State-Tracking

Follow this topic Ask about this topic

Momentum

20 papers in the last four weeks, up 233% on the four weeks before. 0.2% of all new papers.

Jul 6Week of Sep 21

Latest papers 91

All topics

Richer Representations for Neural Algorithmic Reasoning via Auxiliary Reconstruction
May 30, 2026Jiafu Huang, Chao Peng, Chenyang Xu +7Representation Learning Encoders
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
The Deterministic Horizon: When Extended Reasoning Fails and Tool Delegation Becomes Necessary
May 29, 2026Dongxin Guo, Jikun Wu, Siu Ming YiuAgentic Reasoning Chain-of-Thought Reasoning
The University of Hong Kong, Hong Kong, China · Brain Investing Limited, Hong Kong, China · Stellaris AI Limited, Hong Kong, China
Do Language Models Track Entities Across State Changes?
May 28, 2026Zilu Tang, Qiao Zhao, Gabriel Franco +4Entities State-Tracking
Department of Computer Science, Boston University, Boston, USA · Department of Data Science, Monash University, Indonesia · Faculty of Computer Science, University of Vienna, Austria +1
PatchBoard: Schema-Grounded State Mutation for Reliable and Auditable LLM Multi-Agent Collaboration
May 28, 2026Shuyu Zhang, Yaqi Shi, Jiarui Zhang +2State-Tracking Keyed Javascript Object Notation Record Yields
School of Computer Science and Technology Xidian University Xi’an, China
Stochastic Lifting for Generating Trajectories of Stochastic Physical Systems
May 28, 2026Jules Berman, Tobias Blickhan, Benjamin PeherstorferStochastic Dynamics Stochastic
Courant Institute of Mathematical Sciences, New York University, New York, NY 10012, USA.
Causal Intelligence for Constraint-Aware Intervention Design to Induce State Transitions
May 27, 2026Zixuan Song, Uwe Mueller, Dimitris V. ManatakisLatent Feature Interventions State-Tracking
MRL, Merck & Co., Inc., 33 Avenue Louis Pasteur, Boston, 02115, MA, USA.
You Are in Control of Your State: Why Human Outcomes Are Controllable Through Causal State Intervention
May 26, 2026Suraj Biswas, Saurav Gupta, Pritam MukherjeeCausal Intervention State-Tracking
Independent Researchers in Behavioural Modelling, Causal Inference, and Genomics · Assessli · Dots-In
Classical State Preparation for Variational Quantum Algorithms via Reinforcement Learning
May 22, 2026Gino Kwun, Dhanvi Bharadwaj, Gokul Subramanian RaviVariational Quantum Algorithms Qubit
Computer Science and Engineering University of Michigan Ann Arbor, MI 48109, USA
Post-Training is About States, Not Tokens: A State Distribution View of SFT, RL, and On-Policy Distillation
May 21, 2026Dong NieSupervised Finetuning Post-Training
Independent Researcher
Learning Lifted Action Models from Traces with Minimal Information About Actions and States
May 18, 2026Jonas Gösgens, Niklas Jansen, Hector GeffnerPartial Observability State-Tracking
RWTH Aachen University
ASPI: Seeking Ambiguity Clarification Amplifies Prompt Injection Vulnerability in LLM Agents
May 17, 2026Udari Madhushani Sehwag, Zhengyang Shan, Heming Liu +3Indirect Prompt Injection Large Language Model Agents
Scale AI · 2Boston University · 4Human Frontier Collective +3
Rethinking the State Update Gate for Long-Sequence Recurrent 3D Reconstruction
May 16, 2026Kejun Ren, Lei Jin, Tianxin Huang +23D Reconstruction Recurrent State
Beijing University of Posts and Telecommunications, Beijing, China · School of Computing and Data Science, The University of Hong Kong
Deterministic Event-Graph Substrates as World Models for Counterfactual Reasoning
May 15, 2026Fabio RovaiCounterfactuals Rdf
Tesseract Academy
No Action Without a NOD: A Heterogeneous Multi-Agent Architecture for Reliable Service Agents
May 12, 2026Zixu Yang, Hang Zheng, Nan Jiang +5State-Tracking
1X-LANCE Lab, School of Computer Science, Shanghai Jiao Tong University, Shanghai, China · 2Shanghai Innovation Institution, Shanghai, China · 3Jiangsu Key Lab of Language Computing, Suzhou, China
WorldReasonBench: Human-Aligned Stress Testing of Video Generators as Future World-State Predictors
May 11, 2026Keming Wu, Yijing Cui, Wenhan Xue +11Long Video Generation Video Generation
Tsinghua University · Nanyang Technological University · Hong Kong University of Science and Technology (Guangzhou) +2
Rethinking State Tracking in Recurrent Models Through Error Control Dynamics
May 8, 2026Jiwan Chung, Heechan Choi, Seon Joo KimRecurrent Neural Networks Recurrent Model
Yonsei University
Differentiable Parameter Optimization for DAEs with State-Dependent Events
May 6, 2026Ion Matei, Maksym Zhenirovskyy, Anthony WongDifferentiable Optimization Ordinary Differential Equations
Fujitsu Research of America
Investigating Action Encodings in Recurrent Neural Networks in Reinforcement Learning
May 4, 2026Matthew Schlegel, Volodymyr Tkachuk, Adam White +1Recurrent Neural Networks State-Tracking
University of Alberta
Are you with me? A Framework for Detecting Mental Model Discrepancies in Task-Based Team Dialogues
May 4, 2026Katharine Kowalyshyn, Matthias ScheutzTheory-Of-Mind Reasoning Dialogue
Department of Computer Science, Tufts University
Set-Based Training of Neural Barrier Certificates for Safety Verification of Dynamical Systems
May 4, 2026Miriam Kranzlmüller, Lukas Koller, Tobias Ladner +1Neural Network Verification Finite-Sample Certificates
Technical University of Munich, Germany · Ludwig-Maximilians-Universität in Munich, Germany
Physics-Informed Neural Learning for State Reconstruction and Parameter Identification in Coupled Greenhouse Climate Dynamics
May 4, 2026Sani Biswas, Khursheed J. Ansari, Md. Nasim AkhtarParametric Physics-Informed Neural Network Physics-Informed Learning
Centro de Modelamiento Matemático (CMM), Universidad de Chile & IRL 2807 - CNRS, Santiago, 8370456, Chile · Department of Mathematics, College of Science, King Khalid University, Abha, 61413, Saudi Arabia · Department of Mathematics, Presidency University, Kolkata, 700 073, India
Probabilistic Graphical Model using Graph Neural Networks for Bayesian Inversion of Discrete Structural Component States
Apr 26, 2026Teng Li, Stephen Wu, Yong Huang +2Probabilistic Graphical Models Graph Neural Networks
Key Lab of Smart Prevention and Mitigation of Civil Engineering Disasters of the Ministry of Industry and Information Technology, Harbin Institute of Technology, Harbin 150090, China · Key Lab of Structures Dynamic Behavior and Control of the Ministry of Education, School of Civil Engineering, Harbin, Institute of Technology, Harbin 150090, China · The Institute of Statistical Mathematics, Research Organization of Information and Systems, 10-3 Midori-cho, Tachikawa, Tokyo 190-8562, Japan +2
Reasoning Primitives in Hybrid and Non-Hybrid LLMs: Do Architectural Differences Yield Advantages in State-Tracking and Recall?
Apr 23, 2026Shivam Rawat, Lucie Flek, Florian Mai +1LLM Reasoning Strategies Search-Augmented Reasoning
Lamarr Institute for Machine Learning and Artificial Intelligence · Rheinische Friedrich-Wilhelms-Universität Bonn
State Transfer Reveals Reuse in Controlled Routing
Apr 20, 2026Yanzhen Lu, Zhicheng Qian, Muchen Jiang +1State-Tracking Large Language Model Routing
Shanghai Qizhi Institute · Southeast University · Nanjing Whale Cloud +1
Ego-InBetween: Generating Object State Transitions in Ego-Centric Videos
Apr 20, 2026Mengmeng Ge, Takashi Isobe, Xu Jia +7Egocentric Video Camera-Conditioned Video Generation
Advanced Micro Devices, Inc. · Dalian University of Technology · The Hong Kong University of Science and Technology +2
Atomic Decision Boundaries: A Structural Requirement for Guaranteeing Execution-Time Admissibility in Autonomous Systems
Apr 19, 2026Marcelo FernandezAdmissibility Safety-Critical Scenarios
TraslaIA
The Phasor Transformer: Resolving Attention Bottlenecks on the Unit Circle
Mar 18, 2026Dibakar SigdelTransformer Attention Energy-Based Transformer
Mindverse Computing LLC, WA 98087
Learning State-Tracking from Code Using Linear RNNs
Feb 16, 2026Julien Siems, Riccardo Grazzi, Korbinian Pöppel +3State-Tracking Sequence Modeling
University of Freiburg · Prior Labs · Microsoft Research +2
NRR-Phi: A Typed External Text-to-State Interface and Update Contract for Inspectable Ambiguity-State Maintenance
Jan 12, 2026Kei SaitoAmbiguity Natural Language Inference
Independent Researcher, Japan
StatEval: A Comprehensive Benchmark for Large Language Models in Statistics
Oct 10, 2025Yuchen Lu, Run Yang, Yichen Zhang +6Large Language Model Benchmarks Statistical Inference
1Shanghai University of Finance and Economics
Shoot from the HIP: Hessian Interatomic Potentials without derivatives
Sep 25, 2025Andreas Burger, Luca Thiede, Nikolaj Rønne +5Hessian Interatomic Potentials
University of Toronto · Vector Institute for Artificial Intelligence · Technical University of Denmark +4

