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.

Jul 11, 2026

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

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.

James E. Allchin

Independent Researcher

Reinforcement Learning Partially Observable RL State Tracking State Representation Learning

Jul 2, 2026

A-TMA: Decoupling State-Aware Memory Failures in Long-Term Agent Memory

Long term memory lets LLM agents act as persistent assistants, but user facts change. A useful memory system must know what is true now, what used to be true, and what changed. We study ghost memory, a state coordination failure in which old, current, and transition facts coexist in the memory bank, remain mixed during retrieval, and mislead the answer model. We argue that memory systems should be understood and optimized from three levels: bank maintenance, retrieval, and answer time resolution. We propose ATMA, a state aware overlay for existing memory systems. ATMA keeps superseded and transition records in the bank, builds evidence packets for the query's requested state view, and exposes current, historical, and transition labels to QA. We further call for decoupled evaluation of bank, retrieval, and answer level failures, since final QA accuracy can hide where ghost memory occurs. To make this failure measurable, we build LTP (LoCoMo Temporal Plus), a conflict heavy benchmark for ghost memory, and evaluate on LoCoMo for long conversation generalization. On LTP, Graphiti+ATMA improves conflict accuracy by 0.240 absolute over Graphiti. On LoCoMo, Graphiti+ATMA raises temporal F1 from 0.0295 to 0.1705. The gains are host dependent, but they indicate that explicit state roles can reduce memory failures hidden by final QA accuracy.

Zitong Shi, Yixuan Tang, Anthony Kum Hoe Tung

National University of Singapore

State Tracking Long-Term Conversational Memory Agent Memory Management

Jun 29, 2026

LLM Agents Are Latent Context Managers: Eliciting Self-Managed Context via State Proprioception

Long-horizon tool agents are bottlenecked by how their context grows toward the limits of the context window. Recent systems make context management agent- or system-controlled, but they either learn a compression policy that discards evidence or manage context in a layer the agent never sees. We argue both leave a more basic gap unaddressed. Frontier language models are proprioceptively blind to their own context. From the prompt alone they cannot see how large, how old, or how used each block is, the signals a keep-or-drop decision needs. We hypothesize that competent context management is already latent in capable models, and that what is missing is not a learned policy but an interface exposing this state. We introduce VISTA (Visible Internal State for Tool Agents), a training-free, model-agnostic layer that represents working memory as typed, addressable blocks, surfaces a runtime dashboard of per-block token usage, recency, and access history, and archives blocks as recoverable full-fidelity payloads. On LOCA-Bench, BrowseComp-Plus, and GAIA, the same untrained interface transfers across 1M-, 100K-, and 10K-scale trajectories. On LOCA-Bench it improves four backbones and lifts Gemini-3-Flash from 22.7 to 50.7%. The lift grows with context pressure and transfers across backbones. Ablations further confirm that the dashboard matters beyond archive and recovery tools.

Binyan Xu, Haitao Li, Kehuan Zhang

The Chinese University of Hong Kong · LIGHTSPEED · Tencent

Tool-Augmented Language Model Agents LLM Agent Memory LLM Agents State Tracking Long-Horizon LLM Agents LLM Context Management

Jun 28, 2026

Do Models Read What They Write? Causal Registers in Scratchpad Reasoning

A central hope behind process supervision is that models can expose intermediate variables that matter for their later behavior. For this to help with alignment, a scratchpad must be tied to the computation: when the model writes a state, later steps should compute from that state. To test this requirement, we use a controlled state-tracking task with a known update rule, comparing models trained to report only the final state with models trained to write intermediate states before giving the final answer. At evaluation, we edit the internal representation of one written state while leaving the visible scratchpad text fixed. Because the transition rule is known, the edit has a single correct downstream consequence. In Qwen2.5-Coder-7B, the state-writing model predicts the next phase bit implied by the edited state on 80% and 91% of held-out examples across the two task variants, while pretrained and final-answer-only controls remain near baseline. Additional controls rule out generic next-token steering and copying another continuation: the prediction depends on both the edited state and the current move. The same causal-use pattern replicates across model families. Together, these results suggest a sharper goal for scratchpad oversight: not just to make intermediate reasoning legible, but to train written states that the model uses as part of its computation.

Benjamin Shih, John Winnicki, Eric Darve

Institute for Computational and Mathematical Engineering Stanford University

CoT Faithfulness CoT Reasoning State Tracking Process Supervision Causal Interventions in Language Models

Jun 25, 2026

Training Observable Control Policies to Expose Agent State Through Actions

Physical or operational constraints often impose communications limitations on autonomous agents. Such limitations complicate monitoring or multiagent coordination. Even when strong communications are absent, some information may still be available. The remainder of the relevant agent state may be reconstructed via estimation. The actions taken by an agent are a potential source of information -- as the agent interacts with the environment, these actions may be observed even in the absence of explicit communication. We investigate using actions to estimate the state of an agent, using reinforcement learning to develop policies which make the estimation problem more tractable. Policy observability is encouraged through the training reward and is analyzed using simulation of the trained agent. In an aircraft tracking problem a policy with enhanced observability is found that has minimal impact on nominal task performance.

