Next-State Prediction

Follow this topic Ask about this topic

Momentum

8 papers in the last four weeks, up 14% on the four weeks before. 0.1% of all new papers.

Jul 6Week of Sep 21

Latest papers 44

Sep 29, 2026stat.ML

Generative sequence modeling for infinite memory processes via predictive states

We consider estimating the one-step-ahead conditional distribution of a multivariate stochastic process. Many existing approaches rely on assumptions such as finite-range memory, sparsity, or additivity, which can be poorly suited to processes with long-range nonlinear interactions. However, without such structural assumptions, nonparametric estimation is challenging due to the curse of dimensionality. To address this challenge, we introduce a new estimation approach based on the predictive states of a process, possibly with infinite-range memory. We show that our estimator achieves fast convergence rates when the past history can be compressed into a low-dimensional statistic that is sufficient for predicting the future. Specifically, we show that the statistical complexity of the estimation problem is determined by the intrinsic dimension of the predictive state space. We establish guarantees for an instantiation of our method based on deep neural network estimators, and we support these theoretical results with experiments.

Michael Wieck-Sosa, Cosma Rohilla Shalizi

Department of Statistics & Data Science Carnegie Mellon University

Next-State Prediction Sequence Modeling Conditional Distribution

Sep 28, 2026cs.RO

From World Models to World Action Models: Rethinking Next-State Prediction

Predicting the next state is a core paradigm of World Models for modeling physical dynamics, emphasizing prediction fidelity. As World Models evolve into World-Action Models (WAMs), existing methods still fix the next state before training as RGB, a single latent feature, or a static combination of predefined targets, thereby constraining action learning to the inductive biases preserved by a particular representation. To address this limitation, we propose CF-WAM, a dynamic next-state prediction framework that samples visual, semantic, geometric, and interaction projections of the same future, standardizes them into a common video form, and supervises a unified WAM across these projections. The action-relevant constraints exposed by these projections accumulate across training steps, forcing WAM to capture the underlying state-transition structure that supports multiple projections of the same action-conditioned future. This dynamic mechanism also provides a natural cross-embodiment dynamics reference frame for Human and Robot learning. By jointly learning across different next-state parameterizations, heterogeneous Human and Robot experience can bypass appearance differences and directly contribute to shared state-transition learning, improving cross-embodiment generalization. Experiments show that CF-WAM improves both training efficiency and final control performance, while translating Human experience effectively into policy gains. CF-WAM achieves state-of-the-art performance on RoboCasa-GR1 with an average success rate of 82.50%, while reaching 82.65% on LIBERO-Plus and up to 84.00% in real-world evaluations.

Tingyu Yuan, Ziming Ji, Biaoliang Guan +9

CASIA · UCAS · BUPT +4

Efficient World-Action Model World Models Next-State Prediction Faster-Wam Cross-Embodiment Transfer World

Sep 28, 2026cs.LG

GradLev: Token-Parallel Test-Time Training Via Costate Prediction

Test-time training (TTT) allows a model to improve its predictions at inference time by updating weights after every observed token. However, sequential gra- dient writes make parallel training difficult. We observe that, given layer inputs and activation gradients (costates), online gradient descent admits exact parallel scans for both forward evaluation and reverse backpropagation. GradLev lever- ages this duality: a causal auxiliary network predicts costates across all tokens in parallel; associative scans compute the adapted weights and forward activations and propagate gradients backward; and the resulting gradient targets supervise the predictor via a consistency loss. Exact consistency guarantees exact recovery of the sequential online learner. At deployment, the auxiliary predictor is discarded, and the model updates natively via token-by-token forward and backward passes.

Bo Liu, Qiang Liu

The University of Texas at Austin

Test-Time Training Inference-Time Next-State Prediction Causal Graph

Sep 27, 2026cs.CL

Does Learning to Predict the World Help Agents Act? Auditing World-Model Post-Training

Predicting how an environment will change before acting is a natural route to better decision making for agents. Recent post-training methods therefore require agents to predict the next observation and turn that prediction into a reward or a direct supervision signal, which is called world model. Existing next-observation training methods help the agent to learn the environmental content. However, they additionally involve an optimization process, which may introduce several effects other than learning to predict the world. Consequently, where the performance gain comes from during the training process remains an open question. We answer this research question through replacing true next-observation targets with in-distribution mismatched observations during the training process. Across two interactive text environments, mismatched targets lower prediction accuracy by 15.3-61.6% relative to ground-truth targets, yet retain substantial task gains over the base model. Compared with the base model, trained models consider more candidate actions and exhibit less looping. We also introduce a setting that replaces prediction-based rewards with independent random signals. This training expands task coverage (pass@64) even when the reward carries no environment information. We also generalize this finding to VisualWebArena, where random-reward training raises pass@64 by 14.3% relative to the base model, without observation-matching rewards or an external multimodal teacher for reward construction.

Xinyu Che, Hang Yan, Yanchen Liu +5

Xi’an Jiaotong University · University of Southern California · University of the Chinese Academy of Sciences +1

Next-State Prediction World Models Reinforcement Learning Post-Training World Webarena Domains

Sep 23, 2026cs.NE

Spiking Neural Network Predicting Sequence of the External Worlds States in Model-Based Reinforcement Learning

This paper presents a spiking neural network (SNN) designed to predict the sequence of the external world states starting from the current world state. This SNN does not create the world dynamics model - instead it incorporates the SNN trained to predict the next world state and provides all mechanisms necessary to make the chain of predicted world states. These mechanisms are entirely spiking - they are implemented as spiking neuron ensembles. The present article describes this neuronal structure and tests its operation on a classic RL benchmark - ATARI ping-pong.

Mikhail Kiselev

Chuvash State University, Cheboxary, Russia

Spiking Neural Networks Next-State Prediction Model-Based Reinforcement Learning Webarena Domains

Sep 22, 2026eess.SP

Risk-Aware Online Conformal State Probing

AI-based autonomous agents, typically hosted at data centers, must acquire state information from robots or edge devices in order to issue informed control decisions. Managing uncertainty about the state is particularly consequential in safety-critical settings, in which average-case guarantees are insufficient. In this context, we study a sequential decision maker process that jointly decides which actions to take and when to probe given access to an arbitrary state prediction model. We propose online conformal state probing (OCSP), an action and probing policy that certifies worst-case reliability levels without relying on distributional assumptions. OCSP is designed to provably control the missed query error (MQE), i.e., the fraction of instances where probing would have been beneficial, while minimizing the probing rate. OCSP can be applied to existing pre-trained value-based control policies without requiring retraining or fine-tuning. We validate OCSP through numerical simulations to verify theoretical guarantees and to assess performance trade-offs as a function of the calibration of the state predictor.

