Learning to Unscramble: Simplifying Symbolic Expressions via Self-Supervised Oracle Trajectories

Fuente: arXiv
Saved in:
Bibliographic Details
Main Author: Shih, David
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917400939593728
author Shih, David
author_facet Shih, David
contents We present a new self-supervised machine learning approach for symbolic simplification of complex mathematical expressions. Training data is generated by scrambling simple expressions and recording the inverse operations, creating oracle trajectories that provide both goal states and explicit paths to reach them. A permutation-equivariant, transformer-based policy network is then trained on this data step-wise to predict the oracle action given the input expression. We demonstrate this approach on two problems in high-energy physics: dilogarithm reduction and spinor-helicity scattering amplitude simplification. In both cases, our trained policy network achieves near perfect solve rates across a wide range of difficulty levels, substantially outperforming prior approaches based on reinforcement learning and end-to-end regression. When combined with contrastive grouping and beam search, our model achieves a 100\% full simplification rate on a representative selection of 5-point gluon tree-level amplitudes in Yang-Mills theory, including expressions with over 200 initial terms.
format Preprint
id arxiv_https___arxiv_org_abs_2603_11164
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Learning to Unscramble: Simplifying Symbolic Expressions via Self-Supervised Oracle Trajectories
Shih, David
High Energy Physics - Theory
Machine Learning
Symbolic Computation
High Energy Physics - Phenomenology
We present a new self-supervised machine learning approach for symbolic simplification of complex mathematical expressions. Training data is generated by scrambling simple expressions and recording the inverse operations, creating oracle trajectories that provide both goal states and explicit paths to reach them. A permutation-equivariant, transformer-based policy network is then trained on this data step-wise to predict the oracle action given the input expression. We demonstrate this approach on two problems in high-energy physics: dilogarithm reduction and spinor-helicity scattering amplitude simplification. In both cases, our trained policy network achieves near perfect solve rates across a wide range of difficulty levels, substantially outperforming prior approaches based on reinforcement learning and end-to-end regression. When combined with contrastive grouping and beam search, our model achieves a 100\% full simplification rate on a representative selection of 5-point gluon tree-level amplitudes in Yang-Mills theory, including expressions with over 200 initial terms.
title Learning to Unscramble: Simplifying Symbolic Expressions via Self-Supervised Oracle Trajectories
topic High Energy Physics - Theory
Machine Learning
Symbolic Computation
High Energy Physics - Phenomenology
url https://arxiv.org/abs/2603.11164