State Tracking

Follow this topic Ask about this topic

State tracking asks whether a model can keep an accurate account of what has happened and use it to interpret later inputs or choose actions. Approaches include recurrent networks and state-space models that update hidden states, Transformers that infer state from context, and explicit memories, state machines, or structured records that agents update and retrieve. Evaluations range from synthetic counting and permutation tasks to dialogue benchmarks such as MultiWOZ, video entity and event tracking, and long-horizon agent tasks. Explicit state representations can improve reliability, but models still struggle with long sequences, changing or partially observed states, and generalizing learned updates; greater representational power does not ensure that training will discover robust tracking mechanisms.

Latest papers

99 papers20 papers in the last four weeks, down 17% on the four weeks before. 0.1% of all new papers.

When Does Reward Teach State? A Hidden-Automaton Instrument and a Group-Language Warning Signal
Jul 11, 2026James E. AllchinReinforcement Learning Partially Observable RL
Independent Researcher
A-TMA: Decoupling State-Aware Memory Failures in Long-Term Agent Memory
Jul 2, 2026Zitong Shi, Yixuan Tang, Anthony Kum Hoe TungState Tracking Long-Term Conversational Memory
National University of Singapore
LLM Agents Are Latent Context Managers: Eliciting Self-Managed Context via State Proprioception
Jun 29, 2026Binyan Xu, Haitao Li, Kehuan ZhangTool-Augmented Language Model Agents LLM Agent Memory
The Chinese University of Hong Kong · LIGHTSPEED · Tencent
Do Models Read What They Write? Causal Registers in Scratchpad Reasoning
Jun 28, 2026Benjamin Shih, John Winnicki, Eric DarveCoT Faithfulness CoT Reasoning
Institute for Computational and Mathematical Engineering Stanford University
Training Observable Control Policies to Expose Agent State Through Actions
Jun 25, 2026Andres Enriquez Fernandez, John J. BirdAI Agent Monitoring State Tracking
Department of Aerospace and Mechanical Engineering, 500 W University, El Paso, TX 79968
LedgerAgent: Structured State for Policy-Adherent Tool-Calling Agents
Jun 18, 2026Md Nayem Uddin, Amir Saeidi, Eduardo Blanco +1Tool-Augmented Language Model Agents Customer Support Automation
♠Arizona State University · ♢University of Arizona
Bistable by Construction: Wall-Clock-Calibrated State Monitors Have No Moment-Detection Regime at Agent Cadence
Jun 15, 2026Manvendra ModgilAgent Reliability AI Agent Monitoring
Modint Intelligence
Remember, Don't Re-read: Stateful ReAct Agents for Token-Efficient Autonomous Experimentation
Jun 12, 2026Faramarz JabbarvaziriLarge Language Model-Guided Optimization LLM Agent Workflow Optimization
StatefulDiscovery: Evidence-Calibrated Claim Formation in Open-Ended Scientific Discovery
Jun 10, 2026Jiayao Chen, Shi Liu, Linyi YangAI Agents for Scientific Discovery Evidence-Grounded Reasoning
Southern University of Science and Technology
A Held-Out Transition-Pair Falsifier for Long-Horizon Non-Abelian State Tracking
Jun 5, 2026Jeonghoon LeeRecurrent Neural Networks State Tracking
Attractor Dynamics
Benchmarking Visual State Tracking in Multimodal Video Understanding
Jun 2, 2026Sihyun Yu, Nanye Ma, Pinzhi Huang +8Multimodal Large Language Models Video Reasoning
New York University · KAIST
STEP: Learning STructured Embeddings for Progressive Time Series
May 29, 2026Lucas Thil, Jesse Read, Rim Kaddah +1Self-Supervised Time Series Representation Learning Interpretable ML
LIX, École Polytechnique IRT SystemX Palaiseau, France · IRT SystemX Palaiseau, France · Safran Tech Chateaufort, France
Do Language Models Track Entities Across State Changes?
May 28, 2026Zilu Tang, Qiao Zhao, Gabriel Franco +4LLM Interpretability 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
Chess-World-Model: A 10M-Game Benchmark for Exact State Tracking from Chess Move Sequences
May 28, 2026Benjamin Walker, Terry LyonsRecurrent Neural Networks State Tracking
Mathematical Institute, University of Oxford · Department of Mathematics, Imperial College London
PatchBoard: Schema-Grounded State Mutation for Reliable and Auditable LLM Multi-Agent Collaboration
May 28, 2026Shuyu Zhang, Yaqi Shi, Jiarui Zhang +2AI Agent Reliability Multi-Agent LLM Systems
School of Computer Science and Technology Xidian University Xi’an, China
EfficientGraph-RAG: Structured Retrieval-State Management for Cross-Task Retrieval-Augmented Generation
May 25, 2026Miaohe Niu, Lianlei Shan, Zhengtao Yu +2Retrieval-Augmented Generation Graph Retrieval-Augmented Generation
School of Computer Science and Engineering, Northeastern University, China · 2Tsinghua University, China · 3Kunming University of Science and Technology, China +1
