arXiv subjects

Dongbin Zhao

Publications and source records attributed to Dongbin Zhao.

At least 19 recordsLinked to original sources

arXiv2026

GIFT: Guided Intermediate Feature Training via Action-Oriented Structural Supervision for Robotic Manipulation

Vision-language pre-training and predictive world modeling provide robot policies with rich semantic and dynamic visual features, but their native action and visual-prediction objectives may omit critical physical and task structure while retaining control-irrelevant visual redundancy. We call this mismatch between visual richness and control utility the action-sufficiency gap. We investigate whether this gap can be bridged by guiding intermediate features to preserve three control-relevant structure in robotic manipulation: geometry governing motion feasibility, affordance encoding instruction-relevant entities, and goals grounding instructions in task-relevant regions. To this end, we present GIFT (Guided Intermediate Feature Training), an architecture-flexible framework for learning intermediate features that translates these structures into training-time constraints through geometry alignment, affordance prediction, and goal-region reconstruction. We instantiate GIFT in a Vision-Language-Action (VLA) policy, a direct-action World-Action Model (WAM), and an inverse-dynamics WAM while retaining each model's action formulation. Under zero-shot transfer to LIBERO-Plus, GIFT-VLA, GIFT-WAM-Fast, and GIFT-WAM-IDM outperform StarVLA-OFT, Fast-WAM, and Fast-WAM-IDM by 4.6, 12.6, and 5.2 points, reaching 79.6%, 72.6%, and 87.8%, respectively. On RoboCasa, the three GIFT variants reach 61.4%, 83.6%, and 82.3%, outperforming their counterparts by 12.6, 9.0, and 8.4 points, respectively. Together, these results establish learning functionally structured intermediate features as a reusable principle across model-specific action formulations, with especially large gains on articulated-object tasks and high-precision real-world manipulation under unseen visual and spatial perturbations. Project page: https://openphoenix-team.github.io/GIFT-pages.

cs.RO↗

arXiv2026

DriveVLA-M0: Failure-Aware Memory Augmentation for Autonomous Driving

Vision-Language-Action (VLA) models have recently emerged as a promising paradigm for end-to-end autonomous driving by enabling unified reasoning across perception, language, and planning. However, existing approaches lack mechanisms to exploit past failures or adapt to distribution shifts, causing the model to persistently underperform on similar scenarios where it has previously failed. In this paper, we propose DriveVLA-M0, a retrieval-augmented VLA with failure-aware latent memory. We construct a latent memory pool that stores failure cases along with their structure scene representations and expert trajectory labels, and design a dedicated Retrieve Model that decouples static road structure and dynamic agent interactions to enable structurally grounded retrieval. At inference time, retrieved cases are injected into the model via a lightweight decoupled LoRA-based test-time training (TTT) mechanism, allowing targeted and scenario-specific correction without modifying the backbone. Extensive experiments on NAVSIMv1 and NAVSIMv2 benchmark demonstrate that our approach consistently outperforms prior methods, achieving 94.1 PDMS on Navtest and 47.0 EPDMS on Navhard with only 26.44 ms TTT backward latency overhead. Furthermore, we show that DriveVLA-M0 scales effectively with additional memory, enabling training-free performance gains through memory expansion. The code is available at https://github.com/ZebinX/DriveVLA-M0.