Andres Enriquez Fernandez, John J. Bird

Department of Aerospace and Mechanical Engineering, 500 W University, El Paso, TX 79968

AI Agent Monitoring State Tracking

Jun 18, 2026

LedgerAgent: Structured State for Policy-Adherent Tool-Calling Agents

Policy-adherent tool-calling agents in customer-service domains must maintain task states across turns while calling tools and obeying domain policies. Task states consist of relevant facts, identifiers, constraints, and conditions observed through user interaction and tool calls. In standard agents, task states are not represented separately. Observations, tool returns, and policy instructions are placed in the prompt, leaving agents to reconstruct the relevant states from the prompt each time they decide what to do next. This design makes state management implicit, creating two common failure modes. An agent may retrieve the right facts but later ground its decision in stale, missing, or incorrect information; and a syntactically valid tool call may still violate a domain policy that depends on the current task state. We introduce LedgerAgent, an inference-time method for tool-calling agents that maintains observed task states in a separate ledger and renders the states into the prompt. The ledger is also used to check state-dependent policy constraints before environment-changing tool calls are executed, blocking policy violations. Across four customer-service domains and a mixed panel of open- and closed-weight models, LedgerAgent improves average pass\textasciicircum{}k over a standard prompt-based tool-calling approach, with the largest gains under stricter multi-trial consistency metrics.

Md Nayem Uddin, Amir Saeidi, Eduardo Blanco +1

♠Arizona State University · ♢University of Arizona

Tool-Augmented Language Model Agents Customer Support Automation Tool-Using Agents State Tracking LLM Agent Safety LLM Agent Reliability

Jun 15, 2026

Bistable by Construction: Wall-Clock-Calibrated State Monitors Have No Moment-Detection Regime at Agent Cadence

Runtime monitors for autonomous agents commonly threshold an accumulated internal state - a behavioural baseline, a drift statistic, or, in our prior work, a modelled affective state. We previously reported a State Saturation Trap: threshold-on-state triggers over a continuous affect engine become near-constant alarms on SWE-bench debugging agents (Modgil 2026). A post-release audit found the engine received dt=0 between actions, so its exponential decay never operated: the published trap is a pure-accumulator result. We correct the record (erratum, v2) and treat the flaw as an experiment. The key variable it exposes is whether a monitor's dynamics are calibrated in sample time (per observation, as in CUSUM) or wall-clock time (half-lives in seconds, as in affect models and EMA baselines). On fixed-rate streams these coincide; on agent streams, where inter-action time varies by orders of magnitude, they do not. A pre-registered sweep over uniform intervals (dt in {0..600}s) on 20 trajectories shows the wall-clock level trigger has two regimes: at dt<=1s a constant alarm (20/20; median 18 firings); at dt>=60s silent. Every critical dt lies in (1,30]s. A scriptable gpt-5.4-mini agent loop measures latency at median 1.53s (p90 2.33s), inside the trap regime, vindicating the empirical finding under a corrected mechanism. The structure is a property of the calibration class, not the engine: a minimal wall-clock accumulator over the raw error stream reproduces the same cliff, while a sample-time CUSUM over the identical stream is exactly dt-invariant (20/20). A rising-edge trigger with hysteresis fires 0-3 times per trajectory in every condition. We conclude that wall-clock-calibrated leaky-integrator monitors admit no regime in which they act as moment detectors on agent streams; transition detection escapes the trap at every cadence, but does not recover human intervention timing.

Manvendra Modgil

Modint Intelligence

Agent Reliability AI Agent Monitoring State Tracking Change-Point Detection

Jun 12, 2026

Remember, Don't Re-read: Stateful ReAct Agents for Token-Efficient Autonomous Experimentation

The autoresearch pattern enables autonomous experimentation by having a large language model (LLM) iteratively modify code to optimize a target metric. Its stateless design, however, reconstructs experimental context from scratch at every iteration, incurring

O(n)

token cost per iteration and

O(n^{2})

total. This work reformulates the pattern as a stateful ReAct agent using LangGraph, where typed persistent state carries experimental history across iterations via a tool-calling interface. Two benchmarks are evaluated: hyperparameter tuning (15 iterations, small per-iteration observations) and code performance optimization (40 iterations, large per-iteration observations containing full source code and benchmark results). On hyperparameter tuning, the stateful agent consumes 90% fewer tokens (2{,}492 vs.\ 24{,}465). On code optimization, the stateful agent consumes 52% fewer tokens (627K vs.\ 1{,}275K) while achieving comparable optimization quality on both tasks. The token reduction is structural: the stateless agent re-reads the full history at

O(n)

cost per iteration, while the stateful agent operates within a fixed-size conversation window at

O(1)

cost. This paper describes the architecture in sufficient detail for practitioners to implement a stateful autoresearch agent for their own workflows.

Faramarz Jabbarvaziri

Large Language Model-Guided Optimization LLM Agent Workflow Optimization LLM Agents State Tracking Autonomous Experimentation Memory-Augmented Language Model Agents

Jun 10, 2026

StatefulDiscovery: Evidence-Calibrated Claim Formation in Open-Ended Scientific Discovery

Open-ended scientific discovery asks agents to move beyond executing analyses for predefined questions. Across multiple rounds of exploration, a discovery agent must decide which phenomena warrant investigation while avoiding overinterpretation, where emerging claims exceed the evidential scope of the analyses. This creates an evidence-calibration problem: the exploration trajectory must be coupled with claim status so that evidence can guide both what to investigate next and what can be claimed. We introduce StatefulDiscovery, a discovery framework that externalizes investigation state and uses it to coordinate frontier selection, evidence acquisition, and claim adjudication. We evaluate StatefulDiscovery across 40 real-data discovery tasks. Compared with several baselines, StatefulDiscovery produces more claims overall judged to be both well-supported and high-value. Ablations indicate distinct roles for structured hypotheses, local adjudication, frontier control and persistent states. Together, these results suggest that explicit discovery state can couple exploration with evidence-calibrated claim formation. Our code is released at https://github.com/SUSTech-GenAI/StatefulDiscovery.git.

