Saved in:
Bibliographic Details
Main Authors: Qin, Tian, Chen, Yuhan, Wang, Zhiwei, Xu, Zhi-Qin John
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2509.23178
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of Contents:
  • Transformers are able to perform reasoning tasks, however the intrinsic mechanism remains widely open. In this paper we propose a set of information propagation rules based on Transformers and utilize symbolic reasoning tasks to theoretically analyze the limit reasoning steps. We show that the limit number of reasoning steps is between $O(3^{L-1})$ and $O(2^{L-1})$ for a model with $L$ attention layers in a single-pass.