Symbolic World Models for Procedural Reasoning

Abstract

Procedural domains — code execution, theorem proving, configuration management — admit world models whose state is naturally symbolic rather than continuous. We train a symbolic world model on 26k procedural trajectories drawn from the 70k-env pool, show that it outperforms neural baselines by 19-28% on out-of-distribution procedural tasks, and demonstrate that the model's symbolic state allows partial-execution reasoning that the neural baselines structurally cannot support.

Index metadata

Cell

bessel-04

Compute

73 H100-days

Status

Open release

Code

github.com/alphabell-labs/ab-symbolic

DOI

10.48550/arXiv.2512.04918

arXiv

arXiv:2512.04918

What this paper is part of

This index entry is part of the World models research axis. The producing cell — bessel-04 — collaborates with adjacent cells listed in the cell directory. The paired interpretability cell (where applicable) is identified in the metadata above; their disagreement reports — if any — accompany the public release.

How to read this

If you want to use the result: the code (where available) is at https://github.com/alphabell-labs/ab-symbolic; the dataset is at https://huggingface.co/datasets/alphabell/symbolic-2025 when one is released. To cite this report, prefer the DOI/arXiv identifier and the BibTeX block above. To discuss this with the producing cell, contact the lab with the index entry slug symbolic-world-models-procedural.

Limitations

Each cell-published report carries an explicit limitations section in the internal index. We do not paraphrase it here. Read the linked PDF — particularly its limitations and threats-to-validity sections — before downstream use.