# CASSANDRA: Programmatic and Probabilistic Learning and Inference for Stochastic World Modeling

arXiv: https://arxiv.org/abs/2601.18620 · HTML: https://mlsanity.com/paper/2601.18620/

## Key facts

- Cited by 1 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 5 of its 26 references that are in the map.
- First posted on arXiv 26 Jan 2026.

## Placed in

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

## Builds on (most cited first, 5 of 5)

- [Benchmarking the Spectrum of Agent Capabilities](https://mlsanity.com/paper/2109.06780/) (2021)
- [On the Measure of Intelligence](https://mlsanity.com/paper/1911.01547/) (2019)
- [LMPriors: Pre-Trained Language Models as Task-Specific Priors](https://mlsanity.com/paper/2210.12530/) (2022)
- [Efficient Causal Graph Discovery Using Large Language Models](https://mlsanity.com/paper/2402.01207/) (2024)
- [Causal Inference with Large Language Model: A Survey](https://mlsanity.com/paper/2409.09822/) (2024)

## Built on by (most cited first, 1 of 1)

- [Learning POMDP World Models from Observations with Language-Model Priors](https://mlsanity.com/paper/2605.13740/) (2026)

## Abstract (arXiv)

Building world models is essential for planning in real-world domains such as businesses. Since such domains have rich semantics, we can leverage world knowledge to effectively model complex action effects and causal relationships from limited data. In this work, we propose CASSANDRA, a neurosymbolic world modeling approach that leverages an LLM as a knowledge prior to construct lightweight transition models for planning. CASSANDRA integrates two components: (1) LLM-synthesized code to model deterministic features, and (2) LLM-guided structure learning of a probabilistic graphical model to capture causal relationships among stochastic variables. We evaluate CASSANDRA in (i) a small-scale coffee-shop simulator and (ii) a complex theme park business simulator, where we demonstrate significant improvements in transition prediction and planning over baselines.