Pietro Talli, Petar Popovski, Osvaldo Simeone

Institute for Intelligent Networked Systems, Northeastern University London · Connectivity Section, Department of Electronic Systems, Aalborg University

Autonomous Agents Stochastic Exploration Next-State Prediction Artificial Intelligence Agents Conformal Selection Sequential Decision Making

Sep 14, 2026cs.AI

When Should a World Model Move? Loss-Conditioned State Execution

We introduce loss-conditioned state execution, a model-agnostic method that decides whether to execute a world model's fixed feasible proposal or retain the current state. Predictive informativeness alone, however, does not establish whether an update will reduce downstream loss. Occurrence ranking can approach perfection while persistence remains the unique absolute-loss Bayes action. Two transition laws can also share occurrence information and conditional variance yet require opposite absolute-loss decisions. We formalize state movability as the existence of a loss-reducing feasible correction and distinguish it from the benefit of a particular proposal. Our method constructs a loss-specific feasible proposal from a predictive distribution and evaluates its groupwise bounded-loss gain over persistence on independent calibration units. The proposal is executed only in groups with a positive simultaneous lower confidence bound. For fixed proposals and groups with bounded unit losses, we prove that every accepted group has lower expected loss than persistence with high probability when calibration units are i.i.d. draws from the target population. Experiments on public forecasting and action-conditioned dynamics benchmarks show supported updates and a trade-off between certification and coverage. On 28,684 held-out M4 Monthly series, the method executes the proposal for 14.0% of series and achieves bounded loss 0.588, compared with 0.599 for persistence and 0.621 for always executing the proposal. The paired 95% bootstrap intervals for both comparisons lie below zero. In constrained forecasting of six unhealthy-inventory types from JD

\mbox{.}

com, a leading e-retailer in China, strong occurrence-ranking signal coexists with a loss-based preference for persistence, illustrating why event predictability and state execution must be evaluated separately.

Jintao Xu, Zhengyu Chen, Ben Zhang +2

Supply Chain Tech Team Y, JD.com

Next-State Prediction Feasibility World Models Persistence

Sep 11, 2026cs.RO

FARM: Reading Failure Signals from the Internal Predictive States of a Frozen Robotic World Model

Reliable robot deployment requires online failure monitoring, yet existing monitors mainly derive risk from proxy signals or train dedicated monitoring components. We ask whether the internal predictive states of a frozen pretrained robotic world model already contain directly decodable failure information. Failure-Aware Readout from World Models (FARM) trains only a 33,985-parameter supervised readout over frozen VLA-JEPA predictive states, producing step-wise failure scores and causal trajectory risk. Five-fold out-of-fold evaluation across seven source tasks reaches 85.68/88.59 pooled AUROC/AUPRC, and FARM gives the best Seen performance among 15 matched baselines on the 10-task benchmark. Across four real-robot populations on PIPER X, SO-101, and Franka, fixed-readout transfer and readout-only adaptation test deployment shifts without updating the predictive backbone. FARM also discriminates failures from partial causal histories and adds 0.2256 ms mean CUDA latency once the frozen state is available. These results support frozen predictive world-model states as reusable features for causal, transferable, and low-overhead execution monitoring.

Haoran Pei, Mingrui Luo, Senbao Wang +4

Institute of Automation, Chinese Academy of Sciences, Beijing, China · Harbin Institute of Technology, Harbin, China

Early Failure Prediction Next-State Prediction Readout

Sep 8, 2026cs.LG

Leveraging contextual events on structure-aware next activity prediction

Predictive process monitoring aims at forecasting various aspects of running processes. Among the different tasks, next activity prediction represents the most extensively investigated. However, only a limited number of existing approaches explicitly encode contextual information, i.e., the environmental conditions in which the process is executed, typically modeled through event log attributes or aggregated measures. In this paper, an approach based on the concept of Instance Graphs is introduced. To incorporate contextual process instances, several encoding strategies are proposed and evaluated by measuring their impact on prediction performance. For each encoding strategy, a set of prefix-Instance Graphs is generated and subsequently provided as input to a Graph Neural Network for the classification task. The proposed approach is evaluated on multiple real-world event logs, and the experimental results demonstrate that incorporating contextual process instances benefits prediction performance.

Alessandro Mele, Claudia Diamantini, Domenico Potena

Department of Information Engineering, Polytechnic University of Marche, Ancona, Marche, Italy

Next-State Prediction Context-Awareness Action Prediction

Sep 8, 2026cs.AI

WorldAgen: Unified State-Action Prediction with Test-Time World Model Training

How can vision-language-action (VLA) models adapt to new environments where world dynamics shift? While recent research has combined world modeling and action prediction to improve VLA performance, existing methods largely rely on pretraining on static datasets, without mechanisms for active adaptation at deployment time. As a result, these models often fail to generalize when deployed in unseen scenarios with novel object configurations or dynamics. We present WorldAgen, a unified framework that jointly learns world modeling and action prediction while enabling Test-Time Training (TTT) to adapt to new environments. WorldAgen employs a shared Transformer backbone with two heads: (1) a world model head that predicts future states from past state-action trajectories, and (2) an agent model head that predicts actions conditioned on task instructions. We design a Mixed Unidirectional Attention Mask to separate these two models. During test time, WorldAgen samples exploratory actions, collects ground-truth state transitions, and performs lightweight TTT updates to refine its world model. This adaptation improves the model's understanding of the environment and leads to more accurate action predictions. Experiments on the CALVIN and LIBERO benchmarks demonstrate that our baseline model achieves comparable, and in some cases superior, performance to current state-of-the-art approaches. Moreover, with TTT on a small number of samples, our method surpasses existing state-of-the-art models, highlighting the effectiveness of adapting world models at inference time.

Chi Wan, Kangrui Wang, Yuan Si +2

Northwestern University

Efficient World-Action Model Diffusion-Based Vision-Language-Actions Action Prediction World Models Next-State Prediction

Sep 7, 2026cs.CV

A Two-Stage Framework for Ego-Centric Key Object Identification via Object State Prediction

This paper presents a novel framework designed to enhance key object identification in autonomous driving. Existing methods primarily focus on either detecting objects independently or leveraging visual relationships, but they do not explicitly consider the ego vehicle's perspective in determining object importance. To address this gap, we propose a structured approach that integrates a virtual ego-vehicle representation and a modular object state predictor, enabling a more accurate estimation of object behaviors relative to the ego-vehicle. Subsequently, our framework employs spatial-temporal reasoning to refine key object identification, prioritizing objects based on their states and relative spatial information rather than relying solely on visual relationships. Experimental results on real-world driving datasets demonstrate the effectiveness of our approach in accurately detecting critical objects in complex traffic environments.

Shihong Ling, Yue Wan, Xiaowei Jia +1

School of Computing and Information, University of Pittsburgh, Pittsburgh, PA, USA

Autonomous Driving Naturalistic Driving Data Next-State Prediction

Aug 30, 2026cs.LG

How do World Models and Policies Compose in LLM Agents? A Joint Spectral and Behavioral Account

How do LLM agents come to both understand environments they act in and master tasks set within them? Through controlled experiments combining world-model training (next-state prediction) and policy training (reward maximization), we investigate this question. We dissect the resulting models through their additive parameter updates. Geometrically, we find effective world-model updates are low-rank and share an input-feature subspace with policy updates while writing to nearly orthogonal output directions, whether trained separately or sequentially. However, we find that, in projection interventions, the sequential update induces more robustness than separate policy RL when removing the world model's leading input directions, suggesting that it has learned alternative input pathways. Behaviorally, we find the sequentially trained agent explores a wider range of states and actions. Based on this, we ask: does policy training preserve world knowledge as well as it could? We probe this with training-free merging built on the geometrically motivated input basis plus an online world-model loss during policy RL, and show both improve over the untreated baseline. Our findings suggest world knowledge and task-directed ability can be learned in geometrically complementary forms, and that future post-training pipelines should consider how best to engineer the interface between them.

