World Models & Planning - Weekly Roundup

A query optimization framework that integrates a Graph Transformer with the model-based reinforcement learning (RL) algorithm MuZero, which converts SQL queries into heterogeneous graphs containing tables, predicates, and join operators and demonstrates its practical effectiveness and scientific value for building high-performance, adaptive intelligent database systems.

This standard approach to process mining, built on the stochastic language of an event log, reports only the assumptions of its discovery algorithm, because every such log is explained equally well by a model with no concurrency at all.

This work implements two representative architectures --- the Simplified Graph Convolution (SGC) and Linear Graph Convolution (LGC) models and evaluates them on open benchmark graph datasets and semi-supervised learning tasks using quantum simulation and presents a cost gradient analysis that identifies the tasks for which the models are trainable.

This work proposes OPTED (on-policy fine-tuning for end-to-end driving) which decouples reinforcement learning from the post-training of the end-to-end policy: a privileged teacher is trained using RL on vectorized inputs (HD-map and bounding boxes) which provides supervision to the pre-trained student during closed-loop post-training.

REARL, a closed-loop simulation enhancement framework that integrates real traffic data with large language model (LLM) and modulates the simulated vehicle with reference to that real action, is proposed.

A query optimization framework that integrates a Graph Transformer with the model-based reinforcement learning (RL) algorithm MuZero, which converts SQL queries into heterogeneous graphs containing tables, predicates, and join operators and demonstrates its practical effectiveness and scientific value for building high-performance, adaptive intelligent database systems.

This standard approach to process mining, built on the stochastic language of an event log, reports only the assumptions of its discovery algorithm, because every such log is explained equally well by a model with no concurrency at all.

This work implements two representative architectures --- the Simplified Graph Convolution (SGC) and Linear Graph Convolution (LGC) models and evaluates them on open benchmark graph datasets and semi-supervised learning tasks using quantum simulation and presents a cost gradient analysis that identifies the tasks for which the models are trainable.

This work proposes OPTED (on-policy fine-tuning for end-to-end driving) which decouples reinforcement learning from the post-training of the end-to-end policy: a privileged teacher is trained using RL on vectorized inputs (HD-map and bounding boxes) which provides supervision to the pre-trained student during closed-loop post-training.

REARL, a closed-loop simulation enhancement framework that integrates real traffic data with large language model (LLM) and modulates the simulated vehicle with reference to that real action, is proposed.

An architecture extending unanticipated-fault recovery from detection to mitigation and an ensemble methodology for evaluating LLM-assisted mission management on low-power AUVs are made.

Imagine-TAMP is introduced, an interleaved planning and execution framework that uses semantic and geometric imagination to compare alternative task-level strategies under partial observability before committing to expensive motion planning and experiments show that imagination-guided evaluation improves observation-versus-manipulation decisions.

VAST is presented, a V2X/Dynamic Map-aware validation toolchain that connects Scenic, Scenario Simulator v2, AWSIM, Autoware, and SIM-LDM and addresses interoperability challenges, including Lanelet2-to-Scenic mapping, ROS 2-based co-simulation through SS2, Dynamic Map object injection into Autoware, and collection of TTC, PET, collision, timeout, and performance measurements.

A new SF-GVF with prescribed physical speed (PPS) that converge exponentially to the desired path from any initial condition in the higher-dimensional space (including virtual dimension); more importantly, the robot's physical speed converges to the PPS, while the path-error dynamics remain invariant under regular reparameterizations of the desired path.

This work studies a lightweight coding harness whose execution loop is fixed while three components are varied: planning, action space, and context management, and finds that context management becomes increasingly valuable as the context-window budget tightens.

Using realistic communication models reversed simulated traffic speed trends and more than doubled predicted hard-braking events, so researchers and transportation agencies can maintain existing simulation pipelines while accurately accounting for dense-traffic packet loss and denial-of-service impacts.

Sampling-Guided Policy Search (SGPS), which couples recurring action-target refinement by sampling-based model-predictive control with first-order policy optimization with first-order policy optimization, and shows that refinement improves policy learning beyond initialization and tracking alone.

This work proposes an observer-based dynamic cooperative learning framework incorporating online distributed Gaussian Process (GP) regression, which enables accurate estimation despite incomplete in measurements and deficient GP models, and derives an error upper bound encompassing state estimation and model estimation.

A global ambiguity set is constructed as the union of admissible mixtures of local ambiguity sets that allows client-specific ambiguity radii and admits a client-wise separable reformulation and establishes a high-probability out-of-sample performance guarantee.

This work generates a robust synthetic dataset of forward DTOF using exact Monte Carlo simulations at multiple source-detector distances and proposes a machine learning framework as an alternative approach to reconstruct the optical properties of a bilayered medium, benchmarking its efficiency and accuracy against model-based algorithms.

