and Their Dimensions](https://mlsanity.com/paper/1702.08565/) (2017)
- [Planning and Learning with Stochastic Action Sets](https://mlsanity.com/paper/1805.02363/) (2018)
- [Shannon Entropy Rate of Hidden Markov Processes](https://mlsanity.com/paper/2008.12886/) (2020)
- [Information Thermodynamics of Agents: The Work Capacity of Channels with Memory](https://mlsanity.com/paper/2504.06209/) (2025)
- [From Pixels to Factors: Learning Independently Controllable State Variables for Reinforcement Learning](https://mlsanity.com/paper/2510.02484/) (2025)
- [Decomposing Interventional Causality into Synergistic, Redundant, and Unique Components](https://mlsanity.com/paper/2501.11447/) (2025)

## Built on by (most cited first, 4 of 4)

- [Transformers learn factored representations](https://mlsanity.com/paper/2602.02385/) (2026)
- [Compositional Behavioral Semantics for State Abstraction in Reinforcement Learning](https://mlsanity.com/paper/2606.25357/) (2026)
- [World models of environment, agent and joint agent-environment systems](https://mlsanity.com/paper/2608.20401/) (2026)
- [Approximate Homomorphisms and Convergent Representations in Transducers](https://mlsanity.com/paper/2608.20428/) (2026)

## Abstract (arXiv)

World models have been recently proposed as sandbox environments in which AI agents can be trained and evaluated before deployment. While realistic world models often have high computational demands, this can often be alleviated by exploiting the fact that real-world scenarios tend to involve subcomponents that interact in a modular manner. In this paper, we explore this idea by developing a framework for decomposing complex world models represented by transducers, a class of models generalising POMDPs. Whereas the composition of transducers is well understood, our results clarify how to invert this process by deriving sub-transducers operating on distinct input-output subspaces, enabling parallelizable and interpretable alternatives to monolithic world modelling that can support distributed inference. Overall, these results lay groundwork for bridging the computational efficiency required for real-world inference and the structural transparency demanded by AI safety.