Jiayao Chen, Shi Liu, Linyi Yang

Southern University of Science and Technology

AI Agents for Scientific Discovery Evidence-Grounded Reasoning State Tracking Scientific Claim Verification

Jun 5, 2026

A Held-Out Transition-Pair Falsifier for Long-Horizon Non-Abelian State Tracking

State tracking exposes a sharp limitation of sequence models: the relevant signal is often not a summary of observed tokens, but an ordered latent state that evolves through non-commutative transformations. We introduce a held-out transition-pair falsifier for finite non-Abelian group tracking. The protocol forbids selected ordered generator pairs during training and requires the same local patterns during evaluation, blocking one direct local-transition memorization pathway. In a controlled

S_3 \times S_3

benchmark, a projected recurrent state model trained only on length-8 sequences produces error-free final-state predictions (perfect 250/250 per horizon) through evaluation horizons up to 1,048,576 tokens across five seeds. Matched native-readout baselines, including bag, GRU, and a single-configuration structured state-space model, remain near floor under the same protocol. Projection-matched GRU, structured SSM, and bag baselines equipped with analogous finite-group prototype readouts also remain near chance under the same split. Mechanism diagnostics show that hard projection coincides with low homomorphism error, low state-consistency drift, and non-trivial commutator separation, while softened projection collapses final-state accuracy. Clean-split audits verify zero verbatim reduced-word overlap and zero structural-template overlap between training and evaluation partitions. The evidence is scoped to this controlled finite-group falsifier rather than to a general architecture ranking. Within that regime, explicit projected non-commutative state composition acts as a useful inductive bias for long-horizon hidden-state tracking.

Jeonghoon Lee

Attractor Dynamics

Recurrent Neural Networks State Tracking Sequence Modeling

Jun 2, 2026

Benchmarking Visual State Tracking in Multimodal Video Understanding

Understanding a video requires more than recognizing isolated moments, as humans continuously track entities, states, and events over time. This capacity for visual state tracking is fundamental to video understanding, yet remains underexplored in current evaluations of Multimodal Large Language Models (MLLMs). We introduce Visual STAte Tracking benchmark (VSTAT), a video-based benchmark designed to diagnose visual state tracking in MLLMs. VSTAT consists of 834 clips drawn from both synthetic and real-world videos, paired with 1,500 questions that cannot be answered from any single frame or short segment, requiring continuous perception and integration of events across the entire video stream. Despite their strong performance on existing video benchmarks, we find that state-of-the-art MLLMs perform far below humans and only modestly above answer-prior baselines. To analyze this gap, we compare MLLMs' thinking traces with the underlying video stream to understand why and when MLLMs fail on VSTAT. We find that MLLMs reason and track correctly in text, but fail at visually perceiving the events they need to track. Finally, our preliminary evaluation suggests that recent agentic approaches, including MLLM-based video agents and coding agents, do not readily resolve these failures, still falling short on VSTAT.

Sihyun Yu, Nanye Ma, Pinzhi Huang +8

New York University · KAIST

Multimodal Large Language Models Video Reasoning State Tracking Multimodal Model Evaluation Temporal Video Understanding Multimodal Understanding

May 29, 2026

STEP: Learning STructured Embeddings for Progressive Time Series

We present a novel method for learning interpretable representations of progressive time series, that is, data capturing irreversible state transitions such as degradation or task completion. Our approach uses a self-supervised contrastive objective to learn a low-dimensional latent space whose geometry is itself the interpretation: each observation becomes a point on a manifold anchored between two fixed orthogonal prototype vectors, and a trajectory becomes a path across that manifold. From this structure we read a latent compass, the polar coordinates (θ, r) of the latent vector, in which θ tracks the progression of the underlying state (e.g., from healthy to failed) and r identifies the active mode (e.g., the operating condition), without any proxy labels. We evaluate the approach against the state of the art on diverse domains, including industrial degradation, robotic tasks, and neural activity, validating three key capabilities: (1) end-state prediction, (2) multi-step forecasting, and (3) interpretable phase separation. Our method matches or improves over black-box counterparts on all of these while providing transparency about the underlying mechanisms. A simple linear regressor on top of the latent compass coordinates is competitive with deep architectures, direct quantitative evidence that the underlying state is encoded in a geometrically accessible form.

Lucas Thil, Jesse Read, Rim Kaddah +1

LIX, École Polytechnique IRT SystemX Palaiseau, France · IRT SystemX Palaiseau, France · Safran Tech Chateaufort, France

Self-Supervised Time Series Representation Learning Interpretable ML Time Series Forecasting State Tracking State Representation Learning Temporal Representation Learning

May 28, 2026

Do Language Models Track Entities Across State Changes?