cs.CV↗

arXiv2026

MemChain: Learning Interpretable Memory Traces for Memory-Augmented LLM Agents

Memory-augmented LLM agents typically answer queries by retrieving relevant memories and feeding them directly to an answer model. This retrieval-as-evidence paradigm assumes retrieved memories are already suitable for reasoning, leaving the answer model to resolve redundancy, conflicts, and weak relevance while incurring substantial context overhead in long-term memory tasks. We propose MemChain, a trainable post-retrieval memory policy that transforms retrieved candidates into answer-facing active memory, represented as a compact and grounded evidence context. Given a user query and retrieved candidates, MemChain first generates a question-conditioned evidence plan, then constructs an ordered grounded evidence trace that organizes retrieved memories according to their semantic roles and dependencies, and finally executes explicit memory actions to produce a concise evidence context for answer generation. To train the mediator, we introduce a two-stage learning framework. Supervised trace learning first teaches the policy to generate structurally valid plans, traces, actions, and evidence contexts. We then propose Trace-Guided Memory Policy Optimization (TMPO), a reinforcement learning objective that optimizes the memory policy using downstream answer quality while jointly encouraging trace grounding, evidence support, structural validity, and answer stability across multiple rollouts. Experiments on LoCoMo and LongMemEval-S demonstrate that MemChain consistently achieves state-of-the-art performance across both closed-source and open-weight frozen answer models while substantially reducing the memory context passed to the answer model.

cs.AI↗

arXiv2026

WALA Learning Executable Latent Actions from Action-Labeled Demonstrations and Action-Free Videos

Generalizable robot policies typically rely on action-labeled robot demonstrations, which are expensive to collect and difficult to scale. In contrast, large-scale human and robot videos contain rich physical interactions but often lack executable robot action labels. We present WALA, a framework for learning executable latent actions from both action-labeled demonstrations and action-free videos. WALA first pretrains a semantic-geometric latent action model from videos by modeling the evolution between current observations and sparsely sampled future observations. Instead of reconstructing raw pixels, WALA predicts future deltas in the DINOv3 feature space and dense depth space, preserving task-relevant semantic and geometric structure while reducing sensitivity to appearance details. During policy training, the pretrained encoder provides stable latent action targets, and the decoder serves as a trainable latent world model. The latent actions generated by the vision-language backbone are jointly supervised by robot action prediction, latent action target matching, and future dynamics prediction. This enables action-labeled demonstrations to provide executable control supervision, while action-free videos contribute dynamics supervision without requiring robot action annotations. Experiments show that WALA achieves strong performance on RoboTwin, sets a new state-of-the-art result on RoboCasa with 75.2% average success, and improves both policy performance and generalization in real-world manipulation tasks.

cs.RO↗

arXiv2026

VT-WAM: Visual-Tactile World Action Model for Contact-Rich Manipulation

Contact-rich manipulation requires policies to react to local deformation, pressure, slip, and friction, yet these cues are temporally sparse and often invisible in visual observations. Existing visual-tactile policies usually feed tactile observations directly into action prediction, but rarely model tactile deformation dynamics during action generation. In this paper, we introduce VT-WAM, a Visual-Tactile World Action Model that jointly learns future visual prediction, tactile deformation prediction, and action prediction within a unified flow matching framework. In particular, VT-WAM introduces (1) Asymmetric Mixture-of-Transformers (MoT) attention to bridge a first-frame visual anchor with temporal tactile dynamics, and (2) contact-gated Action-Visual-Tactile Attention Guidance (AVTAG) to encourage action queries to rely on tactile evidence during contact phases. Across six real-world contact-rich manipulation tasks, VT-WAM achieves a 71.67% average success rate, outperforming Fast-WAM by 26.67% and OmniVTLA by 35.84%. Ablations demonstrate that modeling tactile deformation dynamics and guiding contact-phase tactile attention are both important for contact-rich tasks. Project website: https://vt-wam.github.io/.

cs.RO↗

arXiv2026

UCOB: Learning to Utilize and Evolve Agentic Skills via Credit-Aware On-Policy Bidirectional Self-Distillation