Ruize Xu, Xiao Yu, Yujin Tang +2

Dartmouth College · Columbia University

Large Language Model Agents World Models Offline Reinforcement Learning Next-State Prediction Goal-Directed Behavior Agent Behavior Modeling

Aug 20, 2026cs.LG

Orthogonal JEPA: Factorized Predictive States for Latent World Models

World models construct latent states that support prediction, planning, and reasoning about an underlying system. Joint-embedding predictive architectures (JEPAs) offer a direct way to learn such states by predicting targets in representation space instead of reconstructing every detail of the observation. Standard JEPAs, however, organize all predictable content through one target embedding and one prediction pathway. In complex systems, this monolithic state can allocate redundant capacity to dominant signals while providing weak or conflicting gradients to less dominant predictive structure. We introduce \method, a latent world-modeling framework based on orthogonal predictive factorization. Learned basis matrices analyze each target state into multiple components, and a dedicated prediction branch estimates each component from a shared context representation. Predictive regression preserves the factor magnitudes required for state synthesis, an orthogonality objective discourages repeated directions, factor-activity regularization maintains variation in projected targets, and online variance regularization discourages coordinate-wise encoder collapse. Predicted components are synthesized into a complete latent state that can be used by a readout, decoder, planner, or autoregressive rollout. The same predictive-state mechanism applies when the target is temporally future, spatially hidden, or another partial observation of the same system. Experiments on controlled vision, single-cell transcriptomics, longitudinal health records, continuous control, and molecular dynamics evaluate representation quality, forecasting, planning, and long-horizon stability.

Taoyong Cui, Pheng Ann Heng, Wanli Ouyang

The Chinese University of Hong Kong (CUHK)

Joint-Embedding Predictive Architectures Next-State Prediction Latent World Models World Models Regularization Single-Cell Rna

Aug 11, 2026cs.NE

Predictive Allostatic Organization in Recurrent and Spiking Agents Under Partial Observability

Adaptive behavior under partial observability depends on internal organization that carries information beyond the current observation. Drawing on Barrett and Miller's account of categorization as predictive, compressive, functionally organized, and allostatically constrained, we test whether recurrent and spiking agents develop internal states with corresponding computational properties. Agents operate in an energy-constrained foraging task requiring resource acquisition, threat avoidance, contact-dependent consumption, and regulation of an internal energy variable. In a frozen benchmark, learned agents outperform random and heuristic baselines; the trace-augmented recurrent policy is strongest overall, while spiking variants show stress-specific differences. Early internal dynamics predict later full-safe-efficient success above permutation baseline, reaching a maximum ROC-AUC of 0.802. Reduced PCA subspaces retain behaviorally relevant information. Feature-family controls show that predictive signal is distributed across trace, policy-head, internal-dynamics, observation, and allostatic variables, and low-energy state remains strongly decodable after explicit energy-related features are removed. Evaluation-time perturbations to temporal state, sensory information, operating conditions, and allostatic mechanisms alter behavior and/or internal prediction. Seed-balanced event probes show weaker but measurable information about future contact, successful consumption, and threat events, alongside strong low-energy decoding. We interpret this pattern as a computational analogue of predictive allostatic organization: distributed control regimes that are predictive, energy-sensitive, action-relevant, and partly causally involved, without claiming biological validation or discrete symbolic categories.

Frederick Hayes

Independent Researcher San Antonio, Texas, USA

Next-State Prediction Partial Observability Brain-Inspired Synergistic Framework Recurrence Spiking Neural Networks

Aug 7, 2026cs.AI

MemWM: Memory-Augmented Text-Based World Model

World models are increasingly used to support planning in agents by predicting how environment states evolve in response to agent actions. Yet fluent next-state predictions can still omit task-critical facts, corrupt product attributes, or apply incorrect transition rules. To address such systematic prediction errors, we introduce MemWM, a memory-augmented text-based world model. MemWM uses world memory, a curated memory bank of transition rules, state caches, and hard-to-predict facts, to condition next-state imagination. We evaluate factual state preservation with Structured State Fidelity (SSF), which scores predicted states through benchmark-specific facts and fields. Compared with SFT, memory-augmented training improves SSF by up to 206.3%. In the full planning setting, we keep the policy model frozen and provide policy-side world skill: retrieved task-level skills and step-wise corrective guidance for action selection. Across ALFWorld, WebShop, and ScienceWorld, memory-augmented agents improve downstream success over an SFT-trained world-model agent, with up to a 65.4% relative gain. Sensitivity analyses further show that retrieved memory improves task success and efficiency under different memory and action-budget settings.

Yujun Wang, Tao Zhang, Jinhe Bi +9

LMU Munich · Munich Center for Machine Learning (MCML) · Huawei Heisenberg Research Center +4

World Models Next-State Prediction Omninwm World Skills

Aug 6, 2026cs.CV

SR-JEPA: Learning Predictive Latent State in 3D Scenes

Joint-embedding predictive architectures learn by predicting latent representations of missing observations, yet many masked JEPAs are evaluated primarily through the encoders they produce. We ask what a trained predictive pathway itself infers when an entire entity is absent from a native 3D scene. We introduce SR-JEPA, a point-native JEPA for scene-scale point clouds whose original frozen predictive pathway can be queried at a supplied location. At evaluation, every point of one object is removed before encoding and replaced by the same shape-free 32-point query at its centroid. Training uses only self-contained 3D EMA targets: no reconstruction, semantic labels, language, or lifted 2D features. On 5,953 held-out ARKitScenes objects, the imputed latent reaches 43.13% semantic-identity macro accuracy, 22.18 points above the strongest floor. Randomizing the prediction path removes 9.78 points, while substituting matched donor context removes 21.98 points. On 8,570 Sr3D support pairs, the full latent reaches 41.15 AP; identity decoded from the missing-object latent, combined with anchor identity and geometry, reaches 39.37 AP, leaving an unresolved 1.78-point residual. These results reveal a queryable, compositional 3D predictive state: the model completes context-dependent entity content, which downstream computation combines with metric geometry.

Zihan Zhou, Qifu Wen, Xi Zeng

Boston University, Boston, MA, USA · Shanghai Jiao Tong University, Shanghai, China

Next-State Prediction Latent Variable Scene Understanding Exponential Moving Average

Aug 5, 2026cs.CV

Predict, Then Retrieve: Cross-Instance Future-State Retrieval from Video Prefixes

We introduce Predictive State Retrieval (PSR), a task in which a model observes a short video prefix and a temporal question about an object's future state, then retrieves instances from other videos or images that depict that state. Unlike action anticipation, which predicts a label, moment retrieval, which localizes an observed event within a video, or video generation, which synthesizes pixels, PSR combines anticipation with cross-instance retrieval across multiple temporal horizons. We construct a benchmark from four datasets with graded, human-validated ground truth, difficulty tiers, and an oracle ceiling. We also propose LFTR, a lightweight retriever with frozen encoders that predicts a question- and horizon-conditioned future latent and matches it in complementary semantic and visual spaces. A ceiling decomposition reveals a clear bottleneck: the true future state is highly retrievable once specified, whereas every predictor we evaluate, including a large multimodal language model with access to the prefix frames, remains far below the oracle. Thus, forecasting rather than perception is the central learnable challenge. LFTR narrows this gap at substantially lower inference cost, and ablations attribute its gains to cross-space fusion and hard-negative training rather than latent rollout. We release the benchmark, code, and evaluation scripts.