Entity tracking (ET), the ability to keep track of states, is a fundamental skill that underlies complex reasoning. An increasing amount of work investigates how transformer language models (LMs) solve entity binding

\textit{without}

state changes. However, there is limited understanding of how non-toy LMs address ET problems of realistic difficulties expressed in natural language. To this end, we investigate the mechanisms underlying ET in more complex scenarios featuring multiple state-changing operations. We find that LMs do not incrementally track world states across tokens or query-relevant states across layers, but simply aggregate relevant information in parallel at the last token when the query becomes evident. We further investigate mechanisms of individual operations (

\texttt{PUT}

,

\texttt{REMOVE}

,

\texttt{MOVE}

) to characterize this non-incremental ET mechanism. Surprisingly, LMs implement the

\texttt{REMOVE}

operation with a fragile global suppression tag; this global removal mechanism predicts various failure modes that we confirm behaviorally. We provide a mechanistic solution of nullifying this tag to partially address this issue. Overall, our findings reveal that LMs solve a fundamentally sequential task using a non-sequential strategy. More broadly, our work illustrates how behavioral and mechanistic analyses can fruitfully interact. Behavioral results inform mechanistic hypotheses, and insights from mechanistic analyses help build stronger behavioral evaluations by predicting failure modes missing from existing evaluations.

Zilu Tang, Qiao Zhao, Gabriel Franco +4

Department of Computer Science, Boston University, Boston, USA · Department of Data Science, Monash University, Indonesia · Faculty of Computer Science, University of Vienna, Austria +1

LLM Interpretability State Tracking

May 28, 2026

Chess-World-Model: A 10M-Game Benchmark for Exact State Tracking from Chess Move Sequences

World models require state tracking, which is the ability to maintain a correct latent state across action sequences. Existing benchmarks are often synthetic or language-based, limiting their value as tests of structured state updates in realistic domains. We introduce Chess-World-Model, a large-scale state-tracking benchmark built from 10 million real chess games, where models predict the exact board state reached after a sequence of legal moves. Alongside a held-out real-game split, we include an out-of-distribution split from uniformly random legal play, which tests whether models learn the transition rules rather than shortcuts from common human positions. Prior theoretical and empirical work has shown that Transformers struggle to state-track, while input-dependent linear RNNs require expressive state-transition matrices to do so. We therefore benchmark a causal Transformer, block-diagonal SLiCE, Mamba-3, and Gated DeltaNet with negative eigenvalues under a matched interface and training protocol. The recurrent models strongly outperform the Transformer at 3 and 8 million parameters. Real-game performance saturates above 18 million parameters, but the random-uniform split remains discriminative up to 40 million, exposing failures otherwise hidden by scale. Additionally, ablations show that less expressive state-transition mechanisms reduce performance on the out-of-distribution split for all three recurrent models. Together, these results establish Chess-World-Model as a practical large-scale benchmark for state tracking that exposes failures model scale would otherwise conceal.

Benjamin Walker, Terry Lyons

Mathematical Institute, University of Oxford · Department of Mathematics, Imperial College London

Recurrent Neural Networks State Tracking Chess World Model Evaluation

May 28, 2026

PatchBoard: Schema-Grounded State Mutation for Reliable and Auditable LLM Multi-Agent Collaboration

LLM multi-agent systems often coordinate through natural-language dialogue or loosely structured shared memory, making intermediate state difficult to validate, attribute, and audit. We introduce PatchBoard, a schema-grounded collaboration architecture that replaces inter-agent dialogue with validated JSON Patch mutations over a shared structured state. An Architect agent constructs a task-specific schema and workflow rules, while a deterministic kernel validates each proposed state mutation against schema constraints, role-specific write contracts, and runtime invariants before committing it transactionally. On 630 matched ALFWorld episodes, PatchBoard achieves an 84.6% success rate, compared with 30.8% for LangGraph and 61.6% for Flock, while reducing tokens per successful task to 45.5k, compared with 368.3k and 64.2k, respectively.

Shuyu Zhang, Yaqi Shi, Jiarui Zhang +2

School of Computer Science and Technology Xidian University Xi’an, China

AI Agent Reliability Multi-Agent LLM Systems State Tracking Multi-Agent Communication LLM Agent Reliability Shared-Memory Multi-Agent Systems

May 25, 2026

EfficientGraph-RAG: Structured Retrieval-State Management for Cross-Task Retrieval-Augmented Generation

Retrieval-augmented generation (RAG) has become the standard way to ground large language models in external knowledge, but many systems still organize evidence as flat chunks and retrieve it through largely unstructured search. This weak structure becomes a bottleneck for complex retrieval: the system must decide where to search, how to move from coarse topics to entity-relation evidence, which evidence has been verified, and which intermediate artifacts can be reused. We define these intermediate variables as a retrieval state and study RAG as structured state management. EfficientGraph-RAG makes this state explicit through three coupled mechanisms: TAM defines a typed hierarchical state space over evidence, MARS updates and verifies the state through role-specialized agents, and SMP stores reusable state under hierarchy-aware access control. Using one shared framework configuration, EfficientGraph-RAG ranks first on the reported answer-quality metrics averaged over the three evaluated LongBench retrieval-style subsets, matches the strongest agentic baseline on HotpotQA EM while reducing large-model token usage by

3.51\times

, and provides a low-token DocVQA result among retrieval-organizing cross-modal methods. Component analysis shows role-specific mechanisms: MARS is the main answer-quality driver, TAM supplies the typed traversal state and Adaptive Routing signal, and SMP enables corpus-dependent reuse, with cross-query cache hit rates ranging from 3.77% to 23.18%.