Which component matters more depends on the loss assigned to erroneous acceptance: at low liability the planning gain dominates; at high liability the verifier's avoided false passes dominate; and a standalone verifier captures nearly all the false-pass benefit of the full planning-plus-verification stack at a fraction of its cost.

The results demonstrate that grounding Mistral-7B within empirically cloned interaction networks produces a realistic simulation framework capable of reproducing complex social dynamics.

DeliveryGym is introduced, a 3D environment for evaluating and training agents on continuous courier shifts that couples multimodal tool interaction with persistent world dynamics and computes trajectory rewards from simulator events, making the costs of an agent's decisions available for reinforcement learning (RL).

It is shown that the workspace token can be used as a drop-in replacement for observations during deployment, enabling policies to solve memory-intensive tasks without the need for VLM reasoning in-the-loop.

A hybrid approach that draws on the stability and generation quality of denoising diffusion models, which yields a stable training process and generates microstructures of varying complexity with minimal slice artefacts and close agreement with ground-truth phase fractions and structural descriptors.

STR-Agent is proposed, an LLM-driven framework for QoS-aware routing in LEO satellite networks that significantly outperforms conventional baselines, and results demonstrate the potential of LLM-driven agent architectures to enable serviceaware and adaptive QoS routing in future LEO satellite networks.

The model presented here is a step toward a more rigorous formalization of cognitive phenomena and may provide a basis for further theoretical analysis, computer simulation, and implementation in artificial-intelligence systems inspired by biological processes.

This article investigates neuro-symbolic agentic AI (NSAAI) as a framework for combining neural grounding, symbolic reasoning, and closed-loop agentic interaction to support more reliable and adaptive UAV autonomy.

Astronex-World 1.0 is presented, an open controllable video world-model foundation that provides a bidirectional model for full-context generation and a causal model with block-causal attention and cross-block KV caching for persistent generation, both built on the Wan2.2-TI2V-5B prior.

The value of execution-improved software as a resource for acquiring new policies in this setting is demonstrated, although initial references remain better on two target tasks when averaged across runs.

Experiments on a real robot platform demonstrate that MaskHarness-WAM substantially outperforms limited-horizon policies on sequential multi-object manipulation, showing its effectiveness in extending local manipulation skills to reliable long-horizon execution.

This work considers N secrets, of which N are linearly independent input values and the remaining N -K secrets are determined by linear computations on these inputs, and analyses the existence of LERS-derived leakage that exploits this structure.

This work introduces DexTouch-WM, an action-conditioned world model that learns from scalable human touch to jointly predict future RGB observations and bilateral tactile dynamics, and shows that scalable human interaction provides a complementary data axis for learning dexterous robot world models.

OmniMimic, a training framework that turns directionally limited animal demonstrations into a single multi-gait policy over target per-axis velocity ranges, and uses a shared actor with soft-gated, gait-specialized residual experts to balance reusable locomotion skills with gait-specific corrections.

PACE (Precise AI Cinematic Expression), a typed representation for the plan: the screenplay evidence, the characters, props and locations it needs, where each subject stands, and what the camera does.

The method retains a nominal task-space controller for structured insertion and seating, while residual PPO supplies bounded local corrections and decides when to release and supports a hybrid design in which geometry preserves reliable task structure and learning is concentrated on the contact-sensitive behaviour that fixed rules handle poorly.

A stereo visual-servoing framework for an autonomous underwater vehicle (AUV) that derives a stable 3D relative state from stereo images through target-specific depth extraction and Kalman filtering and employs adaptive model-fusion predictive control.

This work introduces a spatial-semantic uncertainty formulation that maintains separate beliefs over each component and integrates probabilistic VLM evidence into a global target-identity posterior, including probability mass for undiscovered targets.

This work presents a probabilistic, proactive, motion planning framework that explicitly accounts for actuator failures in space, model actuator failure modes as a Markov chain and propagate the probability of successfully reaching the goal along the planning horizon.

A DMPC framework in which each agent is assigned a connectivity contract: a local region prescribing where its predicted positions may lie over the prediction horizon, and it is proved that the resulting closed-loop system maintains connectivity, avoids collisions, and respects local state and input constraints.

The results show that the nominal 8-DOF model remains ZMP-stable for step completion times down to 0.5 s and for slope inclinations up to 22.5 degrees with the given foot geometry, and that ZMP stability is governed by the mass distribution among the links rather than the total mass of the robot.

The extended ILP to safety-critical navigation in dynamic environments by integrating an anticipatory risk-blended control barrier function (ARB-CBF) is extended, demonstrating superior temporal efficiency and safety with lower computational overhead compared to optimizationbased baselines, making it highly suitable for resourceconstrained platforms.

SmellDiffusion is presented, a simulation pipeline that represents species-specific gas zones in an open-vocabulary olfactory scene graph and shares the selected goal between classical and diffusion planners and remains the fastest and shortest-path method.

