Embodied
-
LOGIV: Graph-Verified Execution with Causal Local Repair for Long-Horizon Robot Tasks
2026-10-30 15:08:57Enqiao Lu (CUHKSZ, THU), Yuxiang Xie (CUHKSZ), Xingrui Yu (A*STAR), Yuyang Wang (Caltech), Yipeng Gu (CUHKSZ), Zhirui Fang (THU, NTU), Xinrun Xu (THU), Zhenglin Wan (NUS), Pengfei Zhou (NUS), Wangbo Zhao (HKUST), Yang You (NUS), Yuxiang Gao (A*STAR, NTU), Ivor Tsang (A*STAR, NTU)Abstract
Agentic robots must turn a high-level goal into actions while keeping the physical conditions needed for future steps valid. A completed action does not ensure that its effects will persist: a later disturbance can invalidate support that the remaining plan still assumes. We present LOGIV, a graph engineering framework for agentic robot execution that uses an explicit task graph to connect symbolic planning, observation-based verification, and embodied action. LOGIV compiles a validated plan into condition-support and resource-ordering edges, checks their physical validity during execution, and uses dependency tracing to determine what must be restored after a failure. Repair is constrained by retained unfinished actions, and the combined continuation is symbolically validated before execution resumes. The framework operates above existing Vision-Language-Action (VLA) and World Action Model (WAM) policies without adding trainable components. Across 20 dual-arm tasks from RoboTwin V2 and BiCoord with three execution backbones, LOGIV improves mean task success without injected disturbances by 10.67 and 15.33 percentage points, respectively. Under predefined perturbations, it achieves higher task completion and condition restoration than three adapted recovery baselines for every backbone on both benchmarks. On three real-robot tasks, successful trials increase from 12/30 to 17/30. These results support explicit, continuously checked task dependencies as a practical interface for reliable agentic robot execution.
Abstract (translated)
URL
https://arxiv.org/abs/2610.40016
PDF
-
When the Past Shapes Action: Understanding Embodied Memory
2026-10-30 12:52:37Siqi Li, Ziyi Bai, Xinrun Xu, Tinglei Huang, B\"orje F. KarlssonAbstract
Recent advances in generative foundation models have expanded the capabilities of embodied AI, enabling increasingly general navigation, manipulation, and long-horizon task execution. However, effective interaction with dynamic environments requires more than only strong perception and reasoning: agents must act with partial knowledge and retain, retrieve, and update information from past observations, actions, and experiences. This survey examines embodied memory as a mechanism for preserving decision-relevant information beyond the current observation. We organize existing approaches along two complementary dimensions: six fundamental memory requirements, spanning world-state persistence, task progress, belief maintenance, and experiential learning; and eight architectural categories, including recurrent states, fast weights, visual and symbolic representations, spatial memory, and experience-based systems. We analyze their capabilities and limitations, and examine how existing benchmarks evaluate memory-dependent behavior, distinguishing genuine use of historical information from general task performance. Finally, we identify open challenges in selecting relevant experiences, maintaining consistent beliefs in changing environments, and consolidating knowledge across episodes. Our analysis provides a framework for understanding memory as an essential component of reliable, adaptive, and lifelong-horizon embodied intelligence.
Abstract (translated)
URL
https://arxiv.org/abs/2610.41688
PDF
-
Seeing and Imagining as One: Unified Video Generation and 4D Perception for Embodied World Modeling
2026-10-30 08:46:14Haitang Feng, Zhuoman Liu, Zhennan Wang, Sheng Wang, Juelin Li, Chengzhi Zhao, Hexiang Wei, Lin ShaoAbstract
Embodied world models should not only imagine plausible futures, but also perceive the geometric, semantic, and motion structure of the evolving world. We present GenSight, a unified embodied world model that brings future video generation and dense perception into a single pretrained video diffusion transformer. GenSight uses a unified spatiotemporal representation for video, depth, embodiment segmentation, and first-frame-relative 2D flow. Built on a shared DiT backbone, GenSight uses lightweight task modulation to predict all modalities within the same architecture. All tasks are jointly optimized within a unified velocity prediction space. At inference, GenSight supports two complementary modes: multi-step future video generation with aligned dense predictions and single-step dense perception from an observed video. By unifying modality representation, model architecture, and prediction space, GenSight avoids separate modality-specific pipelines and couples appearance, geometry, semantics, and motion in a shared representation. It promotes cross-modal consistency and allows dense perception to benefit from the spatiotemporal priors learned through video generation. Trained on embodied manipulation data spanning multiple robot embodiments and human-hand interactions, GenSight demonstrates strong performance in both video generation and dense 4D perception, highlighting the effectiveness of unifying seeing and imagining for embodied world modeling.
