# RESCHED: Rethinking Flexible Job Shop Scheduling from a Transformer-based Architecture with Simplified States

arXiv: https://arxiv.org/abs/2603.07020 · HTML: https://mlsanity.com/paper/2603.07020/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in RL for energy, networks and operations, one of 15 directions in Deep reinforcement learning methods.
- First posted on arXiv 7 Mar 2026.

## Placed in

- Deep reinforcement learning methods / [RL for energy, networks and operations](https://mlsanity.com/deeprl/rl-for-energy-networks-and-operations/)

## Built on by (most cited first, 2 of 2)

- [DGA2D: Directed Graph-Guided Automated Algorithm Design with Large Language Models](https://mlsanity.com/paper/2608.00700/) (2026)
- [Transformer-Based Flow Shop Scheduling Using MILP-Generated Training Data](https://mlsanity.com/paper/2608.29690/) (2026)

## Abstract (arXiv)

Neural approaches to the Flexible Job Shop Scheduling Problem (FJSP), particularly those based on deep reinforcement learning (DRL), have gained growing attention in recent years. However, existing methods rely on complex feature-engineered state representations (i.e., often requiring more than 20 handcrafted features) and graph-biased neural architectures. To reduce modeling complexity and advance a more generalizable framework for FJSP, we introduce textscReSched, a minimalist DRL framework that rethinks both the scheduling formulation and model design. First, by revisiting the Markov Decision Process (MDP) formulation of FJSP, we condense the state space to just four essential features, eliminating historical dependencies through a subproblem-based perspective. Second, we employ Transformer blocks with dot-product attention, augmented by three lightweight but effective architectural modifications tailored to scheduling tasks. Extensive experiments show that textscReSched outperforms classical dispatching rules and state-of-the-art DRL methods on FJSP. Moreover, textscReSched also generalizes well to the Job Shop Scheduling Problem (JSSP) and the Flexible Flow Shop Scheduling Problem (FFSP), achieving competitive performance against neural baselines specifically designed for these variants.