Skill memories can improve agentic reinforcement learning by reusing past experience as textual guidance, but retrieved skills are not oracular: they may help in one state while misleading the same policy in another. This makes the common privileged-teacher assumption fragile, namely that a skill-conditioned prompt can be treated as a fixed teacher for the no-skill prompt. We introduce UCOB, a framework for learning to utilize and evolve agentic skills via credit-aware on-policy bidirectional self-distillation. UCOB treats skill-conditioned and no-skill prompts as two on-policy context views of the same model, compares their return-to-go within the same task and anchor state, and uses the higher-return view as the local teacher. This local credit signal internalizes useful skill-conditioned behavior, corrects misleading skill usage, and guides task/state skill memory updates, utility-aware retrieval, and reflection self-training. Experiments on agentic tasks, including ALFWorld, WebShop, and Search-QA, show that UCOB outperforms skill-free RL, skill-memory baselines, and self-distillation methods across model scales, with up to 23.5 and 18.0 point gains over SOTA baselines on ALFWorld and WebShop. Ablations and analyses further validate its core mechanisms, continual adaptation across environments, and modest training overhead. Code is available at https://github.com/TU2021/UCOB.

cs.AI↗

arXiv2026

ConsistencyPlanner: Real-time Planning with Fast-Sampling Consistency Models

Closed-loop planning in complex, real-world driving scenarios presents a critical challenge for autonomous driving systems. While traditional rule-based methods are interpretable, their predefined heuristics lack the adaptability for dynamic traffic environments. Learning-based approaches have shown considerable promise. Conversely, learning-based approaches, despite their promise, struggle to balance the modeling diverse and multimodal driving behaviors and real-time planning, often leading to indecisive or unsafe actions. To address this limitation, we propose Consistency Planner, a real-time planning framework with fast-sampling consistency models. Our approach is built upon two key technical contributions. Efficient Multimodal Sampling: We employ fast-sampling consistency models to generate a diverse set of plausible future trajectories. This enables efficient, real-time exploration of multimodal actions, overcoming the computational bottlenecks of previous iterative generative methods. Heterogeneous Feature Fusion: We introduce an attention-enhanced decoder that dynamically integrates heterogeneous input features (including scene feature and action token) into a cohesive representation for robust planning. Extensive evaluation in the Waymax simulator demonstrates superior performance in safety metrics compared to existing methods, with particularly strong results in challenging dynamic scenarios.

cs.RO↗

arXiv2026

Are Full Rollouts Necessary for On-Policy Distillation?

On-policy distillation (OPD) provides dense teacher feedback along student-generated rollouts rather than fixed teacher traces and has emerged as a promising post-training paradigm. However, standard OPD typically generates full rollouts during training, which is computationally expensive and may expose the student to unreliable teacher feedback at late rollout positions, especially during early training. We identify the rollout horizon as a key bottleneck in OPD that substantially impacts training efficiency. Unlike Reinforcement Learning with Verifiable Rewards (RLVR), OPD does not require a final answer reward to provide learning signals. Therefore, full rollouts may not always be necessary for OPD. Motivated by this insight, we propose two simple horizon-control strategies: Progressive OPD (POPD), which gradually expands the rollout horizon during training, and Truncated OPD (TOPD), which permanently performs distillation on reliable truncated rollouts. Experiments on mathematical reasoning show that POPD improves the training efficiency of OPD by up to 3$\times$, while TOPD matches OPD performance using only 10\% of the rollout horizon, leading to substantial wall-clock and memory reductions. These results demonstrate that controlling the rollout horizon offers a simple and practical path to more efficient OPD.

cs.CL↗

arXiv2026

X-DiffVLA: X-Embodied Diffusion Action Heads for Vision-Language-Action Models

Learning universal policies from cross-embodied data remains a fundamental challenge in robotics. Although Vision-Language-Action (VLA) models are pre-trained on large and diverse datasets, they typically rely on embodiment-specific fine-tuning to achieve strong performance in downstream tasks. This requirement severely limits their generalization capability and restricts knowledge transfer across embodiments performing similar tasks. To overcome these limitations, we focus on cross-embodied settings with shared robotic bases and heterogeneous end-effectors, and propose X-DiffVLA, a diffusion-based VLA model featuring a unified cross-embodied action head. X-DiffVLA can leverage the generative strengths of diffusion models to capture both the diversity and latent correlations in cross-embodied datasets. Specifically, we introduce Embodiment Forcing, a classifier-free guidance technique to implicitly steer action generation toward embodiment-specific functional components, capturing fine-grained structural nuances without explicit supervision. In addition, a Morphological Tree Diffusion approach is designed to strengthen behavioral correlations across diverse end-effectors, maximizing the transferability of heterogeneous demonstrations. Experimental results across RoboCasa and Isaac Gym, covering different embodiments from grippers to dexterous hands, show that X-DiffVLA achieves state-of-the-art performance, with improvements of 15.3% and 12.5%, respectively. Real-world evaluations further validate the robustness of the proposed framework and its effectiveness in scalable cross-embodied policy learning.