Abstract (translated)
URL
https://arxiv.org/abs/2610.39232
PDF
-
BioAgent: Self-Directed Skill Acquisition and Capability Growth for Long-Horizon Laboratory Protocols
2026-10-30 07:47:08Gaojing Zhang, Changwen Chen, Zichen Luo, Jialiang Li, Yuhan Wang, Yifei Xie, Wenzhao LianAbstract
Executing an unfamiliar laboratory protocol requires a robot to identify missing capabilities and determine whether each operation remains valid as the experiment progresses. This letter presents BioAgent, an embodied agent that addresses these coupled challenges of capability sufficiency and experimental validity. It matches human-reviewed requirements to validated skills and task packages, selects tool-based implementations for missing behaviors, and requests human teaching when needed during learning. Learned skills undergo sequential task-package validation to check outcomes and compatibility between successive operations. During execution, precondition, outcome, and experimental-state checks govern progression, autonomous recovery, or termination. Execution evidence guides tool selection, while accepted experience supports offline policy updates and task packaging. On the second task, BioAgent reuses 17 skill types unchanged, revises two existing implementations, and acquires five new types. On two dual-arm laboratory tasks with 20 and 31 ordered skill invocations, BioAgent achieves complete-task success rates of 66\% and 58\% with autonomous recovery over 50 runs per task. Across 25 atomic skills evaluated over 50 autonomous trials each with recovery disabled, success rates range from 84\% to 100\%, with 17 skills achieving 50/50.
Abstract (translated)
URL
https://arxiv.org/abs/2610.41383
PDF
-
TRACE: Target-State Risk-Aligned Conditional Execution for Embodied Tracking
2026-10-30 05:26:41Mingyang Lyu, Gongce Cao, Yiyang Jia, Lu Jia, Erliang Lin, Yuhao Zhang, Yinqian Sun, Pin Lyu, Feifei Zhao, Bo WangAbstract
Embodied visual tracking requires a robot to follow a language-specified person under occlusion, look-alike distractors, and ambiguous instructions. We show that improving tracking persistence can simultaneously increase safety violations. Using a compact 0.6B vision-language-action (VLA) tracker with a frozen backbone, we update only the planner head with proximal policy optimization (PPO). PPO improves success and following rates across all three EVT-Bench settings, but increases the collision rate on distracted tracking because episodes that previously ended in target loss can instead end in contact. We introduce TRACE, an execution-time target-state risk gate that preserves the learned policy and intervenes selectively. A lightweight risk head processes 84 cues, including candidate boxes, identity margins, a learned range-and-bearing probe, and the policy's commands. When the calibrated risk exceeds a threshold, TRACE rescales the translational component of the next waypoint while leaving yaw unchanged. The executed action is identical to PPO's on more than 98% of steps. In paired evaluations on identical episodes, TRACE reduces the distracted-tracking collision rate by 3.96 percentage points, while further improving success and following rates. Matched slowdown controls without target-state timing do not reproduce this improvement. Concurrent evaluation reproduces a collision reduction of 3.77 points, compared with 0.29 points for identical-arm null pairs, indicating that the effect exceeds evaluation variability. These results show that target-state-aware execution can recover the safety cost of policy post-training with minimal intervention.
