mlsanityData to 14 Oct 2026

Relational Learning as World Modeling

arXiv 2610.16763 ↗First posted 12 Oct 2026cs.LG cs.AIcited by 0

On the map: World models → World models for language agents

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.

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.

Builds on

29 of 41 references.

Closest ancestors · 3

Same direction, newest first

  1. 2026Do Enterprise Systems Need Learned World Models? The Importance of Context to Infer Dynamics12 May
  2. 2026World of Workflows: A Benchmark for Bringing World Models to Enterprise Systems29 Jan
  3. 2024Understanding World or Predicting Future? A Comprehensive Survey of World Models21 Nov

Other references · 26

  1. 2020End-to-End Object Detection with Transformerscited by 7,414
  2. 2022Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?cited by 1,434
  3. 2018Learning Latent Dynamics for Planning from Pixelscited by 1,264
  4. 2018Recurrent World Models Facilitate Policy Evolutioncited by 785
  5. 2018Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Modelscited by 774
  6. 2021Transformers Can Do Bayesian Inferencecited by 360
  7. 2020Context-aware Dynamics Model for Generalization in Model-Based Reinforcement Learningcited by 98
  8. 2020Objective Mismatch in Model-based Reinforcement Learningcited by 96
  9. 2024RelBench: A Benchmark for Deep Learning on Relational Databasescited by 96
  10. 2020The Value Equivalence Principle for Model-Based Reinforcement Learningcited by 94
  11. 2025Griffin: Towards a Graph-Centric Relational Database Foundation Modelcited by 47
  12. 2025Relational Transformer: Toward Zero-Shot Foundation Models for Relational Datacited by 39
14 more
  1. 2026PluRel: Synthetic Data unlocks Scaling Laws for Relational Foundation Modelscited by 19
  2. 2026KumoRFM-2: Scaling Foundation Models for Relational Learningcited by 19
  3. 2019Automated Discovery of Business Process Simulation Models from Event Logscited by 17
  4. 2023From system models to class models: An in-context learning paradigmcited by 16
  5. 2026Relational In-Context Learning via Synthetic Pre-training with Structural Priorcited by 14
  6. 2021Learning Accurate Business Process Simulation Models from Event Logs via Automated Process Discovery and Deep Learningcited by 11
  7. 2025Doubling Your Data in Minutes: Ultra-fast Tabular Data Generation via LLM-Induced Dependency Graphscited by 9
  8. 2025Not All Features Deserve Attention: Graph-Guided Dependency Learning for Tabular Data Generation with Language Modelscited by 8
  9. 2024Enhanced Transformer architecture for in-context learning of dynamical systemscited by 7
  10. 2025Position: Foundation Models for Tabular Data within Systemic Contexts Need Groundingcited by 6
  11. 2026Consolidating Rewarded Perturbations for LLM Post-Trainingcited by 3
  12. 2026SAGE: Sparse Adaptive Guidance for Dependency-Aware Tabular Data Generationcited by 1
  13. 2026Active Tabular Augmentation via Policy-Guided Diffusion Inpaintingcited by 1
  14. 2026Statistically Indistinguishable, Operationally Distinct: A Formal Barrier for Tabular Foundation Modelscited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Making Large Language Models into World Models with Precondition and Effect Knowledge
  2. 2026Agent-Editing World Model: Rethinking World Modeling for LLM Agents
  3. 2026Beyond Next-Observation Prediction: Agent-Authored World Modeling for Sequential Decision Making
  4. 2025R-WoM: Retrieval-augmented World Model For Computer-use Agents
  5. 2026Long-Horizon Textual World Modeling through Structured Reasoning
  6. 2026How do World Models and Policies Compose in LLM Agents? A Joint Spectral and Behavioral Account
  7. 2026Towards a Belief-Based World Model for LLM Agents
  8. 2026RoleWorld: Knowledge Transfer in World Modeling with Functional Role Abstractions