cs.RO↗

arXiv2026

Reinforcement Learning with a Bilevel World-Model Architecture for Scan-Order Optimisation in Laser Directed Energy Deposition

Scan-order design in laser directed energy deposition (LDED) is a delayed, path-dependent thermo-mechanical decision problem, because sequence quality becomes observable only after the complete deposition and cooling cycle. This work formulates LDED scan-order optimisation as a finite-horizon, permutation-constrained reinforcement-learning problem and develops a bilevel finite-element-teacher-labelled AI workflow. A surrogate-assisted teacher-guided optimisation loop learns the Abaqus-labelled response landscape and provides a tractable terminal-reward environment for policy training. A frozen Maskable Proximal Policy Optimization (MaskablePPO) policy is then used to generate legal scan-order candidates, which are independently validated through Abaqus thermo-mechanical simulations. The results show bounded, N-dependent policy-generation value rather than record-level dominance over the mature surrogate-assisted optimiser. The strongest scan orders are obtained by the teacher-guided surrogate loop, whereas PPO autonomously reaches competitive regions of the native response landscape, with stronger rank concentration at smaller track counts and a clear reliability boundary at longer horizons. The teacher-labelled landscape further supports a physically gated lexicographic reward hierarchy in which warpage admissibility is the primary constraint, plastic strain acts as a safety filter and residual-stress-related improvement is pursued conditionally within the admissible region. Validated sequences also reveal an interpretable scale-separated ordering tendency that combines global spatial dispersion with local structured grouping. This workflow provides a route from fixed scan-rule selection toward finite-element-teacher-validated policy generation, while preserving independent finite-element validation as the final physical gate.

cs.LG↗

arXiv2026

AutoSearch: Adaptive Search Depth for Efficient Agentic RAG via Reinforcement Learning

Agentic retrieval-augmented generation (RAG) systems enable large language models (LLMs) to solve complex tasks through multi-step interaction with external retrieval tools. However, such multi-step interaction often involves redundant search steps, incurring substantial computational cost and latency. Prior work limits search depth (i.e., the number of search steps) to reduce cost, but this often leads to underexploration of complex questions. To address this, we first investigate how search depth affects accuracy and find a minimal sufficient search depth that defines an accuracy-efficiency trade-off, jointly determined by question complexity and the agent's capability. Furthermore, we propose AutoSearch, a reinforcement learning (RL) framework that evaluates each search step via self-generated intermediate answers. By a self-answering mechanism, AutoSearch identifies the minimal sufficient search depth and promotes efficient search by rewarding its attainment while penalizing over-searching. In addition, reward mechanisms are introduced to stabilize search behavior and improve answer quality on complex questions. Extensive experiments on multiple benchmarks show that AutoSearch achieves a superior accuracy-efficiency trade-off, alleviating over-searching while preserving search quality.

cs.AI↗

arXiv2026

$\pi$-Play: Multi-Agent Self-Play via Privileged Self-Distillation without External Data