Miaohe Niu, Lianlei Shan, Zhengtao Yu +2

School of Computer Science and Engineering, Northeastern University, China · 2Tsinghua University, China · 3Kunming University of Science and Technology, China +1

Retrieval-Augmented Generation Graph Retrieval-Augmented Generation Agentic RAG State Tracking Structured RAG

May 24, 2026

STREAM: A Data-Centric Framework for Mining High-Value Task-Oriented Dialogues from Streaming Media

Large language models for vertical domains are bottlenecked by the scarcity of complex, domain-specific task-oriented dialogues. Existing data acquisition pipelines face a persistent trilemma: expert annotation is expensive, real-world service conversations are constrained by privacy and commercial restrictions, and static corpora quickly become temporally stale. We propose Stream, a data-centric framework that leverages publicly available streaming media (live streams and short videos) to synthesize high-value service dialogues at scale. Stream mines authentic interaction signals from noisy streams and synthesizes conversations by integrating role-grounded persona construction with Conversational Blueprint construction; it further adopts retrieval-augmented generation (RAG) to support knowledge-aware responses. Based on Stream, we release StreamDial, a large-scale multi-domain dataset covering Automotive, Restaurant, and Hotel. StreamDial contains 87,498 dialogue sessions and 1,497,320 turns in total, with an average of 17.11 turns per session and a comparable scale across domains. Each session is organized as a structured quadruplet

\langle P_u, P_a, B, H \rangle

that pairs dialogue history with explicit user/agent personas and a Conversational Blueprint, capturing realistic service behaviors such as requirement mining, constraint conflicts, negotiation, and recovery. Evaluations with automatic judges and downstream tasks show that StreamDial improves intrinsic dialogue quality over strong baselines, and models trained with StreamDial improve Dialogue State Tracking across backbones; we further report a completed human-evaluation set and encouraging multilingual transfer on Qwen3-8B under a controlled training budget. The data is released in https://github.com/hitxueliang/DialogDataSetBySTREAM.

Liang Xue, Haoyu Liu, Cheng Wang +3

Harbin Institute of Technology Byering Technology Harbin, China · Harbin Institute of Technology Harbin, China

Spoken Dialogue Systems State Tracking Synthetic Data Generation for Language Models Task-Oriented Dialogue Systems

May 21, 2026

Structured-Sparse Attention for Entity Tracking with Subquadratic Sequence Complexity

Entity tracking requires maintaining and updating latent states for entities and attributes over long sequences. Recent task-specific attention operators can compress deep Transformer stacks into a few layers by performing multi-hop state propagation within a single layer, but their dense evaluation remains expensive. We show that in this setting, learned attention is strongly structured: most mass concentrates in local block-diagonal neighborhoods with a light cross-block residue. Exploiting this, we derive a blockwise evaluation of a resolvent-style operator that keeps within-block interactions exact and routes cross-block interactions through a reduced system. The resulting evaluation is subquadratic in sequence length

O(n^{4/3}d)

(and

O(n^{7/3})

when

d\approx n

). On controlled tracking benchmarks, our method matches the dense operator's accuracy while reducing wall-clock time by

12-29\%

under a standardized measurement protocol, and is up to

2.4 \times

faster than a compact dense Transformer at comparable exact-match accuracy. We further provide ablations over block size and model capacity, and identify a limitation: performance collapses when the number of simultaneously evolving properties exceeds the number of attention heads.

Hangyue Zhao, Paul Caillon, Erwan Fagnou +1

ESPCI PSL, Paris, France · LAMSADE, Université Paris Dauphine - PSL, Paris, France

Self-Attention Structured Sparsity Transformer Attention Efficient Attention Sparse Attention State Tracking

May 20, 2026

Markovian Circuit Tracing for Transformer State Dynamic

Many sequence computations are easier to study as movement through internal states than as isolated local circuits. We introduce Markovian Circuit Tracing (MCT), a diagnostic pipeline for testing whether transformer activations contain coarse state-transition structure. The benchmark uses synthetic Hidden Markov Model (HMM) tasks where latent states, transition matrices, Bayesian belief vectors, Bayes-optimal predictions, and forced-state counterfactual targets are known exactly. Across six HMM families and three seeds per family, tiny causal transformers learn near-Bayes next-token predictors, with mean excess loss over Bayes of 0.0138. Residual activations contain partial Bayesian belief information in this controlled synthetic benchmark. State abstractions extracted from these activations recover coarse transition signal, strongest in persistent and lower-state regimes, and weaker in ambiguous-emission and six-state regimes. The clearest result comes from state forcing. Patching a recovered-state centroid reduces KL to the exact HMM counterfactual target from 0.1957 in the unpatched model to 0.0532 on average, beating wrong-state, mean-activation, random-activation, and shuffled-label controls. The contribution is a controlled benchmark and evaluation framework for transformer state-dynamics interpretability, with MCT as a simple reference pipeline

Abdullah X

Project AWARE and Zephara AI

Transformer Interpretability Transformer State Abstraction State Tracking Sequence Modeling Hidden-State Probing