Quynh Vo, Thong Nguyen, Vinh-Hien Do +2

Centre for AI Research, VinUniversity · National University of Singapore

Future Video Prediction Next-State Prediction Long Videos Short Video Bursts Frozen Encoder

Aug 3, 2026cs.AI

Predictive Set Theory: A Generative Framework for Cognitive Architecture with Operationalized Core Mechanisms

Predictive processing theories portray the brain as a hierarchical prediction engine that minimizes prediction error, yet they lack operational definitions for the structure of a "prediction," the standardized response to a prediction error, and the mechanism that maintains consistency across successive updates. Bayesian cognitive science attempts to subsume all uncertainty under probabilistic belief updating, but it presupposes a closed hypothesis space and provides no generative account of how the objects over which probabilities are distributed become discrete, identifiable referents in the first place. This paper introduces Predictive Set Theory (PST), a formal generative framework that reconstructs cognitive architecture from first principles. PST anchors cognition in a minimal set of operations---a sensor formalized as an identity function, set-theoretic state refresh, and three fundamental forms of reference chains (reference, counter-reference, and semi-reference)---and rigorously derives core cognitive functions including state sequences, demand, comparison, efficiency, and finite-horizon probabilistic planning. Rather than modeling neural mechanisms, PST constitutes a design specification for any system that must maintain internal consistency while acting under incomplete information and irreversible risk. The framework offers novel resolutions to classical problems such as Russell's paradox, the cognitive status of Gödelian incompleteness, the grounding of negative feedback, and the comprehension of film editing. The primary purpose of this paper is to establish, through the public academic record, the originality and completeness of the Predictive Set Theory framework.

Yiyang Yu

Predictive Coding Cognitive Science Next-State Prediction Theory State-Tracking Generative Models

Aug 1, 2026cs.AI

Why Does the Future Branch? Identifiable Closure Tests for Stochastic Physical World Models

A calibrated stochastic world model can reveal how uncertain a future is without revealing why it branches. The same conditional future law can arise because an observation aliases physical states or because dynamics remain random after the declared full state is fixed. We prove that ordinary transitions cannot identify these two sources, even for a perfect probabilistic predictor. ClosurePairs makes them identifiable by crossing compatible microstates with repeated exogenous disturbances and estimating state, noise, and state-noise interaction variance. The central consequence is operational: under finite hierarchical sampling, forecast difficulty governs the useful compute scale, while the alias/process composition provides complementary information about its direction-resolving the current state or sampling future randomness. ClosurePairs recovers source attribution at unchanged likelihood, reduces equal-budget decomposition error in a nonlinear interaction benchmark, and supports observation-only routing. On exact-marginal MetaWorld twins, an output-only allocator is at chance while a Closure-supervised probe on frozen JEPA-WM features routes 89.8-100%. In an independent ManiSkill PushCube confirmation, a stochastic RSSM's outputs and latents remain at chance, whereas an RGB-only Closure probe routes 100% under both ID and geometry/camera OOD over five seeds, matching direct allocation rather than exceeding it. Across five unseen allocation menus, the same Closure probe routes 92.5%/90.4% ID/OOD with no new oracle labels, versus 37.9%/32.9% for a frozen direct allocator. ClosurePairs is therefore an identifiable, reusable mechanism target that cannot be recovered from forecast quality alone.

Yibin Dong

Shandong University

Closure Next-State Prediction World Models Random World

Jul 30, 2026cs.RO

One Future, Every Robot: Label-Efficient Collective-State Prediction with Decentralized JEPA

Decentralized robots often need a common view of what their team is becoming, even though each robot sees different evidence and cannot rely on a central estimate or output-level consensus. We ask whether compatible collective-state predictions can emerge under this constraint. Collective-State JEPA (CS-JEPA) trains every robot to predict the same fixed-width latent future from its own history and bounded neighbor messages, with no agreement loss; predictions and plans are never pooled at deployment. In a fresh independent replication, agreement improves for every seed and every evaluated split. Accuracy improves at the same time, ruling out the uninformative solution in which all robots merely collapse to one prediction: relative to capacity-matched raw-future reconstruction, collective-state error falls by 28.4 percent in distribution and by 64.4 to 75.6 percent under topology and swarm-size shift. Translation-free and crossed-pretraining controls preserve this joint result, while action-conditioned and rigid-body evaluations show that the receiver-local representation supports independent decisions. A shared latent future can therefore align decentralized predictions without consensus training while preserving useful, label-efficient information.

Alan-Barsag Gazzaev, Alexey Gavrilov, Sergey Muravyov

ITMO University, Saint Petersburg, Russia.

Next-State Prediction Video Joint Embedding Predictive Architecture S-Jepa Robot Systems

Jul 17, 2026cs.AI

SeerGuard: A Safety Framework for Mobile GUI Agents via World Model Prediction

Mobile graphical user interface (GUI) agents have demonstrated remarkable capabilities in automating complex tasks, yet they introduce critical safety risks because a single erroneous action can lead to irreversible consequences. Existing safety mechanisms are primarily reactive, lacking the ability to assess risks before execution. In this paper, we introduce SeerGuard, a consequence-aware safety framework designed to mitigate these risks through pre-execution instruction-level screening and action-level risk assessment. Specifically, the action-level assessment analyzes agent-proposed actions within current GUI states, anticipating likely outcomes to identify risks before they are executed. To enable these capabilities, we construct a unified safety-augmented world model (SAWM) via multi-task learning, integrating semantic next-state prediction with safety risk assessment. Extensive experiments demonstrate that SeerGuard generalizes effectively across diverse mobile GUI agents. On Qwen3-VL-8B-Instruct, it increases the safety-utility score from

0.191

to

0.596

at

ω=0.8

and reduces the risk-cost score from

0.347

to

0.135

at

α=0.8

. Further analyses on our SAWM validate the effectiveness of the instruction-level screening, alongside the capability of action risk assessment and next-state prediction.

Xue Yu, Bo Yuan, Kailin Zhao +3

JIUTIAN Research

Graphical User Interface Agents Probabilistic Safety Device Next-State Prediction World Models

Jul 6, 2026cs.AI

MoP-JEPA: Hard-Assigned Predictor Mixtures for Stochastic JEPA World Models

JEPA world models commonly predict the next latent state with one regressor. Under stochastic transitions, squared and cosine regression return the conditional mean and its normalized direction, respectively: a single compromise that may match no valid successor. MoP-JEPA instead uses

K

hard-assigned heads and a context-only router to produce a finite candidate set in one pass. On held-out OGBench transitions, graph search with single-output predictors succeeds on

0.02

--

0.09

of queries, whereas MoP-JEPA reaches

0.85

. To distinguish useful successors from indiscriminate coverage, we also measure verified-route success (\emph{realroute}), which checks after graph construction whether the proposal contains a path of real transitions. MoP-JEPA leads this same-protocol metric on all three mazes; an MDN attains high raw coverage but predicts many nonexistent edges.

Zhi Song, Ximing Xing, Zhenchao Tang +8

City University of Hong Kong, China · Tencent, China

Next-State Prediction World Model Planning S-Jepa Intermediate Latent States World Models

Jul 1, 2026cs.CL

The State-Prediction Separation Hypothesis

Transformers use the same forward computation stream to both predict the next token and store useful state for future token predictions. We formulate the \emph{state-prediction separation hypothesis}: disentangling the two roles yields better language modeling performance. We design a Transformer variant that uses two computation streams to separate the two functions, and conduct pretraining experiments across various scales. Our experiments show that state-prediction separation consistently offers better data and compute efficiencies, improving validation loss and outperforming standard Transformers by 2--3 percentage points on average on downstream tasks. We also conduct extensive empirical analysis that rules out potential confounders and demonstrates the fundamental difference in the gradients our design entails.