Four-channel bilateral teleoperation removes ambiguity directly by using the leader arm as a separate measurement of the intended equilibrium, making per-axis stiffness identifiable by regression using only the joint-torque sensing already on the manipulator, which is used to fine-tune a VLA to emit stiffness alongside pose.

Frozen transfer to xArm7/MoveIt requires no xArm-specific retraining and candidate-level deployment-feasibility prediction reaches 81.25% recall, 85.20% specificity, and 83.23% balanced accuracy.

RotateIt!, a single-arm framework that uses adaptive axial rotation for dynamic garment unfolding, is presented, to the best of the knowledge, it is the first unfolding framework to employ dynamic axial rotation as its primary manipulation primitive.

Trie-GRPO, a novel reinforcement learning algorithm based on action prefix trees, which enables step-level advantage estimation, is introduced, which resolves the credit assignment problem by isolating intermediate correct decisions from downstream errors, while effectively balancing exploration efficiency and depth compared to conventional search trees.

SLAMSqueezeBench, a framework that allows testing of SLAM systems under realistic workloads on edge hardware, and compares nine SLAM systems spanning classical systems, learning-based systems, and approaches for Gaussian splatting.

This work considers NAMO in unknown environments revealed through onboard sensing, where the robot must decide whether a blocked route requires relocation or a feasible path may exist through unexplored space, and proposes an online framework that addresses this ambiguity.

A design-oriented evaluation of PFAL in 16nm FinFET and a motivation to exploit adiabatic logic for future low-power system architectures are provided.

This work presents RebarSim, a visual sim-to-real system trained entirely in simulation, a privileged state-based teacher is trained with reinforcement learning over procedurally generated rebar geometries, then distilled into a multi-view student that maps raw RGB and proprioception directly to actions under extensive domain randomization.

This work presents HOPHY (Hierarchical Off-road Planning using Hypergraphs), a reusable hierarchical terrain representation that organizes map-scale terrain into geometrically connected semantic regions (GSNodes), connectivity-preserving critical regions (Coarse Regions), and typed hyperedges for terrain, agent, and weather context.

TraceFlow is introduced, a progress-aligned guidance field that turns the action densities of retrieved successful and failed rollouts into a bounded correction to a frozen flow-matching action expert, using one terminal outcome bit per rollout and no other label.

SkipVLA is a hybrid policy that combines a pretrained VLA with a classical motion planner, using the planner for free-space motion and querying the VLA only for contact-rich skills such as grasping and placing, demonstrating up to 2.5x faster task completion and significantly lower energy consumption.

GeoAAC is proposed, a geometry-based adaptive action chunking method for flow-based VLA policies that adjusts the action horizon according to the reliability of the current action prediction, with geometric variation across action prefixes remaining positively correlated with predictive uncertainty.

This paper proposes a model-based bootstrap framework for uncertainty quantification of OPE in finite-horizon, time-inhomogeneous Markov decision processes (MDPs), and establishes bootstrap distributional consistency, asymptotically valid confidence intervals, and consistent variance estimation for the target policy value.

SafeHarness is presented, which equips the model with two obstacle-aware harnesses that enable it to prioritize the safety constraint, and surpasses the previous SOTA by 6.5% and 27.0%, respectively.

FL-Net is a novel federated clinical research framework that integrates modular data harmonization, data discovery, disclosure control, securely built versioned FL-Net-Tools and containerized federated workflow execution into a persistent network and enables the re-use of harmonized data and workflows across studies.

MAGMA-GEN is an on-policy data-generation pipeline that converts ambiguous failed rollouts into validated recovery supervision and improves task success and recovery capabilities, against distillation and trajectory-repair baselines under evolving task constraints in both simulation and real-robot execution.

This work introduces Travelling Pair Dynamical Alignment and Trajectory Estimation (TP-DATE), a theoretical and computational framework to generalize GW-OT dynamically in a simulation-free manner, and forms a broad class of static and dynamic Quadratic-form OT (QOT) through path actions and proves the static dynamic equivalence.

Graph-Based Stochastic-Power-UCT (GS-Power-UCT), which shares states reached at the same planning depth while keeping separate values for states reached at different depths, is introduced, which shows improved sample efficiency over tree-based and graph-based baselines.

This work studies organizational margins on externally verified software-engineering tasks using controlled workflow experiments on externally verified software-engineering tasks to find out how capacity and task information are distributed across stages of AI production.

A deep architecture that is able to jointly optimize cost functions and route-ranking model towards any route preference is proposed, and a novel loss function is proposed that optimizes a single-objective variable, with other variables strictly under constraints.