Abstract (translated)
URL
https://arxiv.org/abs/2610.41275
PDF
-
FrontierMat: Benchmarking Language Models at the Frontier of Materials R&D
2026-10-30 02:37:21Feng Chen, Jianguo Huang, Yushan Xiao, Yue Li, Bijun Tang, Xuyu Dong, Xingguo Wang, Feiyang Xie, Jianhui Gu, Dongfeng Cao, Hongda Chen, Yongji Gong, Ruiqi Li, Shuxin Li, Xingji Li, Ruitao Lv, Li Song, Lei Wang, Ye Zhang, Xiaoxu Zhao, Xitao Zheng, Bo An, Zheng LiuAbstract
To accelerate materials discovery, language models must be able to address problems at the research frontier. Yet textbook- and examination-derived benchmarks primarily assess established knowledge, leaving performance on frontier research problems largely untested. We introduce FrontierMat, a benchmark of 330 problems drawn from frontier academic and industrial research in fields including aerospace, semiconductors, embodied intelligence and nuclear fusion. Every problem is validated by leading experimentalists and industry experts in its field. Each problem presents a real study and asks the model to infer a withheld outcome or draw a conclusion from selected experimental evidence. Problems are annotated by functional domain, material system and the scale of the governing mechanism; 130 require cross-scale reasoning. The strongest general-purpose model scores only 53.7%, and on matched problems, cross-scale problems score 8.7 points below single-scale ones. Half of the problems are solved by at most one model, and models fail chiefly by endorsing what is plausible rather than what was observed. A domain-adaptation study with meta-weighted continued pretraining and scale-modular self-distillation raises an open-weight model from 36.7% to 55.4%, matching the strongest proprietary model, with improvements on public materials benchmarks and no decline in aggregate performance on general benchmarks. FrontierMat provides a testbed for measuring progress toward language models that support frontier materials R&D.
Abstract (translated)
URL
https://arxiv.org/abs/2610.41162
PDF
-
MotorSense: A Video-EMG Dataset of Motoric Representations for Action Understanding
2026-10-30 01:32:19Eadom Dessalene, Michael Maynord, Amir-Hossein Shahidzadeh, Botao He, Yasamin Tabatabaee, Ruoshi Liu, Ruohan Gao, Paul Pu Liang, Yiannis AloimonosAbstract
Computer vision models learn hand action only from its visual consequences, without access to the underlying embodied motor signals. We address this absence with MotorSense, the first large-scale paired egocentric video and surface electromyography (EMG) dataset. MotorSense pairs bimanual EMG bands with egocentric video and yields synchronized video, bimanual EMG and IMU, and audio across 100 hours of unscripted manipulation. EMG offers a powerful scalable alternative to manual annotation: it captures finger movement, hand configuration, and the forces exerted between hand and environment as a dense signal free of occlusion and labeler bias, whereas manual annotation is costly, subjective, and unreliable under occlusion. We use MotorSense to learn sensorimotor alignment, producing an organization of action that is shared across the visual and motoric spaces, through cross-modal pre-training between video and EMG. The resultant vision models are then transferred to downstream tasks that benefit from sensorimotor alignment: in this case, action recognition, 3D hand reconstruction, and 3D contact reconstruction. We further demonstrate a generative application in which EMG motor signals are used to condition a video diffusion model, yielding videos of fine-grained hand manipulation. Across four action-centric computer vision tasks and eight popular video datasets, we demonstrate that sensorimotor alignment provides a stronger foundation for visual representation learning than conventional self-supervised learning methods over video, outperforming every baseline across all tasks and datasets evaluated.
