CASSANDRA: Programmatic and Probabilistic Learning and Inference for Stochastic World Modeling
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910001105207296 |
|---|---|
| author | Lymperopoulos, Panagiotis Rajasekharan, Abhiramon Berlot-Attwell, Ian Aroca-Ouellette, Stéphane Suleman, Kaheer |
| author_facet | Lymperopoulos, Panagiotis Rajasekharan, Abhiramon Berlot-Attwell, Ian Aroca-Ouellette, Stéphane Suleman, Kaheer |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_18620 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | CASSANDRA: Programmatic and Probabilistic Learning and Inference for Stochastic World Modeling Lymperopoulos, Panagiotis Rajasekharan, Abhiramon Berlot-Attwell, Ian Aroca-Ouellette, Stéphane Suleman, Kaheer Machine Learning I.2.6 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. |
| title | CASSANDRA: Programmatic and Probabilistic Learning and Inference for Stochastic World Modeling |
| topic | Machine Learning I.2.6 |
| url | https://arxiv.org/abs/2601.18620 |