V2-STRep is presented, a zero-shot framework that converts generated video motion into reusable robot skills through VLM-grounded structured task representations, and demonstrates improved execution success over baselines, reliable cross-scene transfer of successfully acquired skills, and adaptation to changed deployment instructions.

MM-Future, a world-action model that generates multiple paired scene-action hypotheses and models bidirectional interaction within each pair, shows consistent improvements over both single-mode and action-only variants, validating the benefit of multi-mode joint world-action modeling.

This work presents learning interactives, a structured framework leveraging the generative UI capabilities of Gemini to construct effective customized interactive simulations that students learn best through active engagement through interactive experiences tied to real-world concepts.

This work presents S4R (Scaling for Rigid-Body Interpenetration Resolution), a scale-continuation method for static interpenetration repair, and evaluates S4R on Kubric, HY3D-Bench, and Thingi10K using a shared mesh-level evaluator and a unified per-scene timing protocol.

FlipToSee is proposed, a probabilistic framework that removes representational ambiguity by parameterizing placements as unit support normals on $S^2$ while modeling their multimodal conditional distribution via a von Mises--Fisher mixture density network.

The results show that reliable scenario generation requires verifying realized behavior, not merely executable code, and demonstrate the value of explicit intermediate representations for verifiable and repairable language-driven co-simulation.

An RTK-vision-guided reinforcement-learning framework in which a child UAV is physically transported by a larger carrier, takes off from the carrier while airborne, executes an independent sortie, returns to the carrier's current position, redocks, and subsequently descends with the carrier.

Feel-WM is presented, the first off-road navigation world model that conditions on proprioception and predicts what the robot will feel alongside what the camera will see, and outperforms visual-only navigation world models in open-loop planning and closed-loop rough-terrain navigation across wheeled and legged platforms.

Group Relative Return Policy Optimization (GR2PO), a critic-free reinforcement learning framework for continuous robot control, is proposed and significantly outperforms critic-free baselines that use immediate rewards and performs competitively against state-of-the-art actor-critic methods.

MAGNETAR is presented, which infers a joint posterior over planar transmitter position and heading from a single asynchronous radio-frequency multipath snapshot, represented by angle-of-arrival and signal-to-noise-ratio estimates, given the room layout and receiver pose.

This work shows that view-invariant control can be achieved without explicit test-time 3D sensing by encoding geometric knowledge into the visual representation during simulation, and presents AnyViewDex, an asymmetric training pipeline that combines multi-view contrastive alignment with privileged 3D geometric supervision.

A framework that fuses the output of Trajectron++, a neural network-based trajectory predictor, with extended Kalman filter (EKF)-based multiple trajectory candidates at a late stage indicates that EKF-based trajectory candidates can effectively complement neural trajectory prediction through learned fusion.

This work examines the trade-off between explicitly incorporating compliance through series-elastic actuation and using so-called proprioceptive, low-gear-ratio transmissions, and explores how these mechanisms interact with control policies during locomotion.

JaxPIP is introduced, a JAX-based implementation that reformulates PIP/FI evaluation into tensorized linear algebra operations that allows efficient execution with just-in-time compilation and enables large-scale batch evaluation of energies and forces.

CoreSense is presented, a robot-system integration architecture that combines traceable episodic evidence with a conflict-aware belief gate and bounded, auditable recommendations that supports an auditable integration pattern, not autonomous recovery or certified safety.

WorldContact is presented, a contact-centric world model for deformable-object manipulation, constructed from a limited set of high-quality trajectories to generate additional training data efficiently and fine-tune an existing vision-language-action policy and deploy it directly on a real robot.

JEPA-Anything, a domain-agnostic framework based on orthogonal predictive factorization (OPF), achieves the lowest one-step and 100-step molecular errors among compared methods in all four systems and supports a common factorized predictive principle across heterogeneous worlds.

It is argued that chess provides a useful bridge between cognitive and computational perspectives on strategic reasoning, and identifies explicit planning, grounded and faithful explanation, metacognitive calibration, and human--AI complementarity as directions for future research.

WAVE-Go, an image-goal navigation framework that separates world-action prediction from interruptible command execution, and its executor adaptively selects an action prefix and cancels pending commands when updated observations invalidate execution, support adaptive, interruptible execution as a means of balancing navigation performance and planning overhead.

Finder is presented, an agentic closed-loop object-finding primitive for embodied grounding that maintains a typed loop state that links query-conditioned planning, scoped evidence gathering, candidate verification, and accept/continue/abort control.

F-DACE abstains for all five markdown indicators: some estimates are imprecise, one refutation fails, and MarkDown5 has a direct sign conflict; a LangGraph conversational agent exposes impact, what-if, and lever-optimization tools while a deterministic verifier preserves causal-layer status.

The results show that replay retention depends on change magnitude and on how the dynamics evolve, and an estimator built from interaction data can still provide the quantities needed to choose a replay strategy after permanent changes.