May 18, 2026

ReacTOD: Bounded Neuro-Symbolic Agentic NLU for Zero-Shot Dialogue State Tracking

Task-oriented dialogue systems -- handling transactions, reservations, and service requests -- require predictable behavior, yet the moderately-sized LLMs needed for practical latency are prone to hallucination and format errors that cascade into incorrect actions (e.g., a hotel booked for the wrong date). We propose ReacTOD, a bounded neuro-symbolic architecture that reformulates NLU as discrete tool calls within a self-correcting ReAct loop governed by deterministic validation. A bounded ReAct loop enables iterative self-correction, improving accuracy by up to 9.3 percentage points over single-pass inference on MultiWOZ. A symbolic validator enforces action compliance, schema conformance, and coreference consistency on every dialogue state update, achieving a 93.1% self-correction rate on intercepted errors and producing structured execution traces. Incremental state prediction and on-demand history retrieval keep prompts compact, empirically improving instruction adherence in parameter-constrained models. On MultiWOZ 2.1, ReacTOD achieves a new zero-shot state-of-the-art: gpt-oss-20B reaches 52.71% joint goal accuracy, surpassing the previous best by 14 percentage points, while Qwen3-8B achieves 47.34% with only 8B parameters. On the Schema-Guided Dialogue (SGD) benchmark, ReacTOD with Claude-Opus-4.6 achieves 80.68% JGA under fully end-to-end evaluation with predicted domains, and Qwen3-32B reaches 64.09% -- demonstrating cross-benchmark generalization without task-specific training data.

Yanjun Lin, Zimo Xiao, Kartik Natarajan +7

Amazon

Spoken Dialogue Systems LLM Agents State Tracking Neuro-Symbolic AI Task-Oriented Dialogue Systems Multi-Turn Dialogue Management

May 12, 2026

A Proprioceptive-Only Benchmark for Quadruped State Estimation: ATE, RPE, and Runtime Trade-offs Between Filters and Smoothers

We compare three state-of-the-art proprioceptive state estimators for quadruped robots: MUSE [1], the Invariant Extended Kalman Filter (IEKF) [2], and the Invariant Smoother (IS) [3], on the CYN-1 sequence of the GrandTour Dataset [4]. Our goal is to give practitioners clear guidance on accuracy and computation time: we report long-term accuracy (Absolute Trajectory Error, ATE), short-term accuracy (translational and rotational Relative Pose Error, RPE), and per-update computation time on a fixed hardware/software stack. On this dataset, RPEs are broadly similar across methods, while IEKF and IS achieve a lower ATE than MUSE. Runtime results highlight the accuracy-latency trade-offs across the three approaches. In the discussion, we outline the evaluation choices used to ensure a fair comparison and analyze factors that influence short-horizon metrics. Overall, this study provides a concise snapshot of accuracy and cost, helping readers choose an estimator that fits their application constraints, with all evaluation code and documentation released open-source at https://github.com/iit-DLSLab/state_estimation_benchmark for full reproducibility.

Ylenia Nisticò, João Carlos Virgolino Soares, Joan Solà +1

Dynamic Legged Systems (DLS) Lab, Istituto Italiano di Tecnologia, 16163 Genova, Italy · Institut de Rob`otica i Inform`atica Industrial - CSIC, 08028 Barcelona, Spain

State Tracking Robot State Estimation Invariant EKF

May 8, 2026

Rethinking State Tracking in Recurrent Models Through Error Control Dynamics

The theory of state tracking in recurrent architectures has predominantly focused on expressive capacity: whether a fixed architecture can theoretically realize a set of symbolic transition rules. We argue that equally important is error control, the dynamics governing hidden-state drift along the directions that distinguish symbolic states. We prove that affine recurrent networks, a class of models encompassing State-Space Models and Linear Attention, cannot correct errors along state-separating subspaces once they preserve state representations. Consequently, practical affine trackers do not learn robust state tracking; rather, they learn finite-horizon solutions governed by accumulated state-relevant error. We characterize the mechanics of this failure, showing that tracking remains readable only while the accumulating within-class spread remains small relative to the between-class separation. We demonstrate empirically on group state-tracking tasks that this breakdown is predictable: tracking collapses when the distinguishability ratio crosses the readability threshold. Across trained models, the point of this crossing predicts the horizon at which downstream accuracy fails. These results establish that robust state tracking is determined not only by an architecture's theoretical expressivity but crucially by its error control.

Jiwan Chung, Heechan Choi, Seon Joo Kim

Yonsei University

Recurrent Neural Networks State Tracking State Space Models

May 6, 2026

GEM: Graph-Enhanced Mixture-of-Experts with ReAct Agents for Dialogue State Tracking

Dialogue State Tracking (DST) requires precise extraction of structured information from multi-domain conversations, a task where Large Language Models (LLMs) struggle despite their impressive general capabilities. We present GEM (Graph-Enhanced Mixture-of-Experts), a novel framework that combines language models and graph-structured dialogue understanding with ReAct agent-based reasoning for superior DST performance. Our approach dynamically routes between specialized experts: a Graph Neural Network that captures dialogue structure and turn-level dependencies, and a finetuned T5-Small encoder-decoder for sequence modeling, coordinated by an intelligent router. For complex value generation tasks, we integrate ReAct agents that perform structured reasoning over dialogue context. On MultiWOZ 2.2, GEM achieves 65.19% Joint Goal Accuracy, substantially outperforming end-to-end LLM approaches (best: 38.43%) and surpassing state-of-the-art (SOTA) methods including TOATOD (63.79%), D3ST (58.70%), and Diable (56.48%). Our graph-enhanced mixture-of-experts architecture with ReAct integration demonstrates that combining structured dialogue representation with dynamic expert routing and agent-based reasoning provides a powerful paradigm for dialogue state tracking, achieving superior accuracy while maintaining computational efficiency through selective expert activation.