Giovanni Monea, Nathan Godey, Kianté Brantley +1

†Cornell University · ⋄Harvard University

Transformer Architectures Next-State Prediction Separation

Jun 24, 2026cs.CL

Beyond Next-Observation Prediction: Agent-Authored World Modeling for Sequential Decision Making

Recent studies on world modeling for Large Language Model (LLM) agents typically formulate the learning objective as next-observation prediction. However, this objective ties supervision to what a transition happens to reveal, which may omit the dynamics most relevant to the agent's current decision. To bridge this gap, we propose Agent-Authored World Modeling (AAWM), a training procedure that constructs supervision from the policy's own decision needs. Specifically, at each state, the agent identifies what it needs to understand about the environment before acting. These needs drive the retrieval of relevant transition evidence across trajectories, which is then synthesized into training targets that capture decision-oriented dynamics instead of reconstructing the next observation. This aligns the training objective with the dynamics the policy needs before acting, not with the contents of the next observation. Experimental results validate the effectiveness of AAWM across multiple environments and training settings. These results show that decision-aware world-model targets provide a more effective learning signal than next-observation prediction.

Guangfeng Cai, Kaibing Yang, Shuo He +4

Southeast University · Meituan

Next-State Prediction World Models Sequential Decision Making

Jun 14, 2026cs.AI

Mind-Studio: Executable World Models with Lookahead Evaluation for Partially Observable Games

World-model synthesis aims to turn interaction experience into an internal model of environment dynamics. Existing symbolic approaches often fit observed transitions or mixtures of local rules, but they do not produce a complete executable program that can run independently of the real environment. We present Mind-Studio, a framework that synthesizes executable pygame-style world models from state-action-next-state trajectories using large language models. Mind-Studio combines entropy-selected traces with a lightweight game skill file containing object, action, and static scene information extracted from screenshots. We evaluate synthesis quality with a K-step lookahead fidelity protocol that compares generated world-model rollouts against Real-ALE rollouts from the same state. On Montezuma's Revenge, Mind-Studio improves chosen-action next-state prediction from 0.3% for PoE-World to 48.7% while verifying 5 of 8 subgoals; across Alien, Assault, and Skiing, it achieves stronger branch-level fidelity than prior learned lookahead sources.

Yifei Dong, Mingen Zheng, Linquan Wu +2

Hong Kong University of Science and Technology · City University of Hong Kong · University of Edinburgh +1

World Models Synthetic Environments Next-State Prediction Synthesis Lookahead Ecosystems

Jun 11, 2026cs.LG

Exposure Bias as Epistemic Underidentification in Recursive Forecasting

Recursive multi-step forecasting is usually framed as distribution shift: models are trained on observed histories but deployed on their own predictions. We show this framing is incomplete by proving that, under partial observability or state truncation, recursive rollout is also an epistemic underidentification problem. Even with deterministic latent dynamics, one-step Bayes supervision identifies behavior only on observed contexts and need not identify the deployed recursive predictor once rollout queries self-generated induced states whose correct local targets are not determined by numeric state alone. We formalize this with induced states

Z

and provenance variables

P

, and derive a decomposition of induced-state error into teacher-forcing/rollout mismatch, representation--class approximation, and provenance information gaps. Empirically, we show that rollout enters a distinct induced-state regime, that fixed induced states define a distinct local corrective task, and that closed-loop gains arise not only from local adaptation but also from changing the induced states visited during rollout. Using a simple binary provenance encoding, provenance-aware correction can further improve performance, though gains are conditional rather than uniform. These results recast exposure bias as reasoning under self-induced epistemic uncertainty.

Riku Green, Zahraa S. Abdallah, Telmo M Silva Filho

University of Bristol, UK

Next-State Prediction Dynamic Epistemic Logic Epistemic Asymmetry

Jun 9, 2026cs.RO

Bridging the sim2real gap in the table tennis robot with a transformer-based ball states predictor

Robotic table tennis is a representative benchmark for high-speed, closed-loop robotic control in dynamic environments, where accurate and fast prediction of ball states is critical for reliable planning and control. Physics-based approaches rely heavily on accurate parameter identification and precise initial state, while learning-based methods often struggle to capture long-range temporal dependencies and are typically trained on limited or simulated data. We propose a transformer-based framework for table tennis ball state prediction that leverages attention mechanisms to model long-range temporal correlations directly from historical observations, without relying on explicit flight or bounce models. To support robust learning and generalization, we collected a large-scale real-world dataset from players of varying skill levels and diverse ball cannon configurations. The combination of a high-capacity transformer architecture and extensive real-world data enables accurate long-horizon forecasting. Building on this capability, we introduce a plug-and-play sim-to-real transfer strategy, Swap Predictor at Deployment (SPAD), which replaces the physics-based simulator used during training with the proposed real-world-trained predictor at deployment, improving the sim-to-real transferability of the policy without requiring retraining. We demonstrate that this simple substitution effectively narrows the sim-to-real gap while preserving the efficiency and scalability of simulation-based training.

Yin Bi, Christian Conti, Bilan Yang +3

Sony AI, Zürich, Switzerland · Sony AI, Tokyo, Japan

Table Tennis Robot Sim-To-Real Reinforcement Learning Sim-To-Real Gap Next-State Prediction Human Motion Prediction Physics Simulation+3

Jun 8, 2026cs.AI

Predictive Assistance and the Temporal Dynamics of Exploratory Compression

Classical theories of cognition describe problem solving as exploratory search through structured problem spaces in which repeated interaction gradually compresses search into efficient representational structures. Predictive artificial intelligence systems introduce a distinct regime in which stabilization may occur before exploratory diversification unfolds, supplying solutions and decision trajectories prior to internally generated search. This paper develops a geometric dynamical framework in which attention evolves over a landscape of strategies shaped by stabilizing drift, endogenous exploratory perturbation, and responsiveness-gated learning. Predictive assistance is modeled as a process of exogenous exploratory compression that stabilizes trajectories before self-generated exploration broadens the accessible regions of strategy space. The framework yields three main results. First, sustained predictive stabilization reduces exploratory responsiveness by attenuating the effective influence of intrinsic perturbations even when exploratory variability remains present. Second, curvature accumulates and relaxes asymmetrically, producing hysteresis and delayed recovery of exploratory mobility after assistance withdrawal. Third, developmental outcomes depend critically on the timing of stabilization, with early intervention narrowing future exploratory traversal before broad representational diversification has occurred. The framework generates empirically testable predictions concerning exploratory entropy, premature convergence, and delayed recovery following predictive stabilization. More broadly, the results suggest that predictive systems may reshape the geometry of exploratory cognition itself.

Balaraju Battu

European University Institute, Florence, Italy · New York University Abu Dhabi, UAE

Predictive Coding Stochastic Exploration Next-State Prediction Temporal Dynamics Task-Aware Compression

May 29, 2026cs.LG

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

Timestep Embeddings Time Series Next-State Prediction

May 28, 2026cs.LG

Early Prediction of Future Behavioral Strategy from Process Traces

Adaptive systems often need to make task-specific decisions about people from limited evidence: a tutor may need to anticipate how a learner will approach a new problem, a game may need to adapt when a player enters a new level, and a human-AI system may need to infer whether a partner will persist with a plan or switch goals. These decisions depend on person-level tendencies that shape how people solve related tasks, but such tendencies are difficult to infer from standard behavioral evidence. One approach is to use aggregate outcome summaries, such as scores, completion rates, or productivity; these summaries are compact and available across tasks, but can collapse distinct behavioral processes into similar outcomes. Another approach is to use process-level traces, which record how behavior unfolds; however, process modeling within one task can entangle stable person-level tendencies with task-specific layout and affordances. In this work, we study early cross-task behavioral inference: whether partial source-task process traces can reveal transferable person-level structure that predicts strategy in a held-out target task. We introduce a Process-Level Latent Variable Model (PLVM), which encodes task-specific traces and fuses them into a shared person-level latent representation for cross-task prediction. In PowerWash Simulator, a naturalistic telemetry dataset of human gameplay, PLVM uses partial traces from two cleaning tasks to predict locally persistent Zone Planner behavior versus frequent Zone Hopper behavior in the held-out Fire Station level. Controlled simulations with known latent types show that cross-task fusion helps when source tasks reveal complementary dimensions of a shared latent process. These results suggest that process-level cross-task modeling can support early prediction of target-task strategy when observing sufficient target-task behavior is impractical.