STREAM: A Data-Centric Framework for Mining High-Value Task-Oriented Dialogues from Streaming Media
May 24, 2026Liang Xue, Haoyu Liu, Cheng Wang +3Spoken Dialogue Systems State Tracking
Harbin Institute of Technology Byering Technology Harbin, China · Harbin Institute of Technology Harbin, China
Structured-Sparse Attention for Entity Tracking with Subquadratic Sequence Complexity
May 21, 2026Hangyue Zhao, Paul Caillon, Erwan Fagnou +1Self-Attention Structured Sparsity
ESPCI PSL, Paris, France · LAMSADE, Université Paris Dauphine - PSL, Paris, France
Markovian Circuit Tracing for Transformer State Dynamic
May 20, 2026Abdullah XTransformer Interpretability Transformer
Project AWARE and Zephara AI
ReacTOD: Bounded Neuro-Symbolic Agentic NLU for Zero-Shot Dialogue State Tracking
May 18, 2026Yanjun Lin, Zimo Xiao, Kartik Natarajan +7Spoken Dialogue Systems LLM Agents
Amazon
A Proprioceptive-Only Benchmark for Quadruped State Estimation: ATE, RPE, and Runtime Trade-offs Between Filters and Smoothers
May 12, 2026Ylenia Nisticò, João Carlos Virgolino Soares, Joan Solà +1State Tracking Robot State Estimation
Dynamic Legged Systems (DLS) Lab, Istituto Italiano di Tecnologia, 16163 Genova, Italy · Institut de Rob`otica i Inform`atica Industrial - CSIC, 08028 Barcelona, Spain
Rethinking State Tracking in Recurrent Models Through Error Control Dynamics
May 8, 2026Jiwan Chung, Heechan Choi, Seon Joo KimRecurrent Neural Networks State Tracking
Yonsei University
GEM: Graph-Enhanced Mixture-of-Experts with ReAct Agents for Dialogue State Tracking
May 6, 2026Ziqi Zhu, Adithya Suresh, Tomal Deb +1Spoken Dialogue Systems State Tracking
Generative AI Innovation Center, Amazon Web Services
Language models fail at extended rule following
May 3, 2026Tianxiang Dai, Jonathan FanLLM Evaluation LLM Reliability
Department of Electrical Engineering, Stanford University, Stanford, CA 94305.
The Topological Trouble With Transformers
Apr 18, 2026Michael C. Mozer, Shoaib Ahmed Siddiqui, Rosanne LiuTransformer FFNs Recurrent Neural Networks
Google DeepMind
SRMU: Relevance-Gated Updates for Streaming Hyperdimensional Memories
Apr 16, 2026Shay Snyder, Andrew Capodieci, David Gorsich +1Hyperdimensional Computing Vector Symbolic Architectures
George Mason University · George Mason University, USA · Neya Robotics +3
SiMing-Bench: Evaluating Procedural Correctness from Continuous Interactions in Clinical Skill Videos
Apr 10, 2026Xiyang Huang, Jiawei Lin, Keying Wu +9Video-Language Model Evaluation Multimodal Model Evaluation
School of Artificial Intelligence, Wuhan University · Center for Language and Information Research, Wuhan University · Southwest Jiaotong University +3
Where Did It Go Wrong? Process-Level Evaluation of Web Agents with Semantic State Tracking
Apr 8, 2026Jiwan Chung, JiHyuk Byun, Vibhav Vineet +1Process-Based Agent Evaluation Agent Evaluation
Yonsei University · Microsoft Research
EchoChain: A Full-Duplex Benchmark for State-Update Reasoning Under Interruptions
Apr 8, 2026Smit Nautambhai Modi, Gandharv Mahajan, Marc Wetter +1State Tracking Voice Agent Evaluation
Applied Machine Learning Research
The UNDO Flip-Flop: A Controlled Probe for Reversible Semantic State Management in State Space Model
Apr 7, 2026Hongxu ZhouState Space Models State Tracking
Erasmus Mundus Language and Communication Technologies Saarland University Saarbrücken, Germany

Jul 11, 2026J/K move · Enter open · S save

When Does Reward Teach State? A Hidden-Automaton Instrument and a Group-Language Warning Signal

James E. Allchin

Independent Researcher

Reinforcement Learning Partially Observable RL State Tracking State Representation Learning

Open paper AskPDF arXiv

Does a reinforcement-learning agent that earns reward learn its task's hidden state? We study this question with hidden finite automata that the agent partially controls. Because each automaton is known, we can normalize reward by the best achievable return and probe the network for the true state at every step. Together the two measurements separate failures that reward alone conflates. An agent can encode too little of a state its network could hold, or encode the state and still control poorly. Weak on-policy RL matches random play while the state probe stays at chance. State learning depends on the optimizer, the training budget, and the task's structure. Permutation automata provide a warning before training: no input symbol maps two distinct states to the same successor. On a stratified held-out set, 86 of 103 permutation automata fail the state probe, and the classification is stable across probe read-outs and recovery thresholds. Most of these failures come with weak reward. High reward without the state occurs but is rare. Non-permutation automata can also fail. Oracle-normalized reward alone therefore does not establish that the task's state was learned.