May 30, 2026, cs.LGJ/K move · Enter open · S save

Richer Representations for Neural Algorithmic Reasoning via Auxiliary Reconstruction

Jiafu Huang, Chao Peng, Chenyang Xu, Zhengfeng Yang+6

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

Representation Learning Encoders Deterministic Reconstruction State-Tracking

Open paper AskPDF arXiv

Neural algorithmic reasoning has 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 architecture, where the encoder learns representations of states, the processor simulates algorithmic steps, and the decoder reconstructs output states. While prior work has focused on improving the processor, the role of the encoder in representation learning has received little attention. Most methods rely on simple MLP encoders, raising the question of whether such representations are sufficiently informative for supporting algorithmic reasoning. This paper investigates how to improve encoder representations for neural algorithmic reasoning. We propose a reconstruction module that aims to recover the input state from its encoded representation. This auxiliary reconstruction task encourages the encoder to retain critical information about the input. We demonstrate that incorporating this task during training improves the performance of existing neural architectures on standard benchmarks. Furthermore, we observe that current encoders often underutilize the correlations among features within a state. To address this, we draw inspiration from self-supervised learning and design an enhanced variant of the auxiliary task that encourages the encoder to capture intra-state feature dependencies. Experimental results show that our method enables the encoder to learn richer representations, thereby enhancing the performance of existing processors on algorithmic reasoning tasks.

Momentum

Related topics

Latest papers 91