Reinforced Planning with Latent World Models (RP1) is a novel method that learns to evaluate imagined outcomes via a critic and to improve multi‑step plans through an optimizer trained offline on world‑model roll‑outs. It is the first approach to fully learn plan improvement and can be attached to any pretrained latent world model. In experiments on visual navigation, arm reaching, and robotic manipulation, RP1 outperforms hand‑designed search algorithms, achieving near‑perfect success while using far fewer roll‑outs and running up to 67× faster than the strongest alternative.
By Armin Sommer, Jannik Schilling
MLREF introduces a Module Level Reward Evolution Framework that uses a persistent pool of reusable reward components to improve reward design in reinforcement learning. The framework constructs reward functions as linear combinations of modules from this pool and evolves the pool through reflection-based refinement, hybrid credit assignment, and a merge strategy with rollback. Experiments on 17 tasks demonstrate that MLREF outperforms strong baselines, achieving a 25.2% improvement in locomotion and 6.6% in manipulation with more stable optimization dynamics.
By Chenglin Liu, Xun Wang, Ruishuo Chen, Zhuoran Li, Longbo Huang
The paper investigates how the CutMix data augmentation technique affects reliability and robustness in semantic segmentation. It evaluates two architectures—CNN-based DeepLabV3+ and transformer-based SegFormer—on both in-domain and out-of-domain data. Results show that CutMix has a minor effect on segmentation accuracy but consistently improves reliability, especially under distribution shifts, by enhancing calibration and uncertainty quality.
By Steven Landgraf, Markus Ulrich
The paper introduces the Orienteering Problem with Uncertain Time‑Varying Rewards (OP‑UTVR), a new variant of the classic orienteering problem that allows agents to estimate and forecast reward dynamics from observations. Three planners with different planning horizons and online adaptivity are proposed, and theoretical performance bounds under reward stochasticity are derived. A mobile service robot benchmark is presented, and experiments show trade‑offs between planning horizon and adaptivity, highlighting the benefits of long‑horizon planning with online adaptation.
By Masafumi Endo, Kohei Honda, Yuu Jinnai, Ryo Yonetani
The paper introduces a Metamorphic Artificial Age Score (AAS) decision-support prototype for monitoring drone propeller health using flight logs. It extracts six health indicators—trajectory tracking error, attitude instability, thrust-command burden, motor-command imbalance, ESC-command instability, and battery-level stress—from MATLAB matrices and normalizes them against a healthy baseline. A controlled retrospective evaluation classified three defective propeller cases into different severity levels, demonstrating that fault effects manifest across multiple operational channels and highlighting the need for a multi-indicator decision-support layer for maintenance prioritization.
By Seyma Yaman Kayadibi
The paper introduces the Environment State-Text Injection (ESTI) attack, a novel method that manipulates the textual representation of environment states in large language model‑driven embodied agents without altering user instructions, model parameters, or executors. ESTI re‑frames adversarial goals as false state evidence that aligns with the current environment, thereby influencing both planning and execution through object properties, spatial relations, affordances, task‑stage rules, and execution feedback. The authors also present ESTI‑Bench, a benchmark that evaluates attack propagation across the planning‑to‑execution closed loop, and demonstrate that ESTI outperforms existing baselines on multiple embodied task datasets, achieving up to 89.32% higher planning‑level and 43.69% higher execution‑level attack success rates.
By Jiawei Liu, Jiacheng Guo, Tian Zhang, Yiwei Xu, Juan Wang, Jinlin Fan, Bowen Xiao, Chi Guo, Keyan Guo, Hongxin Hu
The paper discusses the "embodiment gap" in robot foundation models, highlighting that while models can generalize across tasks, additional work is often needed to deploy them on specific robot bodies. It surveys what components can be reused across different robot embodiments and what must be implemented anew, mapping existing methods along axes of shared structure and adaptation stage. The authors propose a reporting framework to better assess adaptation efforts and identify remaining challenges for cross-embodiment learning.
By Yukiyasu Domae, Keisuke Shirai, Hanbit Oh, Ryoichi Nakajo, Tomohiro Motoda, Koshi Makihara, Masaki Murooka, Takuma Yagi, Yoshiaki Bando, Ryo Hanai
FedLNS is a server‑side framework that screens federated learning updates by representing each client’s contribution through changes in trainable normalization‑layer parameters, creating lightweight signatures that can be compared against a history‑aware cross‑client reference. The method requires no extra client‑to‑server communication, raw data, or labeled attack examples, and after screening, the remaining full‑model updates are aggregated with standard federated learning rules. Experiments on GPT‑style, BERT‑style, and LLaMA‑style models with 200 clients demonstrate that FedLNS achieves lower test perplexity than six baselines even when 40% of the population performs target manipulation under both IID and non‑IID data partitions.
By Kai Li, Jong-Ik Park, Carlee Joe-Wong, Wei Ni, Falko Dressler
State-of-the-art vision-language-action (VLA) models such as $π_{0.5}$ exhibit strong semantic understanding, instruction following and task behavior. However, when deployed on new robots, even minor...
