Neural Algorithmic Reasoning

Follow this topic Ask about this topic

Momentum

2 papers in the last four weeks, with none the four weeks before. 0.0% of all new papers.

Jul 13Week of Sep 28

Latest papers 18

All topics

Executing Causal Structure Learning with Linear-Attention Transformers
Oct 7, 2026Amartya Roy, Sayar KarmakarNeural Algorithmic Reasoning Causal Structure Learning
School of Interdisciplinary Research Indian Institute of Technology Delhi · University of Florida
The Dichotomy Between Pattern Recognition and Step-by-Step Reasoning
Oct 6, 2026Amrut Nadgir, Pratik Chaudhari, Vijay BalasubramanianLLM Reasoning Efficient Language Model Reasoning
University of Pennsylvania
Algorithmic Scratchpads and Curriculum Staging for Arithmetic Reasoning in Tiny Transformers
Oct 6, 2026Sourabh KasliwalNumerical Reasoning in Language Models Neural Algorithmic Reasoning
Neural Algorithmic Reasoning for Graph Saddle Point Problems
Oct 5, 2026Samantha Chen, Jesse He, Coleman Clougherty +2Primal-Dual Optimization Graph Neural Networks
Oberlin College · Department of Computer Science, Oberlin College · University of California, San Diego +2
What Limits Recursive Reasoning Models: Optimization, Architecture and Test-Time Scaling
Sep 30, 2026Yuliana Shakhvalieva, Dmitrii Kharchev, Viacheslav Bezrukov +4Neural Algorithmic Reasoning Recurrent Transformers
RND NLP, DAIMLD, Russian Federation
Not All Thinking is Created Equal: Latent Reasoning Discovers a Recurrent Search Algorithm for Depth Generalization
Sep 28, 2026Huzi Cheng, Zhewei ZhangLLM Reasoning with Graphs LLM Interpretability
University of Minnesota · Independent Researcher
Graph Machine: Exploring Edge Mechanisms as an Inductive Bias
Aug 7, 2026Lintai HouGraph Structure Learning Neural Algorithmic Reasoning
Iter Labs
Measuring in-context algorithmic reasoning in language models against an exact Bayes-optimal standard
Aug 3, 2026Hector Zenil, Luan OzelimLLM Evaluation Bayesian Inference
Oxford Immune Algorithmics, Oxford University Innovation & London Institute for Healthcare Engineering, U.K · Department of Biomedical Computing, School of Biomedical Engineering and Imaging Sciences & King’s Institute for AI, King’s College London, U.K
A Symbolic Neural CPU for Quantization-Simulated Writeback and Interpretable Program Execution
Jul 10, 2026Jose Luis Lima de Jesus SilvaNeural Algorithmic Reasoning Neural Network Interpretability
Federal University of Bahia, Department of Geophysics, Salvador, BA 40170-115, Brazil · Grupo de Estudos e Aplicação de Inteligência Artificial em Geofísica (GAIA), Federal University of Bahia, Salvador, BA 40170-115, Brazil
A Verifiable Search Is Not a Learnable Chain-of-Thought
Jun 20, 2026Harsh PatelInference-Time Search Memorization in Language Models
Independent Researcher
Efficiently Representing Algorithms With Chain-of-Thought Transformers
Jun 18, 2026Yanhong Li, Anej Svete, Ashish Sabharwal +1Transformer CoT Reasoning
Allen Institute for AI · ETH Zürich
Contrastive Neural Algorithmic Reasoning for Graph Coloring
Jun 2, 2026Thien Le, Tianyu Zhao, Melanie WeberGraph Neural Networks Graph Representation Learning
Harvard University SEAS · Harvard University T.H. Chan School of Public Health
Richer Representations for Neural Algorithmic Reasoning via Auxiliary Reconstruction
May 30, 2026Jiafu Huang, Chao Peng, Chenyang Xu +7Neural Algorithmic Reasoning State Representation Learning
Shanghai Key Laboratory of Trustworthy Computing, East China Normal University, China · Overseas Education College, Xiamen University, China · Dept. of Electrical and Electronic Engineering, The University of Melbourne, Australia
Neuro-symbolic Syntactic Parsing: Shaping a Neural Network with the CYK Algorithm
May 29, 2026Fabio Massimo Zanzotto, Federico Ranaldi, Giorgio SattaNeural Algorithmic Reasoning Recurrent Neural Networks
Human-centric ART, University of Rome Tor Vergata, Italy · DEI, University of Padua, Italy
Represented Is Not Computed: A Causal Test of Candidate Algorithmic Intermediates in a Transformer
May 21, 2026Ishita Darade, Sushrut ThoratNumerical Reasoning in Language Models Transformer Interpretability
MKSSS’s Cummins College of Engineering for Women, Pune 411052, India · Institute of Cognitive Science, Osnabrück University, Osnabrück 49069, Germany
Efficiently Learning Branching Networks for Multitask Algorithmic Reasoning
Nov 30, 2025Dongyue Li, Zhenshuo Zhang, Minxuan Duan +2Neural Algorithmic Reasoning Multi-Task Learning
†Northeastern University, Boston, Massachusetts · ‡University of Pennsylvania, Philadelphia, Pennsylvania
Tackling GNARLy Problems: Graph Neural Algorithmic Reasoning Reimagined through Reinforcement Learning
Sep 23, 2025Alex Schutz, Victor-Alexandru Darvariu, Efimia Panagiotaki +2Graph Neural Networks Reinforcement Learning
Oxford Robotics Institute, University of Oxford · Stateful Robotics
Scaling Online Complex Event Detection with Synthetic Supervision and Mamba-Based Neural Algorithmic Reasoning
Date pendingLiying Han, Gaofeng Dong, Xiaomin Ouyang +4Neural Algorithmic Reasoning Algorithmic Reasoning
Department of Electrical and Computer Engineering University of California, Los Angeles · Department of Computer Science and Engineering Hong Kong University of Science and Technology · U.S. Army DEVCOM Army Research Laboratory +1

Oct 7, 2026, cs.LGJ/K move · Enter open · S save

Executing Causal Structure Learning with Linear-Attention Transformers

Amartya Roy, Sayar Karmakar

School of Interdisciplinary Research Indian Institute of Technology Delhi · University of Florida

Neural Algorithmic Reasoning Causal Structure Learning

Open paper AskPDF arXiv

Transformers can execute algorithms on data given in their input. We ask whether they can do the same for causal discovery. We study a standard continuous method that repeatedly updates a candidate causal graph while enforcing acyclicity. We explicitly construct a fixed-weight transformer whose forward pass exactly reproduces one update of this method, so repeated blocks reproduce its optimization trajectory. The transformer carries the current graph and the algorithm's multiplier between updates. We show that retaining the multiplier is essential for exact execution, since different multiplier values can lead to different next updates. We also give conditions under which, within a fixed stage, the number of updates needed to reach a target accuracy can be computed in advance and rounding errors stay bounded as depth grows. Experiments show that the constructed block agrees with a reference update to floating-point precision, while arithmetic replay on synthetic data and seven published benchmark network topologies inherits the reference solver's successes and failures. This separates accurate algorithm execution from accurate causal recovery. In contrast, the ordinary attention models tested under our training budgets do not reliably execute the update or transfer to larger graphs. Whether gradient training can learn an executor in the architecture class of the construction remains open.

Momentum

Related topics

Latest papers 18