Robert Kasumba, Dennis Barbour, Chien-Ju Ho

Division of Computational and Data Sciences Washington University in Saint Louis Saint Louis, MO 63130 · Department of Biomedical Engineering Washington University in Saint Louis Saint Louis, MO 63130 · Department of Computer Science Washington University in Saint Louis Saint Louis, MO 63130

Behavioral Foundation Models Next-State Prediction Traces

May 27, 2026q-bio.NC

Exploratory Experience Shapes the Geometry of Predictive Representations

Active sensing links behavior and learning through an action-perception loop: actions determine the observations used to update internal predictive models of perception, which subsequently guide the next actions. Predictive-coding frameworks provide a natural way to model this process, since internal representations are continuously updated to predict future observations. Here, we ask how exploratory and exploitative behavioral strategies shape these internal predictive representations. We build an online learning agent in a tree-like maze with a controllable parameter regulating the balance between exploratory and exploitative regimes. The agent updates a predictive-coding-based perception model from experience generated by its own behavior. The model predicts both future maze states and reward probability, allowing the agent to select actions either by expected information gain during exploration or by predicted reward during exploitation. We show that the resulting internal predictive representations depend strongly on the agent's behavioral regime. Exploratory agents develop representations that are more spatially organized and better preserve the structure of maze transitions in latent space. In contrast, exploitative agents learn less organized representations. We then train this predictive model on natural trajectories of water-deprived mice navigating the same maze and compare the resulting representations with those learned from agent trajectories. More exploratory mice show representational geometries that closely match those of exploratory agents, whereas mice with more restricted visitation patterns resemble reward-driven, exploitative agents. Together, these findings suggest that exploration enables predictive models to form generalized internal representations by organizing latent space around both spatial location and transition context in artificial agents and animals.

Kseniia Shilova, Abdelrahman Sharafeldin, Advay Balakrishnan +1

School of Mathematics Georgia Institute of Technology Atlanta, GA 30332 · College of Computing Georgia Institute of Technology Atlanta, GA 30332

Next-State Prediction Stochastic Exploration Perception Pipeline Fuzzy Cognitive Map

May 20, 2026cs.CV

Grounding Driving VLA via Inverse Kinematics

Existing Driving VLAs predict trajectories while largely ignoring their visual tokens -- a phenomenon we trace not to insufficient training but to a structurally ill-posed task formulation. We show that trajectory recovery, when viewed through the lens of inverse kinematics, requires both a current and a future visual state as boundary conditions; existing VLAs supply only the former, which encourages the model to shortcut through ego status and text commands alone. To address this, we re-design Driving VLA in the style of an inverse kinematics solver. First, a next visual state prediction objective that requires the LLM to predict the future visual scene provides dense visual supervision and suppresses shortcut paths. Second, a separate Inverse Kinematics Network (a cross-attention-based conditional diffusion model) that takes only the current and future visual states as input is designed to suppress reliance on ego status and textual shortcuts during trajectory decoding. With this simple prescription alone, our 0.5B-scale model recovers visual grounding and reaches trajectory planning performance comparable to 7B--8B VLAs more than an order of magnitude larger, on both the closed-loop NAVSIM-v2 and the nuScenes benchmarks. Extensive analysis further shows that this improvement stems from a recovered ability to exploit visual features, with the effect being most pronounced in dynamic driving situations such as turning.

Junsung Park, Hyunjung Shim

Korea Advanced Institute of Science and Technology KimJaeChul AI Graduate School 18, Taebong-ro, Seocho-gu, Seoul, South Korea

Dynamic Driving Scenes Trajectory Generation Weak Visual Grounding Inverse Kinematics Next-State Prediction Text-Conditioned Diffusion Model

May 19, 2026cs.LG

Learning with Foresight: Enhancing Neural Routing Policy via Multi-Node Lookahead Prediction

Neural policies have shown promise in solving vehicle routing problems due to their reduced reliance on handcrafted heuristics. However, current training paradigms suffer from a fundamental limitation: they primarily focus on next-node prediction for solution construction, resulting in myopic decision-making that undermines long-horizon planning capacity. To this end, we introduce Multi-node Lookahead Prediction (MnLP), a novel training strategy that extends the supervised learning paradigm to predict multiple future nodes simultaneously. We incorporate causal and discardable MnLP modules that operate exclusively during training, facilitating models to anticipate multi-step decisions while preserving inference-time efficiency. By incorporating multi-depth auxiliary supervision into the loss function, MnLP equips neural policies with the ability of long-range contextual understanding. Experimentally, MnLP outperforms existing training methods, improving the generalization capability of neural policies across various problem sizes, distributions, and real-world benchmarks. Moreover, MnLP can be seamlessly integrated into diverse neural architectures without introducing additional inference overhead.

Xia Jiang, Yaoxin Wu, Yew-Soon Ong +1

Eindhoven University of Technology · Nanyang Technological University · Agency for Science, Technology and Research (A*STAR)

Neural Policies Long-Horizon Planning Ego-Trajectory Prediction Next-State Prediction Foresight

May 16, 2026cs.LG

Mechanism Learning: Prototype-Anchored Mechanism Inference for Scientific Forecasting

Scientific forecasting typically relies on direct state prediction, an approach that grows brittle under data scarcity, extended horizons, non-stationary dynamics, or high-dimensional complexity. While raw state trajectories are highly sensitive in these regimes, underlying local evolution rules often exhibit robust reusability. We introduce mechanism learning, a framework that forecasts future states by estimating the currently active local mechanism. Our method compresses local spatiotemporal fragments into mechanism descriptors, forming a data-driven, structured mechanism space where proximity reflects similar local evolution rules. To ground these estimates in observed data, we utilize prototype anchors, a set of representative mechanisms that sparsely cover the space of local rules. We evaluate this approach on Burgers dynamics, WeatherBench2, and Lorenz96. Empirically, the learned mechanism spaces resist collapse and maintain strong local consistency. Compared to direct prediction and other models including FNO, NODE, LSTM, and reservoir-family methods, our framework demonstrates predictive gains in fragile regimes: it significantly improves switching stability in Burgers dynamics and achieves state-of-the-art performance both under the scarce-data fixed-horizon WeatherBench2 protocol and in intermediate-complexity Lorenz96. Ablation studies and drift diagnostics confirm that these improvements are driven by finite prototype anchoring rather than sheer latent capacity. Together, these results establish mechanism learning as a principled, robust alternative to direct state prediction in forecasting complex systems.