Abstract (translated)
URL
https://arxiv.org/abs/2610.41127
PDF
-
EgoHSI3R: Online 4D Hand-Scene Interaction Reconstruction from Egocentric Video
2026-10-29 18:14:06Mingzhi Pei, Zhangchen Ye, Ruoqu Chen, Liu Cao, Mengdi XuAbstract
Egocentric videos offer an abundant source of hand-scene interactions for embodied learning, which requires recovering hands, camera, and scene consistently in a shared 3D world. Existing methods focus on either camera-frame hands or world-space hand trajectories, without jointly recovering the scene pointmaps or interaction information. Building a complete reconstruction from such specialized predictions therefore typically requires per-sequence optimization. We propose EgoHSI3R, a unified feed-forward framework for online 4D hand-scene interaction reconstruction from egocentric monocular video. To jointly recover these components, it maintains a recurrent scene representation that accumulates geometric evidence over time and provides a shared world space and scale. We introduce hand-centric prompts that fuse pretrained hand priors and local scene context, while MANO vertex queries attend to scene features to predict dense per-vertex contact. These designs enable a single network to jointly estimate camera motion, dense scene geometry, world-space bilateral MANO hands, and per-vertex hand contact. Despite operating causally, EgoHSI3R achieves the lowest world-space hand joint error on ARCTIC among the evaluated methods, while offering faster inference than existing world-space hand reconstruction pipelines and competitive camera and scene reconstruction accuracy.
Abstract (translated)
URL
https://arxiv.org/abs/2610.40832
PDF
-
Gym-Anything for Robotics: Scaling physical simulations with digital agents
2026-10-29 17:42:32Pranjal Aggarwal, Sean WelleckAbstract
Realistic, fast robotics simulations could enable large-scale training of embodied AI models that transfer to the real world. However, despite decades of progress, available simulations cover only a narrow range of real-world tasks and physical phenomena. The core bottleneck is that creating better simulations requires significant expert effort and therefore does not scale. To address this, we introduce Gym-Anything for Robotics, a framework in which coding agents create realistic robotics simulations. Our core insight is that simulation creation is a coding agent task, so improvements in coding agents translate directly into richer and more faithful simulations. We select simulations based on U.S. GDP data to cover economically valuable physical work, define what makes a good simulation and a good task, and develop an adversarial creation-audit loop that checks each simulation and task against these definitions. Using this pipeline, we build RoboWorld, a set of 25 simulations with 25 test and 175 training RL environments of varying difficulty. Even the best frontier models fail on every RoboWorld test task, achieving an average reward of only 0.06. Building on RoboWorld, we introduce several new ways for frontier models to improve, including in-context learning across repeated attempts, a privileged teacher that reads the simulator state and teaches a student in context, self-assisted learning from the model's own privileged experience, and code policies that generate demonstrations across varied scenes to train vision-language-action models (VLAs) such as $\pi_{0.5}$. Each of these substantially improves performance. We release our pipeline, RL environments, and benchmark to facilitate future research. Code and data are available at this https URL
Abstract (translated)
URL
https://arxiv.org/abs/2610.40565
PDF
-
BURGER: Benchmarking and Understanding Robotic Generalization via Embodied Drawing
2026-10-29 17:34:04Xiangyu Xu, Bangshuai Peng, Ziyi Liu, Mengjie Zhao, Chenhao Lu, Zhengyang Fan, Huazhe Xu, Kaizhe HuAbstract
How effectively can vision-language-action (VLA) models learn diverse language-conditioned behaviors as training data scales? Investigating this question requires large and varied robot datasets, whose collection on physical robots remains costly. We introduce BURGER, a language-conditioned robotic drawing benchmark with a scalable, prompt-driven pipeline for generating continuous drawing trajectories, both in simulation and the real world. In BURGER, an agent starts from the same blank canvas and controls a robot arm to draw the object or spatial composition specified by language, while each instruction allows an open-ended variety of valid drawings and stroke orders. Using 28,200 simulated demonstrations spanning 282 drawing tasks, we evaluate five representative VLA models across data scales, language grounding, and multimodal behavior. BURGER supports fine-grained analysis of language grounding, spatial composition, and action generation, revealing distinct failure patterns across VLA models. Our experiments suggest that some VLA models can benefit from greater task diversity and demonstration scale, capture multimodal drawing behaviors, and generalize to unseen compositions of familiar objects. Finally, we deploy a trained policy on a Franka Panda arm, demonstrating the ability to draw reactively under human intervention. Project homepage and code can be found at this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2610.40532
PDF
-
WorldBridge: Bridging Video and Action for Task Generalization in World Action Models