Ziqi Zhu, Adithya Suresh, Tomal Deb +1

Generative AI Innovation Center, Amazon Web Services

Spoken Dialogue Systems State Tracking Mixture-of-Experts Models Task-Oriented Dialogue Systems

May 3, 2026

Language models fail at extended rule following

Large language models are highly capable of answering difficult questions by retrieving, recombining, and attending to information in long contexts. For agentic tasks, an additional capability is required: the preservation of an exact state while repeatedly applying rules. We find that this reliability is absent across language models. To demonstrate, we query 126 leading model variants with the task of counting a long string of repeated characters, and we find they all cannot accurately count above a model-dependent, syntax-sensitive counting capacity threshold. Failures are abrupt and persist even with increasing model size, inference time computation, and external tool. Mechanistic probing indicates that models use a finite number of internal states to mimic counting as a rule and fail once these states are exhausted. Furthermore, such states are the basis for performing complex tasks beyond counting. These results indicate that fundamentally new model architectures are required for autonomous agents to achieve truly reliable rule following capabilities.

Tianxiang Dai, Jonathan Fan

Department of Electrical Engineering, Stanford University, Stanford, CA 94305.

LLM Evaluation LLM Reliability State Tracking Algorithmic Reasoning

Apr 18, 2026

The Topological Trouble With Transformers

Transformers encode structure in sequences via an expanding contextual history. However, their purely feedforward architecture fundamentally limits dynamic state tracking. State tracking -- the iterative updating of latent variables reflecting an evolving environment -- involves inherently sequential dependencies that feedforward networks struggle to maintain. Consequently, feedforward models push evolving state representations deeper into their layer stack with each new input step, rendering information inaccessible in shallow layers and ultimately exhausting the model's depth. While this depth limit can be bypassed by dynamic depth models and by explicit or latent thinking that externalizes state representations, these solutions are computationally and memory inefficient. In this article, we argue that temporally extended cognition requires refocusing from explicit thought traces to implicit activation dynamics via recurrent architectures. We introduce a taxonomy of recurrent and continuous-thought transformer architectures, categorizing them by their recurrence axis (depth versus step) and their ratio of input tokens to recurrence steps. Finally, we outline promising research directions, including enhanced state-space models and coarse-grained recurrence, to better integrate state tracking into modern foundation models.

Michael C. Mozer, Shoaib Ahmed Siddiqui, Rosanne Liu

Google DeepMind

Transformer FFNs Recurrent Neural Networks Recurrent Transformers State Tracking

Apr 16, 2026

SRMU: Relevance-Gated Updates for Streaming Hyperdimensional Memories

Sequential associative memories (SAMs) are difficult to build and maintain in real-world streaming environments, where observations arrive incrementally over time, have imbalanced sampling, and non-stationary temporal dynamics. Vector Symbolic Architectures (VSAs) provide a biologically-inspired framework for building SAMs. Entities and attributes are encoded as quasi-orthogonal hyperdimensional vectors and processed with well defined algebraic operations. Despite this rich framework, most VSA systems rely on simple additive updates, where repeated observations reinforce existing information even when no new information is introduced. In non-stationary environments, this leads to the persistence of stale information after the underlying system changes. In this work, we introduce the Sequential Relevance Memory Unit (SRMU), a domain- and cleanup-agnostic update rule for VSA-based SAMs. The SRMU combines temporal decay with a relevance gating mechanism. Unlike prior approaches that solely rely on cleanup, the SRMU regulates memory formation by filtering redundant, conflicting, and stale information before storage. We evaluate the SRMU on streaming state-tracking tasks that isolate non-uniform sampling and non-stationary temporal dynamics. Our results show that the SRMU increases memory similarity by

12.6\%

and reduces cumulative memory magnitude by

53.5\%

. This shows that the SRMU produces more stable memory growth and stronger alignment with the ground-truth state.

Shay Snyder, Andrew Capodieci, David Gorsich +1

George Mason University · George Mason University, USA · Neya Robotics +3

Hyperdimensional Computing Vector Symbolic Architectures State Tracking Associative Memory

Apr 10, 2026

SiMing-Bench: Evaluating Procedural Correctness from Continuous Interactions in Clinical Skill Videos

Current video benchmarks for multimodal large language models (MLLMs) focus on event recognition, temporal ordering, and long-context recall, but overlook a harder capability required for expert procedural judgment: tracking how ongoing interactions update the procedural state and thereby determine the correctness of later actions. We introduce SiMing-Bench, the first benchmark for evaluating this capability from full-length clinical skill videos. It targets rubric-grounded process-level judgment of whether interaction-driven state updates preserve procedural correctness across an entire workflow. SiMing-Bench is instantiated with SiMing-Score, a physician-annotated dataset of real clinical skill examination videos spanning cardiopulmonary resuscitation, automated external defibrillator operation, and bag-mask ventilation, each paired with a standardized step-wise rubric and dual-expert labels. Across diverse open- and closed-source MLLMs, we observe consistently weak agreement with physician judgments. Moreover, weak performance on rubric-defined intermediate steps persists even when overall procedure-level correlation appears acceptable, suggesting that coarse global assessment substantially overestimates current models' procedural judgment ability. Additional analyses with binary step judgment and step-aligned clips indicate that the bottleneck is not merely fine-grained scoring or temporal localization, but modeling how continuous interactions update procedural state over time.