Qian Jiang, Liping Sun

School of Computing · The Australian National University · Canberra, ACT 2601, Australia +3

Retrieval-Augmented Forecasting Next-State Prediction Evolutionary Optimization Methods

May 15, 2026cs.LG

From Observed Viability to Internal Predictive Approximation: A Single-Subject Latent-Space Analysis of Gait Dynamics Under Occlusal Constraint

Understanding adaptive biomechanical systems requires distinguishing observable performance, static multivariate representation, longitudinal displacement, and internal approximation of observed change. This study introduces Level 5, which examines whether the M1-M2 transformation observed in a single-subject gait dataset can be approximated within a selected PCA representation. Gait was recorded with instrumented insoles in a participant with Parkinson's disease under six occlusal observational probes during two sessions eleven weeks apart. A simplified feed-forward neural network was trained to approximate M2 PC1-PC2 coordinates from M1 coordinates, occlusal-probe descriptors, and the longitudinal-transition indicator. In the core analysis aligned with Level 4, the model preserved the Euclidean centroid-displacement hierarchy dOC3 < dONL < dOC2.5. In the extended six-probe analysis, it preserved the broad structure of the exploratory ordering. Held-out M2 and leave-condition-out analyses provided internal tests beyond the full-dataset fit, while a within-session analysis described probe positions relative to ONL. The term predictive is used only in a restricted methodological sense. The model does not provide prospective clinical prediction, patient-level forecasting, or generalization to unseen individuals. Occlusal conditions are treated as observational probes applied during measurement, not as continuous causal drivers of longitudinal evolution. The findings are exploratory, retrospective, representation dependent, and non causal. They do not establish causal occlusal effects, validated viability thresholds, therapeutic superiority, distinct physiological states, or generalizable predictive validity.

Jacques Raynal, Pierre Slangen, Elsa Raynal +1

Laboratory of Bioengineering and Nanosciences (LBN), University of Montpellier, France · 2EuroMov Digital Health in Motion, University of Montpellier, IMT Mines Alès, Alès, France · 3Certified Sophrologist and Dental Assistant, Sensorimotor Practice, Montpellier, France +1

Gait Dynamics Biomechanics Next-State Prediction Occlusal Constraint Long-Term

May 12, 2026cs.RO

World Action Models: The Next Frontier in Embodied AI

Vision-Language-Action (VLA) models have achieved strong semantic generalization for embodied policy learning, yet they learn reactive observation-to-action mappings without explicitly modeling how the physical world evolves under intervention. A growing body of work addresses this limitation by integrating world models, predictive models of environment dynamics, into the action generation pipeline. We term this emerging paradigm World Action Models (WAMs): embodied foundation models that unify predictive state modeling with action generation, targeting a joint distribution over future states and actions rather than actions alone. However, the literature remains fragmented across architectures, learning objectives, and application scenarios, lacking a unified conceptual framework. We formally define WAMs and disambiguate them from related concepts, and trace the foundations and early integration of VLA and world model research that gave rise to this paradigm. We organize existing methods into a structured taxonomy of Cascaded and Joint WAMs, with further subdivision by generation modality, conditioning mechanism, and action decoding strategy. We systematically analyze the data ecosystem fueling WAMs development, spanning robot teleoperation, portable human demonstrations, simulation, and internet-scale egocentric video, and synthesize emerging evaluation protocols organized around visual fidelity, physical commonsense, and action plausibility. Overall, this survey provides the first systematic account of the WAMs landscape, clarifies key architectural paradigms and their trade-offs, and identifies open challenges and future opportunities for this rapidly evolving field.

Siyin Wang, Junhao Shi, Zhaoyang Fu +11

1Fudan University · 2Shanghai Innovation Institute · 3National University of Singapore

Recent World-Action Models World Models Embodied Artificial Intelligence Action Generation Next-State Prediction Egocentric Video+1

May 7, 2026cs.LG

BRICKS: Compositional Neural Markov Kernels for Zero-Shot Radiation-Matter Simulation

We introduce a new strategy for compositional neural surrogates for radiation-matter interactions, a key task spanning domains from particle physics through nuclear and space engineering to medical physics. Exploiting the locality and the Markov nature of particle interactions, we create a \emph{next-particle prediction} kernel using hybrid discrete-continuous transformer models based on Riemannian Flow Matching on product manifolds. The model generates variable-sized typed sets of particles and radiation side effects that are the result of the interaction of an incident particle with a material volume. The resulting kernel can be composed to simulate unseen large-scale material distributions in a zero-shot manner. Unlike mechanistic simulators, our model is designed to be differentiable, provides tractable likelihoods for future downstream applications. A significant computational speed-up on GPU compared to CPU-bound mechanistic simulation is observed for single-kernel execution. We evaluate the model at the kernel level and demonstrate predictive stability over multi-round autoregressive rollouts. We additionally release a novel 20M-event radiation-matter interaction dataset for further research.

Richard Hildebrandt, Evangelos Kourlitis, Baran Hashemi +7

Technical University of Munich · Max-Planck Institute for Mathematics in the Sciences, Leipzig, Germany · SLAC National Accelerator Laboratory +3

Nuclear Data Physics Simulation Neural Fields Next-State Prediction

Apr 30, 2026cs.RO

Predictive Spatio-Temporal Scene Graphs for Semi-Static Scenes

We have seen tremendous recent progress in our ability to build "spatio-semantic" representations that enable robots to perform complex reasoning across geometry and semantics. However, the vast majority of these methods lack any ability to perform reasoning across time. This is a desirable property in situations where a robot repeatedly observes an environment where instances may change in between observations, but in a structured way. Consider as an example a home environment where the location of a mug typically moves from the cupboard to a countertop to the sink and then back to the cupboard on a daily basis. We should be able to learn this cyclic behavior and use it to predict the state of the mug in the future. In this work, we propose a method that is able to perform this type of tempo-spatio-semantic reasoning. Underpinning the method is a filter, Perpetua

^*

, that performs Bayesian reasoning on the states of the environment that are observed over time. This filter is integrated within a 3D scene graph structure that we call PredictiveGraphs, where nodes represent objects and edges function as Perpetua

^*

filters encoding spatio-semantic relationships. We validate the method in both simulation and real-world dynamic navigation tasks, where our real world experiments consist of an environment that is undergoing semi-static changes at a bi-hourly frequency over a period of three weeks. In both settings, we demonstrate that our method outperforms baselines in predicting future environment states, even in the presence of distributional shifts.

Miguel Saavedra-Ruiz, Charlie Gauthier, Kumaraditya Gupta +4

Department of Computer Science and Operations Research, Universit´e de Montr´eal, Montr´eal, QC, Canada. · Mila - Quebec AI Institute, Montreal, QC, Canada. · Independent Researcher. +1

Spatio-Temporal Scene Graphs Spatio-Temporal Reasoning 3D Scene Graphs Next-State Prediction Object Goal Navigation Robot Systems

Mar 3, 2026cs.LG

What Capable Agents Must Know: Selection Theorems for Robust Decision-Making under Uncertainty

As artificial agents become increasingly capable, what internal structure is necessary for an agent to act competently under uncertainty? Classical results show that optimal control can be implemented using belief states or world models, but not that such representations are required. We prove quantitative "selection theorems" showing that strong task performance (low average-case regret) forces world models, belief-like memory and -- under task mixtures -- persistent regime-tracking variables resembling functional primitives of emotion, along with informational modularity under block-structured tasks. Our results cover stochastic policies, partial observability, and evaluation under task distributions, without assuming optimality, determinism, or access to an explicit model. Technically, we reduce predictive modeling to binary "betting" decisions and show that regret bounds limit probability mass on suboptimal bets, enforcing the predictive distinctions needed to separate high-margin outcomes. In fully observed settings, this yields approximate recovery of the interventional transition kernel; under partial observability, it implies necessity of predictive state and belief-like memory, addressing an open question in prior world-model recovery work.