2026-10-29 16:00:06Jun Cen, Yubo Guo, Hao Li, Liangkai Li, Yaoxu Lyu, Meng Wei, Zeqi Xiao, Sizhe Yang, Yuqiang Yang, Yifan Ye, Shanghang Zhang, Duo ZhengAbstract
Achieving the broad task generalization of embodied models in physical environments remains a central challenge in robot learning. We study this challenge in World Action Models (WAMs) through two complementary capabilities: video generalization, which predicts the visual evolution of new tasks, and action generalization, which translates these predictions into executable behavior through a video-to-action bridge. By varying video and action supervision for tasks outside an initial training set, we examine their respective contributions to task transfer. On RoboTwin 2.0, using only in-distribution video-action supervision yields a 25.07% success rate on out-of-distribution tasks. Introducing videos of these tasks without their action labels raises success to 55.90%, while adding just one action-labeled demonstration per task further improves it to 70.70%. These findings suggest that broader video coverage enables task transfer by leveraging existing inverse-dynamics capabilities, while even sparse action supervision further strengthens those capabilities. Guided by this perspective, we introduce WorldBridge, a WAM with separate video and action experts connected through structured attention and trained with joint flow matching. WorldBridge incorporates visual memory at two temporal scales and action forcing, alongside a unified data processing pipeline that standardizes and filters heterogeneous robot trajectories and egocentric hand-derived supervision. Across multiple manipulation benchmarks, WorldBridge achieves state-of-the-art performance among the compared methods, including 96.23% on RoboTwin 2.0 full data setting and 80.9% on clean to random setting, 82.8% on RoboCasa GR1 TableTop, and 57.6% on DOMINO Level-1. Our study highlights the complementary roles of video prediction and action grounding in developing robots that generalize across tasks.
Abstract (translated)
URL
https://arxiv.org/abs/2610.40748
PDF
-
WorldFlow: Joint Video and 3D Motion Prediction via Large-Scale Pretraining
2026-10-29 03:30:27Yuhao Lu, Jiongxu Chen, Hexiang Wei, Jiajin Wu, Juelin Li, Mingjian Liang, Fan Yang, Zhuowei Liang, Zihao Liu, Zhennan Wang, Sheng Wang, Lin ShaoAbstract
Predicting future physical states stands as a central challenge in embodied intelligence. Existing video world models leave 3D dynamics implicit, action-based formulations remain tied to specific robot configurations, and 3D motion prediction models use flow-only supervision, providing a limited learning signal for physical dynamics. To circumvent these limitations, we introduce \method{}, a generative world model that jointly predicts future video and query-based 3D trajectories. By parameterizing 3D motion as continuous displacement tokens aligned with the video grid, a unified Mixture-of-Transformers (MoT) backbone jointly denoises both modalities under a rectified-flow objective. This formulation couples explicit geometric dynamics with visual evolution, effectively unlocking the physical commonsense embedded within pretrained video models. To empirically scale and validate this unified architecture, we train \method{} on a heterogeneous mixture of 1.44 million object-level samples spanning simulated and real-world domains. We further introduce WorldFlowBench, comprising 1,678 evaluation samples from 11 data sources across simulated and real-world interactions, including spatial reasoning tasks. Across all three evaluation sets, WorldFlow achieves the lowest average displacement error (ADE) and final displacement error (FDE) among the evaluated learning-based methods. Notably, on the challenging SpatialCog set, WorldFlow achieves an ADE of 0.060 m, a 54.2\% reduction compared with the strongest external baseline. It also reduces ADE and FDE by 55.9\% and 68.5\%, respectively, compared with its flow-only variant. Project page: this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2610.39278
PDF
-
EmbodiExp: Compositional Experience Transfer for Embodied Agents
2026-10-29 02:08:42Zhifeng Gu, Ying Chen, Rui Jiang, Lei Yi, Bing WangAbstract
Experience can help embodied agents turn high-level plans into grounded actions, but transferring it across tasks remains challenging: previously effective strategies may be inapplicable to the current state or fail to produce their intended outcomes. We present EmbodiExp, a framework for constructing transferable experiences and composing them online during embodied task execution. Our key observation is that tasks often share subgoals whose completion can be assessed independently of overall task success. We therefore introduce an outcome-grounded subgoal experience that specifies a subgoal, applicability conditions, an adaptable policy, and a verifiable outcome. During execution, applicable experiences guide action generation, while verified outcomes can establish the conditions required by subsequent experiences, enabling online composition. Subgoal-level outcome attribution further enables failure utilization: failed trajectories can still contribute verified local successes and condition-specific guidance on actions to avoid. Experiments on multiple embodied benchmarks under a fold-based protocol with frozen experience banks demonstrate the effectiveness of EmbodiExp.