Deep search agents have emerged as a promising paradigm for addressing complex information-seeking tasks, but their training remains challenging due to sparse rewards, weak credit assignment, and limited labeled data. Self-play offers a scalable route to reduce data dependence, but conventional self-play optimizes students only through sparse outcome rewards, leading to low learning efficiency. In this work, we observe that self-play naturally produces a question construction path (QCP) during task generation, an intermediate artifact that captures the reverse solution process. This reveals a new source of privileged information: self-play can provide high-quality privileged information for the self-distillation at low cost and at scale, without relying on human feedback or curated privileged information. Leveraging this insight, we propose Privileged Information Self-Play ($\pi$-Play), a novel multi-agent self-evolution framework combining self-play and self-distillation. In $\pi$-Play, an examiner generates tasks together with QCPs, and a teacher employs QCP as privileged context to densely supervise a student via self-distillation. This design transforms sparse-reward self-play into a dense-feedback co-evolution. Extensive experiments show that data-free $\pi$-Play surpasses fully supervised search agents and improves evolutionary efficiency by 2-3$\times$ over conventional self-play. Code is available at https://github.com/zhyaoch/pi-play.

cs.LG↗

arXiv2026

Saliency-Guided Representation with Consistency Policy Learning for Visual Unsupervised Reinforcement Learning

Zero-shot unsupervised reinforcement learning (URL) offers a promising direction for building generalist agents capable of generalizing to unseen tasks without additional supervision. Among existing approaches, successor representations (SR) have emerged as a prominent paradigm due to their effectiveness in structured, low-dimensional settings. However, SR methods struggle to scale to high-dimensional visual environments. Through empirical analysis, we identify two key limitations of SR in visual URL: (1) SR objectives often lead to suboptimal representations that attend to dynamics-irrelevant regions, resulting in inaccurate successor measures and degraded task generalization; and (2) these flawed representations hinder SR policies from modeling multi-modal skill-conditioned action distributions and ensuring skill controllability. To address these limitations, we propose Saliency-Guided Representation with Consistency Policy Learning (SRCP), a novel framework that improves zero-shot generalization of SR methods in visual URL. SRCP decouples representation learning from successor training by introducing a saliency-guided dynamics task to capture dynamics-relevant representations, thereby improving successor measure and task generalization. Moreover, it integrates a fast-sampling consistency policy with URL-specific classifier-free guidance and tailored training objectives to improve skill-conditioned policy modeling and controllability. Extensive experiments on 16 tasks across 4 datasets from the ExORL benchmark demonstrate that SRCP achieves state-of-the-art zero-shot generalization in visual URL and is compatible with various SR methods.

cs.CV↗

arXiv2026

Posterior Optimization with Clipped Objective for Bridging Efficiency and Stability in Generative Policy Learning

Expressive generative models have advanced robotic manipulation by capturing complex, multi-modal action distributions over temporally extended trajectories. However, fine-tuning these policies via RL remains challenging due to instability and sample inefficiency. We introduce Posterior Optimization with Clipped Objective (POCO), a principled RL framework that formulates policy improvement as a posterior inference problem tailored for temporal action chunks. Through an Expectation-Maximization procedure, POCO distills a reward-weighted implicit posterior into the policy without likelihood estimation. Furthermore, POCO adopts an offline-to-online paradigm that anchors online exploration to pre-trained priors, and its model-agnostic design scales to fine-tune large VLA models without architectural modifications. Evaluations across 7 simulation benchmarks and 4 contact-rich real-world tasks demonstrate that POCO prevents catastrophic policy collapse, outperforms SOTA baselines, and achieves a 96.7% success rate on real-world tasks. Videos are available at our project website https://cccedric.github.io/poco/.

cs.RO↗

arXiv2026

Dynamic Dual-Granularity Skill Bank for Agentic RL

Agentic RL can benefit substantially from reusable experience, yet existing skill-based methods mainly extract trajectory-level guidance and often lack principled mechanisms for maintaining an evolving skill memory. We propose D2Skill, a dynamic dual-granularity skill bank for agentic RL that organizes reusable experience into task skills for high-level guidance and step skills for fine-grained decision support and error correction. D2Skill jointly trains the policy and skill bank through paired baseline and skill-injected rollouts under the same policy, using their performance gap to derive hindsight utility signals for both skill updating and policy optimization. Built entirely from training-time experience, the skill bank is continuously expanded through reflection and maintained with utility-aware retrieval and pruning. Experiments on ALFWorld, WebShop, and Search-Augmented QA tasks show that D2Skill substantially improves performance over skill-free baselines across models of different scales. Further ablations and analyses show that both dual-granularity skill modeling and dynamic skill maintenance are critical to these gains, while the learned skills exhibit higher utility, transfer across evaluation settings, and introduce only modest training overhead.