Xiyang Huang, Jiawei Lin, Keying Wu +9

School of Artificial Intelligence, Wuhan University · Center for Language and Information Research, Wuhan University · Southwest Jiaotong University +3

Video-Language Model Evaluation Multimodal Model Evaluation State Tracking

Apr 8, 2026

Where Did It Go Wrong? Process-Level Evaluation of Web Agents with Semantic State Tracking

Web agents act through long interaction sequences, yet existing benchmarks evaluate only terminal success, discarding all process information and offering little guidance on improvement. In this work, we conduct a process-level analysis of web agents. We introduce WebStep, a benchmark of 1,800 task instances with controlled difficulty and automatic semantic state tracking. Each website exposes a deterministic semantic MDP alongside the GUI: the agent operates on the interface, while the environment records high-level states and transitions in the background, enabling fine-grained analysis without manual annotation. Based on the semantic trajectory, we first show that process metrics reveal differences invisible to outcome evaluation: three agents whose success rates cluster within 34-37% diverge in exploration reach versus execution accuracy. Then, decomposing by skill characterizes the nature of these differences, exposing opposite per-skill rankings hidden within the same website: e.g., on Q&A, Claude CUA outperforms OpenAI CUA by 30% on navigation actions yet underperforms it by 6.7% on inspection, pinpointing a concrete skill to improve even within a domain. Bifurcation analysis further localizes the decisive error that loses the task and shows that this error is agent-specific rather than shared. Finally, these differences widen as tasks grow harder: success rate is similar on easy tasks but separates sharply as exploration becomes more demanding. Our process-level analysis opens a new avenue in web agent evaluation, providing fine-grained and actionable insight into where and how each agent should be improved. Project page: https://jiwanchung.github.io/webstep

Jiwan Chung, JiHyuk Byun, Vibhav Vineet +1

Yonsei University · Microsoft Research

Process-Based Agent Evaluation Agent Evaluation AI Agent Evaluation Web Agents Web Agent Benchmarks State Tracking

Apr 8, 2026

EchoChain: A Full-Duplex Benchmark for State-Update Reasoning Under Interruptions

Real-time voice assistants must revise task state when users interrupt mid-response, but existing spoken-dialog benchmarks largely evaluate turn-based interaction and miss this failure mode. We introduce EchoChain, a controlled benchmark for evaluating full-duplex state-update reasoning under mid-speech interruptions. EchoChain identifies three recurring failure patterns in post-interruption continuations: contextual inertia, interruption amnesia, and objective displacement. The benchmark generates scenario-driven conversations and injects interruptions at a standardized point relative to assistant speech onset, enabling controlled cross-model comparison. In a paired half-duplex control, total failures drop by 40.2% relative to interrupted runs, indicating that many errors are driven by state-update reasoning under interruption rather than task difficulty alone. Across evaluated real-time voice models, no system exceeds a 50% pass rate, showing substantial room for improvement in mid-generation state revision. EchoChain provides a reproducible benchmark for diagnosing state-update reasoning failures in full-duplex voice interaction.

Smit Nautambhai Modi, Gandharv Mahajan, Marc Wetter +1

Applied Machine Learning Research

State Tracking Voice Agent Evaluation Spoken Dialogue Systems Full-Duplex Spoken Dialogue Systems

Apr 7, 2026

The UNDO Flip-Flop: A Controlled Probe for Reversible Semantic State Management in State Space Model

State space models (SSMs) have been shown to possess the theoretical capacity to model both star-free sequential tasks and bounded hierarchical structures Sarrof et al. (2024). However, formal expressivity results do not guarantee that gradient-based optimisation will reliably discover the corresponding solutions. Existing benchmarks probe either monotonic state tracking, as in the standard Flip-Flop task, or structural nesting, as in the Dyck languages, but neither isolates reversible semantic state retrieval. We introduce the UNDO Flip-Flop task to fill this gap. By extending the standard Flip-Flop with an UNDO, the task requires a model to maintain an implicit bounded stack and recover historical states under non-monotonic update sequences. We evaluate one-layer and two-layer Mamba-2 under this framework. Both variants fail to acquire the provably expressible stack-based rollback mechanism, converging instead on a local toggle heuristic that inverts the current state rather than retrieving stored history. Under an adversarial retraction pressure test held within the training length distribution, the two-layer model collapses to 41.10% accuracy, which is below random chance. The results confirm systematic rather than incidental failure. Causal ablation shows that the bottleneck lies in retrieval, not storage. These results draw a clear line between what an architecture can in principle represent and what gradient descent reliably learns, a distinction that theoretical expressivity analyses alone cannot capture.

Hongxu Zhou

Erasmus Mundus Language and Communication Technologies Saarland University Saarbrücken, Germany

State Space Models State Tracking Neural Network Expressivity Selective SSMs