Abstract (translated)
URL
https://arxiv.org/abs/2610.39180
PDF
-
AtomTree: A Hierarchical Framework for State-Aware Embodied Instruction Following with LLMs
2026-10-28 19:30:40Haotian Zhai, Tianming Sha, Junnan LiAbstract
Embodied instruction following in interactive environments requires agents to interpret natural language commands and complete long-horizon tasks. Existing planners either rely on large labeled trajectories, or use few-shot and zero-shot LLM prompting that produces a whole plan in a single serial reasoning process. These approaches depend on linguistic common sense, commit to a plan from the initial instruction, and only update after failures, which weakens robustness and state awareness. We present AtomTree, a hierarchical framework for state-aware task planning with LLMs. AtomTree incrementally builds a tree of subgoals and actions, where the LLM decides at each step, from the current symbolic state, whether to further decompose or to output a grounded low-level action. A lightweight memory module summarizes past outcomes for reuse in later decisions. When a low-level action stalls, AtomTree triggers hierarchical backtracking replanning to return to the parent node and regenerate the subtree plan from the latest state, preventing continued drift along an incorrect trajectory. In zero-shot evaluation on the ALFRED benchmark, AtomTree outperforms prior LLM-based planners. Project page: this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2610.38744
PDF
-
Ego-CEVR: Learning Cross-Embodiment Visual Representations from Human Egocentric Videos
2026-10-27 16:30:35Keru Zhou, Zhirui Fang, Xinrun Xu, Yaopeng Lou, Zeyuan He, Zihao Zhu, Xinze Niu, Chen Wang, Tianfu Li, Samith Va, Bin Qian, Junwei Li, Wenjia Ding, Yicheng Xu, Chang Zhou, Ziwei Wang, Li Liu, Xiu Li, Maoqing YaoAbstract
As egocentric video becomes increasingly available for embodied learning, an important research question is how to turn this low-cost, scalable source of data into robot manipulation capabilities. Egocentric videos naturally provide rich context for high-level task understanding, while real-robot demonstrations with wrist observations and action annotations provide supervision for fine-grained action alignment. We present Ego-CEVR, a data-native framework for hierarchical visual representation learning that assigns distinct learning objectives to global and interaction representations. The global module learns object relations, task state, and temporal progress through future prediction on egocentric video. The Interaction module interprets wrist observations in global context and learns local alignment and contact cues through robot action supervision. Separate residual paths expose both representations to the action policy, preserving direct access to task context alongside fine-grained execution information. Ego-CEVR supports independent pretraining of its global video module on large-scale human egocentric videos and videos from diverse robot embodiments, without requiring robot action labels or paired wrist observations.
Abstract (translated)
URL
https://arxiv.org/abs/2610.37509
PDF
-
PDRVLA: A Vision-Language-Action Model with Physical Dynamics Representations
2026-10-27 15:09:10Hanqing Wang, Zhaotian Cai, Ruichuan An, Bohan Zeng, Tao Zhang, Yilin Chen, Xu Jiang, Kaiquan Chen, Chongyang Wu, Haoran Li, Fan Yang, Mingan Lin, Wentao Zhang, Zenan Zhou, Youzheng WuAbstract
Vision--Language--Action (VLA) models generate robot actions from visual observations and language instructions, but their understanding of physical dynamics remains limited. Video world models can capture scene dynamics, yet generating future videos introduces high latency into the control loop. We introduce PDRVLA, whose lightweight Physical Dynamics Module extracts physical tokens from vision--language features to condition action generation without online video generation. The module learns through direct prediction of future RGB, depth, and optical-flow features, with auxiliary supervision through a frozen pretrained video world model. Training relies entirely on publicly available data, expanded through human-to-robot synthesis, subtask annotation, and embodied chain-of-thought (ECoT) annotation. Across four simulation benchmarks, PDRVLA achieves success rates of 99.3% on LIBERO, 89.9% on LIBERO-Plus, 93.6% on RoboTwin~2.0, and 81.5% on SimplerEnv. Ablations show improved future prediction with world-model supervision and evaluate how subtask conditioning, future object-pose supervision, and ECoT training affect action success.
