Richer Representations for Neural Algorithmic Reasoning via Auxiliary Reconstruction

Jiafu Huang; Chao Peng; Chenyang Xu; Zhengfeng Yang; Kecheng Cai; Chenhao Zhang; Yi Wang; Yiwei Gong

AAAI 2026technical0 citations

Richer Representations for Neural Algorithmic Reasoning via Auxiliary Reconstruction

Jiafu Huang, Chao Peng, Chenyang Xu, Zhengfeng Yang, Kecheng Cai, Chenhao Zhang, Yi Wang, Yiwei Gong

Abstract

Neural algorithmic reasoning has recently emerged as a popular research direction. It aims to train neural networks to mimic the step-by-step behavior of classical rule-based algorithms. More specifically, the execution of such algorithms can be abstracted as a sequence of states, where each state represents the intermediate outcome after an execution step. The training objective is to generate state sequences that replicate the underlying algorithmic process. A common framework for this task adopts an ``encoder-processor-decoder

BibTeX

@inproceedings{aaai2026_richerrepresenta,
  title = {Richer Representations for Neural Algorithmic Reasoning via Auxiliary Reconstruction},
  author = {Jiafu Huang and Chao Peng and Chenyang Xu and Zhengfeng Yang and Kecheng Cai and Chenhao Zhang and Yi Wang and Yiwei Gong and Wanqin Zhou and Irene Zheng},
  booktitle = {AAAI 2026},
  year = {2026}
}