# Operationally Guided Placement-Aware Learning for Industrial Online 3D Bin Packing

arXiv: https://arxiv.org/abs/2607.28257 · HTML: https://mlsanity.com/paper/2607.28257/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 27 references that are in the map.
- First posted on arXiv 30 Jul 2026.

## Builds on (most cited first, 8 of 8)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Revisiting Deep Learning Models for Tabular Data](https://mlsanity.com/paper/2106.11959/) (2021)
- [Solving a New 3D Bin Packing Problem with Deep Reinforcement Learning Method](https://mlsanity.com/paper/1708.05930/) (2017)
- [A Large Recurrent Action Model: xLSTM enables Fast Inference for Robotics Tasks](https://mlsanity.com/paper/2410.22391/) (2024)
- [Attend2Pack: Bin Packing through Deep Reinforcement Learning with Attention](https://mlsanity.com/paper/2107.04333/) (2021)
- [Deliberate Planning of 3D Bin Packing on Packing Configuration Trees](https://mlsanity.com/paper/2504.04421/) (2025)
- [ASAP: Exploiting the Satisficing Generalization Edge in Neural Combinatorial Optimization](https://mlsanity.com/paper/2501.17377/) (2025)
- [GENPACK: KPI-Guided Multi-Criteria Genetic Algorithm for Industrial 3D Bin Packing](https://mlsanity.com/paper/2601.11325/) (2026)

## Abstract (arXiv)

The online three-dimensional bin packing problem (3D-BPP) is a longstanding challenge in logistics and industrial palletizing. Recent learning-based methods use a learned policy to select among feasible candidate placements. Performance depends on the candidate generator and representation, especially in industrial settings where packings must be space-efficient, stable, compact, and balanced. However, prior work has mainly optimized the policy, while candidate generation and representation remain largely geometry-driven. We address this gap with OPAL, an operationally guided placement-aware learning framework for industrial online 3D-BPP which combines an Operationally Guided Empty-Maximal-Space generator (OG-EMS), an operational representation for each candidate placement, and a masked ranking policy trained with proximal policy optimization. OG-EMS evaluates multiple anchors within each free-space region and prioritizes low, well-supported, compact, and spatially diverse placements. An xLSTM-based Placement Encoder models dependencies among geometric and operational candidate attributes, while a lightweight recurrent core combines the resulting embeddings with the current item and pallet state to rank feasible actions. On the BED-BPP benchmark, OPAL achieves a mean space utilization of 0.49, with improvements of 15.1% from operationally guided candidate generation and 6.3% from learned ranking, while maintaining robust inference-time performance.