Abstract (translated)
URL
https://arxiv.org/abs/2610.37381
PDF
-
Zooming without Zooming v2: From Seeing Details to Connecting Evidence for Generalizable Multimodal Perception
2026-10-27 11:11:53Lai Wei, Yatai Li, Liangbo He, Jun Lan, Renjie Gu, Linhan Cao, Junkai Lin, Huijia Zhu, Weiqiang Wang, Linghe Kong, Yue Wang, Zhuosheng Zhang, Weiran HuangAbstract
Multimodal perception forms the foundation of multimodal intelligence. In particular, spatial perception and multimodal long-context understanding are two pivotal tasks that underpin embodied AI and multimodal agents. However, synthesizing targeted, high-quality training data for these tasks remains difficult and costly. Our key insight is that these tasks share an underlying capability, which we call connecting evidence: identifying relevant visual facts, binding them to the correct entities, recovering their relations, and composing them into an answer. Crucially, targeted training data are far easier to synthesize for this capability than for these tasks themselves. To strengthen this capability, we propose EvidenceConnect, an easy-to-implement data synthesis framework that uses zoomed views of related regions within a single image to generate questions requiring comparison, aggregation, or chaining of visual evidence. To ensure quality, a reference answer is retained only when independent VLMs agree on it, and region-ablation tests discard questions whose answer survives the removal of selected regions. We then train base VLMs on the resulting data with RLVR, obtaining Zooming without Zooming v2 (ZwZ2). Although the synthesized data are not tailored to any downstream benchmark, ZwZ2 improves fine-grained and spatial perception, with further gains on embodied spatial reasoning, multimodal long-context understanding, multimodal agent tasks, and general visual reasoning. These results establish EvidenceConnect as an effective framework for supervising evidence connection and suggest that strengthening this shared capability leads to more generalizable multimodal perception.
Abstract (translated)
URL
https://arxiv.org/abs/2610.37037
PDF
-
A fully articulated humanoid dexterous hand with human-level joint structure enabled by linkage-based actuation
2026-10-27 07:53:51Jihao Li, Jianguo Wang, Haotian Guo, Yanzhe Wang, Guodong Lu, Huixu DongAbstract
Humanoid dexterous hands are a core component of embodied intelligence, enabling robots to translate high-level intent into rich and adaptive physical interaction. However, existing designs remain constrained by a persistent trade-off among anthropomorphic kinematic complexity, mechanical robustness, load capacity and control simplicity, limiting dexterous manipulation in unstructured environments. Here we present Torch-Hand, a fully articulated humanoid dexterous hand that replicates the joint structure and motion hierarchy of the human hand with 21 degrees of freedom (DOF), comprising a highly articulated five-DOF thumb and four DOF in each of the remaining fingers. The differentiated thumb integrates multi-axis CMC motion to provide broad opposition and flexible contact orientation relative to the four fingers. Unlike tendon-driven or hybrid actuation approaches, Torch-Hand adopts an entirely linkage-based transmission architecture. By integrating screw-linkage actuation, the hand achieves high grasping force and substantial payload capacity while maintaining a compact anthropomorphic form. Its actuation architecture is optimized for control tractability, with all actuators integrated within the palm and arranged in a serial-robot-like configuration that establishes a direct correspondence between motor motion and joint kinematics. This architecture mechanically decouples functional DOF to reduce unintended inter-joint motion propagation, while allowing independently addressable DOF to be actively coordinated into coupled multi-joint motion patterns during complex manipulation. Comprehensive experiments assess reachable workspace, coordinated fingertip trajectories, thumb opposition, 33-grasp taxonomy coverage, grasping force, payload capacity and task-level manipulation. These results establish Torch-Hand as a robust hardware foundation for dexterous embodied manipulation.