Aran Nayebi

Machine Learning Department and Neuroscience & Robotics Institutes, Carnegie Mellon University, Pittsburgh, Pennsylvania, USA

Partially Observable Markov Decision Process Next-State Prediction Action Selection Uncertainty

Jan 26, 2026cs.LG

Toward Learning POMDPs Beyond Full-Rank Actions and State Observability

We are interested in enabling autonomous agents to learn and reason about systems with hidden states, such as locking mechanisms. We cast this problem as learning the parameters of a discrete Partially Observable Markov Decision Process (POMDP). The agent begins with knowledge of the POMDP's actions and observation spaces, but not its state space, transitions, or observation models. These properties must be constructed from a sequence of actions and observations. Spectral approaches to learning models of partially observable domains, such as Predictive State Representations (PSRs), learn representations of state that are sufficient to predict future outcomes. PSR models, however, do not have explicit transition and observation system models that can be used with different reward functions to solve different planning problems. Under a mild set of rankness assumptions on the products of transition and observation matrices, we show how PSRs learn POMDP matrices up to a similarity transform, and this transform may be estimated via tensor decomposition methods. Our method learns observation matrices and transition matrices up to a partition of states, where the states in a single partition have the same observation distributions corresponding to actions whose transition matrices are full-rank. Our numerical experiments suggest that explicit observation and transition likelihoods can be leveraged to generate new plans for different goals and reward functions after the model has been learned. We also show that learning a POMDP beyond a partition of states is impossible from sequential data by constructing two POMDPs that agree on all observation distributions but differ in their transition dynamics.

Seiji Shaw, Travis Manderson, Chad Kessens +1

MIT Computer Science and Artificial Intelligence Lab, 51 Vassar St, Cambridge, MA 02139, USA · DEVCOM Army Research Laboratory 2800 Powder Mill Road, Adelphi, MD 20783, USA

Partially Observable Markov Decision Process Markov Decision Processes Next-State Prediction Partial Observability Transitions Reward Functions

Oct 16, 2025cs.LG

Why Do LLM Agents Fail in Exploring New Environments? A World-Modeling Perspective

Large Language Models (LLMs) as agents often fail to improve in new environments. We identify and characterize a failure mode we call exploration collapse: under reinforcement learning (RL) in environments whose states are unfamiliar to the policy, Pass@k, the probability that at least one of k sampled trajectories succeeds, drops markedly over training even as Pass@1 edges up, revealing increasingly brittle exploration; environments closer to the pretraining distribution show no such decline. We trace this collapse to weak grounding in environment states and dynamics, and study a simple remedy: explicitly teaching the agent to estimate the current state and predict its transitions before optimizing for reward. We instantiate it as SPA, an explore-then-exploit recipe that cold-starts the policy with a Self-Experience supervised finetuning (SFT) stage, collecting the model's own interaction trajectories and supervising state and next-state prediction, and then runs standard RL. The resulting world model serves as a grounded initialization for RL rather than an inference-time planner. Across unseen environments, SPA consistently and substantially improves over vanilla RL: for example, it raises the Sokoban success rate from 25.6% to 59.8% on Qwen2.5-1.5B-Instruct, letting sub-3B models surpass a 20B baseline on these tasks. Controlled studies indicate that the gains track four factors: grounded state representations, explicit transition modeling, self-experience trajectories from a sufficiently strong exploration policy, and adequate coverage of transition data.

Shiqi Chen, Tongyao Zhu, Zian Wang +8

City University of Hong Kong · National University of Singapore · The Hong Kong Polytechnic University +5

Large Language Model Agents Next-State Prediction World Models Dynamic Environments

Apr 8, 2025cs.LG

Information Thermodynamics of Agents: The Work Capacity of Channels with Memory

Predicting future observations plays a central role in machine learning, biology, economics, and many other fields. It lies at the heart of organizational principles such as the variational free energy principle and, based on the second law of thermodynamics, has even been shown to be necessary for reaching the fundamental energetic limits of information processing on a tape. While the usefulness of the predictive paradigm is undisputed, complex adaptive systems that interact with their environment are more than just predictive machines: they have the power to act upon their environment and cause change. In this work, we develop a framework to analyze the thermodynamics of information processing in percept-action loops, a model of agent-environment interaction, allowing us to investigate the thermodynamic implications of actions and percepts on equal footing. To this end, we introduce the concept of work capacity, defined as the maximum rate at which an agent can expect to extract work from its environment. Our results reveal that work-efficient agents must balance prediction and forgetting. This highlights a fundamental departure from the thermodynamics of passive observation, suggesting that prediction and energy efficiency may be at odds in active learning systems.

Lukas J. Fiderer, Paul C. Barth, Isaac D. Smith +1

Universität Innsbruck, Institut für Theoretische Physik, Technikerstraße 21a, A-6020 Innsbruck, Austria

Thermodynamics Free Energy Principle Next-State Prediction Perception Pipeline Channel

May 29, 2024cs.LG

Active Exploration via Autoregressive Generation of Missing Data

We pose uncertainty quantification and exploration in online decision-making as a problem of training and generation from an autoregressive sequence model, an area experiencing rapid innovation. Our approach rests on viewing uncertainty as arising from missing future outcomes that could be revealed through action choices, rather than from unobservable latent parameters of the environment. This reformulation aligns naturally with modern machine learning capabilities: we can i) train generative models through next-outcome prediction rather than fit explicit priors, ii) assess uncertainty through autoregressive generation rather than sampling latent parameters from posteriors, and iii) adapt to new information by extending the sequence model's context rather than explicit posterior updating. Our main theoretical result establishes a reduction from online decision-making to offline next-outcome prediction: Bayesian regret is controlled directly by the sequence model's offline prediction loss, without requiring an explicit latent-variable posterior. Experiments, including a semi-synthetic news recommendation task, show that autoregressive generation produces calibrated epistemic uncertainty and enables effective exploration by using article text as prior information to focus exploration on resolving remaining uncertainties.

Tiffany Tianhui Cai, Hongseok Namkoong, Daniel Russo +1

Department of Statistics Columbia University New York, NY 10025, USA · Decision, Risk, and Operations Division Columbia Business School New York, NY 10025, USA · Department of Mathematics Imperial College London London SW7 2AZ, United Kingdom

Stochastic Exploration Learning-Augmented Algorithms Autoregressive Model Model-Based Reinforcement Learning Autoregressive Generation Exploration+3

Aug 25, 2023eess.SY

From system models to class models: An in-context learning paradigm

Is it possible to understand the intricacies of a dynamical system not solely from its input/output pattern, but also by observing the behavior of other systems within the same class? This central question drives the study presented in this paper. In response to this query, we introduce a novel paradigm for system identification, addressing two primary tasks: one-step-ahead prediction and multi-step simulation. Unlike conventional methods, we do not directly estimate a model for the specific system. Instead, we learn a meta model that represents a class of dynamical systems. This meta model is trained on a potentially infinite stream of synthetic data, generated by simulators whose settings are randomly extracted from a probability distribution. When provided with a context from a new system-specifically, an input/output sequence-the meta model implicitly discerns its dynamics, enabling predictions of its behavior. The proposed approach harnesses the power of Transformers, renowned for their \emph{in-context learning} capabilities. For one-step prediction, a GPT-like decoder-only architecture is utilized, whereas the simulation problem employs an encoder-decoder structure. Initial experimental results affirmatively answer our foundational question, opening doors to fresh research avenues in system identification.

Marco Forgione, Filippo Pura, Dario Piga

IDSIA Dalle Molle Institute for Artificial Intelligence USI-SUPSI, Via la Santa 1, CH-6962 Lugano-Viganello, Switzerland.

System Identification In-Context Learning Next-State Prediction Meta-Learning Sequence Modeling Decoder Layers+1