cs.AI↗

arXiv2026

Revisiting On-Policy Distillation: Empirical Failure Modes and Simple Fixes

On-policy distillation (OPD) is increasingly used in LLM post-training because it can leverage a teacher model to provide dense supervision on student rollouts. The standard implementation, however, usually reduces distribution matching to a sampled-token log-ratio, which can make the learning signal fragile on long rollouts whose prefixes drift away from the teacher's typical support. We revisit this formulation from both theoretical and implementation perspectives. Theoretically, token-level OPD is biased relative to sequence-level reverse-KL minimization, but admits a substantially tighter worst-case variance bound; a controlled synthetic study further shows that stronger future-reward coupling increases gradient variance and destabilizes training. Empirically, we identify three failure modes of sampled-token OPD: imbalanced token-level supervision, unreliable teacher guidance on student-generated prefixes, and tokenizer or special-token mismatch. These findings motivate teacher top-K local support matching, a truncated reverse-KL objective that compares teacher and student distributions over a teacher-supported token set at each prefix, together with top-p rollout sampling and special-token masking. Across single-task reasoning and multi-task benchmarks spanning agentic and reasoning settings, this objective improves optimization stability and yields a +19.8% performance gain over standard sampled-token OPD baselines, providing a practical recipe for more stable on-policy distillation.

cs.LG↗

arXiv2026

Latent-WAM: Latent World Action Modeling for End-to-End Autonomous Driving

We introduce Latent-WAM, an efficient end-to-end autonomous driving framework that achieves strong trajectory planning through spatially-aware and dynamics-informed latent world representations. Existing world-model-based planners suffer from inadequately compressed representations, limited spatial understanding, and underutilized temporal dynamics, resulting in sub-optimal planning under constrained data and compute budgets. Latent-WAM addresses these limitations with two core modules: a Spatial-Aware Compressive World Encoder (SCWE) that distills geometric knowledge from a foundation model and compresses multi-view images into compact scene tokens via learnable queries, and a Dynamic Latent World Model (DLWM) that employs a causal Transformer to autoregressively predict future world status conditioned on historical visual and motion representations. Extensive experiments on NAVSIM v2 and HUGSIM demonstrate new state-of-the-art results: 89.3 EPDMS on NAVSIM v2 and 28.9 HD-Score on HUGSIM, surpassing the best prior perception-free method by 3.2 EPDMS with significantly less training data and a compact 104M-parameter model.

cs.CV↗

arXiv2026

DreamerAD: Efficient Reinforcement Learning via Latent World Model for Autonomous Driving

We introduce DreamerAD, the first latent world model framework that enables efficient reinforcement learning for autonomous driving by compressing diffusion sampling from 100 steps to 1 - achieving 80x speedup while maintaining visual interpretability. Training RL policies on real-world driving data incurs prohibitive costs and safety risks. While existing pixel-level diffusion world models enable safe imagination-based training, they suffer from multi-step diffusion inference latency (2s/frame) that prevents high-frequency RL interaction. Our approach leverages denoised latent features from video generation models through three key mechanisms: (1) shortcut forcing that reduces sampling complexity via recursive multi-resolution step compression, (2) an autoregressive dense reward model operating directly on latent representations for fine-grained credit assignment, and (3) Gaussian vocabulary sampling for GRPO that constrains exploration to physically plausible trajectories. DreamerAD achieves 87.7 EPDMS on NavSim v2, establishing state-of-the-art performance and demonstrating that latent-space RL is effective for autonomous driving.

cs.LG↗