SCAPE is a scenario‑conditioned simulation‑augmented policy evaluation framework that predicts real‑world policy performance for specific scenarios using limited paired simulation‑and‑real samples and extensive simulation rollouts. It corrects sim‑to‑real bias in simulation labels before training the prediction model and calibrates prediction uncertainty via conformal prediction. Experiments on autonomous driving and quadruped velocity tracking show SCAPE reduces scenario‑level prediction error, improves testing sample efficiency, narrows calibrated prediction intervals, and generalizes better to out‑of‑distribution scenarios, enabling fine‑grained deployment strategies.
LT-Mem introduces a volatility‑aware memory evolution framework for lifelong scene understanding, combining spatially aligned instance‑level 3D perception with temporal reasoning. It uses a multi‑session SLAM backbone, a reasoning layer that scores evidence and selects memory actions, and a Tri‑Memory structure (Live, Delta, Meta) to preserve current states and event histories. The accompanying LT‑VQA dataset provides multi‑session recordings, persistent identity annotations, and temporal QA pairs, and experiments show LT‑Mem outperforms baselines while using far fewer tokens.
The paper investigates how Vision Language Models (VLMs) can be fooled by tiny, human‑imperceptible changes to images. It introduces a gradient‑based attack that targets only the vision encoder, reducing computational cost while still effectively disrupting both untargeted and targeted multimodal interpretations. Experiments on open‑source VLMs such as Qwen2.5‑VL, Granite‑Vision, FastVLM, and Phi‑3.5‑Vision demonstrate that these small perturbations can dramatically alter the models’ textual outputs.
TestifAI is a deep learning testing framework that estimates model robustness against combinations of input perturbations efficiently. It allows users to define structured spaces of semantic perturbations and severity levels, then query robustness for any combination. By using partial model tomography, TestifAI reconstructs higher-order perturbation effects from low-order tests, achieving less than 7% error while reducing inferences by 60–80%.
TestifAI is a deep learning testing framework that estimates model robustness against combinations of input perturbations efficiently. It allows users to define structured spaces of semantic perturbations and severity levels, then query robustness for any combination. By employing partial model tomography, TestifAI reconstructs higher‑order perturbation effects from low‑order tests, achieving less than 7% error while cutting inference counts by 60‑80% on image and language classification tasks.
The paper introduces RoomWright, a code‑driven framework that generates 3D indoor scenes for embodied AI by focusing on functional usage rather than just visual layout. It performs usage‑driven object reasoning, treating anchors as task centers to select task‑required objects and their affordances, and compiles interactions into trigger‑condition‑effect rules that update object states. The system also addresses ambiguous object orientation through annotation‑guided usage cues, producing scenes that are executable, editable, and ready for simulation‑based policy learning.
Reinforced Planning with Latent World Models introduces RP1, a neural planner that learns to evaluate imagined outcomes via a critic and improve multi‑step plans through an optimizer trained offline on world‑model roll‑outs. Unlike existing planners that are hand‑designed or only inform policies, RP1 fully learns to refine plans and can be attached to any pretrained latent world model. In experiments on visual navigation, arm reaching, and robotic manipulation, RP1 outperforms hand‑designed search algorithms, achieving near‑perfect success while using 1,000× fewer roll‑outs and up to 67× faster inference.
The paper proposes using encoder‑decoder networks based on LSTM cells to reduce communication in distributed model predictive control (DMPC). Agents transmit a compressed representation of their messages, which receivers reconstruct, thereby lowering the data exchanged each time step. Experiments with mobile robot formations show that the trained networks maintain performance even when full communication is unavailable, and they can adapt to different prediction horizons without retraining.
By Torben Schiz, Pedro H. J. Nardelli, Henrik Ebel
The paper presents a reinforcement learning framework that refines robotic grasp poses using a Deep Q-Network and keypoint-based object representations. Starting from initial grasp candidates generated by a geometric algorithm on 2D overhead images, the method iteratively improves grasps, converting previously failed attempts into successful ones. Experiments on 300 Dex‑Net objects with a UR5 arm achieved a 100% success rate on items that were ungraspable by geometry alone, and the approach transferred to a Delta robot in real‑world tests.
By Amir Arsalan Nematollahi, Shayan Ahmadi, Mehdi Tale Masouleh, Ahmad Kalhor
The paper introduces ORPA, a framework that adds a lightweight, feedback-conditioned module to a pretrained robotic manipulation policy, enabling real‑time residual adjustments in joint space without retraining the base policy. ORPA allows immediate correction of execution errors and distribution shifts, improving success rates and recovery on precision‑sensitive tasks compared to baseline policies and rule‑based inverse kinematics. The method is evaluated on the ALOHA platform, showing its effectiveness in real‑time deployment scenarios.
By Muhammad A. Muttaqien, Tomohiro Motoda, Ryo Hanai, Yukiyasu Domae
The article reports that in July 2025, 18 arXiv manuscripts contained hidden instructions designed to manipulate AI‑assisted peer review, such as covert commands to give only positive reviews. These prompts were concealed using white text and microscopic fonts, and the authors’ reactions ranged from withdrawal to defending the practice as a test of reviewer misuse of large language models. The study identifies four types of hidden prompts, critiques the ineffectiveness of honeypot defenses, and highlights inconsistent publisher policies while calling for controlled AI integration and harmonized guidelines in academic evaluation.
By Zhicheng Lin