Abstract (translated)
URL
https://arxiv.org/abs/2610.36789
PDF
-
LabWorld: Learning Interactive 4D Worlds for Scientific Experimentation
2026-10-27 03:52:08Suozhi Huang, Kelsey Fu, Binxu Li, Luna Lyu, Kaize Wu, Wenbo Lu, David Smerkous, Jiahan Li, Siqi Zhu, Zhizhou Sha, Jiacheng Guo, Zhixuan Liang, Shilong Liu, Le Cong, Mengdi WangAbstract
Autonomous scientific agents must not only reason about experiments but also interact with the physical environments in which they are executed. Existing laboratory simulators typically rely on manually constructed assets and predefined procedures, while laboratory videos capture real equipment, layouts, and interactions but leave this information implicit in pixels. We introduce LabWorld, an agent-driven Real2Sim framework for reconstructing interactive 4D laboratory worlds from monocular RGB video. LabWorld recovers reusable 3D assets, a metric scene, time-varying object states, and procedure events. Multi-frame observations provide complementary evidence for asset and scene reconstruction, while motion reconstruction combines visual and geometric observations with event constraints encoding the spatial and temporal requirements of laboratory interactions. We evaluate LabWorld on real pipetting and vortexing videos collected in our laboratory against general-purpose agentic and dedicated reconstruction baselines. For pipetting, LabWorld achieves a mean Mask IoU of 0.501, exceeding the strongest baseline by 0.033. For vortexing, it achieves a mean Tube-Length-Normalized PCK-AUC of 0.638, exceeding the strongest baseline by 0.035. On five pipetting videos, event-conditioned reconstruction increases the fraction of modeled physical constraints satisfied from 14.3% (5/35) to 100% (35/35). The resulting worlds expose geometry, motion, articulation, and events as explicit, editable state for replay, inspection, and future embodied scientific systems.
Abstract (translated)
URL
https://arxiv.org/abs/2610.36592
PDF
-
RoboAuto: Autonomous Robot Program Search through Multi-Level Physical Understanding
2026-10-27 02:41:22Buzhao Liu, Jianing Ye, Xiu Yuan, Yangtong Feng, Chengsong Huang, Tyler Dinh, Yevgeniy Vorobeychik, Ning Zhang, Chongjie ZhangAbstract
Recently, LLM-based autonomous agents have shown strong capabilities in iteratively generating, evaluating, and refining executable solutions. In robotic manipulation, Code-as-Policy lets these agents search over modular and editable robot programs. However, effective program search requires physical understanding: agents must understand how objects can be manipulated, how scene geometry constrains actions, and why interactions succeed or fail. Existing methods rely mainly on execution feedback for program refinement, often leaving these physical questions unresolved. We introduce RoboAuto, a framework for robot program search that explicitly organizes physical understanding at the object, scene, and interaction levels through three components. First, a hierarchical knowledge base combines executable skills with object-centric knowledge of affordances, spatial relations, and action effects, learned from embodied data and online task solving. Second, scene grounding connects this knowledge to the current environment by identifying relevant objects and resolving action-critical quantities. Third, multi-stage planning with self-designed experiments checks whether each stage produces its expected physical effects and actively tests competing hypotheses to resolve physical uncertainties. RoboAuto achieves superior performance across five benchmark families, attaining an 89.1% success rate on short-horizon LIBERO-PRO tasks and more than twice the mean success rate of ASPIRE on LIBERO-PRO Long and LIBERO-Plus. It also outperforms ASPIRE and $\pi_{0.5}$ on three challenging long-horizon real-robot tasks requiring precise manipulation. We further show that the knowledge base transfers across simulators and embodiments, and that program search performance scales with its size. Project page: this https URL
Abstract (translated)
URL
https://arxiv.org/abs/2610.36533
PDF
