# Relational Learning as World Modeling

arXiv: https://arxiv.org/abs/2610.16763 · HTML: https://mlsanity.com/paper/2610.16763/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in World models for language agents, one of 11 directions in World models.
- Builds on 29 of its 41 references that are in the map.
- First posted on arXiv 12 Oct 2026.

## 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)

- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?](https://mlsanity.com/paper/2202.12837/) (2022)
- [Learning Latent Dynamics for Planning from Pixels](https://mlsanity.com/paper/1811.04551/) (2018)
- [Recurrent World Models Facilitate Policy Evolution](https://mlsanity.com/paper/1809.01999/) (2018)
- [Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models](https://mlsanity.com/paper/1805.12114/) (2018)
- [Transformers Can Do Bayesian Inference](https://mlsanity.com/paper/2112.10510/) (2021)
- [Understanding World or Predicting Future? A Comprehensive Survey of World Models](https://mlsanity.com/paper/2411.14499/) (2024)
- [Context-aware Dynamics Model for Generalization in Model-Based Reinforcement Learning](https://mlsanity.com/paper/2005.06800/) (2020)
- [Objective Mismatch in Model-based Reinforcement Learning](https://mlsanity.com/paper/2002.04523/) (2020)
- [RelBench: A Benchmark for Deep Learning on Relational Databases](https://mlsanity.com/paper/2407.20060/) (2024)
- [The Value Equivalence Principle for Model-Based Reinforcement Learning](https://mlsanity.com/paper/2011.03506/) (2020)
- [Griffin: Towards a Graph-Centric Relational Database Foundation Model](https://mlsanity.com/paper/2505.05568/) (2025)
- [Relational Transformer: Toward Zero-Shot Foundation Models for Relational Data](https://mlsanity.com/paper/2510.06377/) (2025)
- [PluRel: Synthetic Data unlocks Scaling Laws for Relational Foundation Models](https://mlsanity.com/paper/2602.04029/) (2026)
- [KumoRFM-2: Scaling Foundation Models for Relational Learning](https://mlsanity.com/paper/2604.12596/) (2026)
- [Automated Discovery of Business Process Simulation Models from Event Logs](https://mlsanity.com/paper/1910.05404/) (2019)
- [From system models to class models: An in-context learning paradigm](https://mlsanity.com/paper/2308.13380/) (2023)
- [Relational In-Context Learning via Synthetic Pre-training with Structural Prior](https://mlsanity.com/paper/2603.03805/) (2026)
- [Learning Accurate Business Process Simulation Models from Event Logs via Automated Process Discovery and Deep Learning](https://mlsanity.com/paper/2103.11944/) (2021)
- [World of Workflows: A Benchmark for Bringing World Models to Enterprise Systems](https://mlsanity.com/paper/2601.22130/) (2026)
- [Doubling Your Data in Minutes: Ultra-fast Tabular Data Generation via LLM-Induced Dependency Graphs](https://mlsanity.com/paper/2507.19334/) (2025)
- [Not All Features Deserve Attention: Graph-Guided Dependency Learning for Tabular Data Generation with Language Models](https://mlsanity.com/paper/2507.18504/) (2025)
- [Enhanced Transformer architecture for in-context learning of dynamical systems](https://mlsanity.com/paper/2410.03291/) (2024)
- [Position: Foundation Models for Tabular Data within Systemic Contexts Need Grounding](https://mlsanity.com/paper/2505.19825/) (2025)
- [Consolidating Rewarded Perturbations for LLM Post-Training](https://mlsanity.com/paper/2605.31494/) (2026)
- [Do Enterprise Systems Need Learned World Models? The Importance of Context to Infer Dynamics](https://mlsanity.com/paper/2605.12178/) (2026)
- [SAGE: Sparse Adaptive Guidance for Dependency-Aware Tabular Data Generation](https://mlsanity.com/paper/2604.24368/) (2026)
- [Active Tabular Augmentation via Policy-Guided Diffusion Inpainting](https://mlsanity.com/paper/2605.10315/) (2026)
- [Statistically Indistinguishable, Operationally Distinct: A Formal Barrier for Tabular Foundation Models](https://mlsanity.com/paper/2606.29091/) (2026)

## Abstract (arXiv)

Relational learning typically predicts from a database state, but decision making asks a different question: how will that state change under an action? In operational systems, the answer depends on system-specific dynamics that may not be visible in the database itself. We view each such system as a relational "world" and ask whether a model can infer how it behaves from observed executions. We introduce TabWM (Tabular World Model) and WorldRel, a generator of executable relational worlds for pretraining. Given executions from an unseen world, TabWM uses them as context to predict the sparse structured edits caused by a new action without parameter updates. Across 512 held-out worlds, complete-edit F1 rises from 0.016 with no observed executions to 0.685 with 64, where a correct edit must match its operation, relational location, and value. Because these predictions are explicit relational edits, they can be applied recursively to imagine candidate futures and compare actions before they are taken. Broader search over these predicted futures improves the realized return of selected action sequences. Together, these results suggest that relational dynamics can be learned in context, broadening relational learning from modeling system state to modeling how that state changes under action.