Xuyang Chen

Yinjie Wang, Xuyang Chen, Xiaolong Jin et al.

Every agent interaction generates a next-state signal, namely the user reply, tool output, terminal or GUI state change that follows each action, yet no existing agentic RL system recovers it as a live, online learning source. We present OpenClaw-RL, a framework built on a simple observation: next-state signals are universal, and policy can learn from all of them simultaneously. Personal conversations, terminal executions, GUI interactions, SWE tasks, and tool-call traces are not separate training problems. They are all interactions that can be used to train the same policy in the same loop. Next-state signals encode two forms of information: evaluative signals, which indicate how well the action performed and are extracted as scalar rewards via a PRM judge; and directive signals, which indicate how the action should have been different and are recovered through Hindsight-Guided On-Policy Distillation (OPD). We extract textual hints from the next state, construct an enhanced teacher context, and provide token-level directional advantage supervision that is richer than any scalar reward. Due to the asynchronous design, the model serves live requests, the PRM judges ongoing interactions, and the trainer updates the policy at the same time, with zero coordination overhead between them. Applied to personal agents, OpenClaw-RL enables an agent to improve simply by being used, recovering conversational signals from user re-queries, corrections, and explicit feedback. Applied to general agents, the same infrastructure supports scalable RL across terminal, GUI, SWE, and tool-call settings, where we additionally demonstrate the utility of process rewards. Code: https://github.com/Gen-Verse/OpenClaw-RL

Weixuan Liu, Qingfeng Zhuge, Xuyang Chen

Legal article retrieval is critical for building traceable and reliable legal AI systems, where conclusions must be grounded in specific legal articles. However, existing open-domain retrieval methods rely heavily on surface-level lexical or semantic similarity, making it difficult for them to distinguish legally relevant articles from those that are textually similar but legally inapplicable or misaligned with the user's underlying intent. To bridge this gap, we propose \textsc{LexPath}, a domain-oriented multi-path framework comprising a multi-path retrieval module and an intent-aware reranking module. The retrieval module combines two complementary legal-specific paths to collect candidate articles: an IRAC-guided sparse path that expands queries with legally informative keywords, and a structure-guided dense path trained with hard negatives derived from legal hierarchy and citation relations. Then, the reranking module further refines the candidate ranking by incorporating the intent consistency score between queries and legal articles. We evaluate \textsc{LexPath} on two publicly available benchmarks focusing on general-public queries and a self-constructed benchmark targeting domain-professional scenarios. Experimental results demonstrate that \textsc{LexPath} consistently outperforms lexical, dense, hybrid, and adaptive retrieval-augmented generation (RAG) baselines. Ablation studies further verify the effectiveness of each component.

Xuyang Chen, Jingliang Duan, Yingbin Liang et al.

The actor-critic (AC) reinforcement learning algorithms have been the powerhouse behind many challenging applications. Nevertheless, its convergence is fragile in general. To study its instability, existing works mostly consider the uncommon double-loop variant or basic models with finite state and action space. We investigate the more practical single-sample two-timescale AC for solving the canonical linear quadratic regulator (LQR) problem, where the actor and the critic update only once with a single sample in each iteration on an unbounded continuous state and action space. Existing analysis cannot conclude the convergence for such a challenging case. We develop a new analysis framework that allows establishing the global convergence to an $ε$-optimal solution with at most an $\mathcal{O}(ε^{-2.5})$ sample complexity. To our knowledge, this is the first finite-time convergence analysis for the single sample two-timescale AC for solving LQR with global optimality. The sample complexity improves those of other variants by orders, which sheds light on the practical wisdom of single sample algorithms. We also further validate our theoretical findings via comprehensive simulation comparisons.

Jingliang Duan, Jie Li, Xuyang Chen et al.

In recent times, significant advancements have been made in delving into the optimization landscape of policy gradient methods for achieving optimal control in linear time-invariant (LTI) systems. Compared with state-feedback control, output-feedback control is more prevalent since the underlying state of the system may not be fully observed in many practical settings. This paper analyzes the optimization landscape inherent to policy gradient methods when applied to static output feedback (SOF) control in discrete-time LTI systems subject to quadratic cost. We begin by establishing crucial properties of the SOF cost, encompassing coercivity, L-smoothness, and M-Lipschitz continuous Hessian. Despite the absence of convexity, we leverage these properties to derive novel findings regarding convergence (and nearly dimension-free rate) to stationary points for three policy gradient methods, including the vanilla policy gradient method, the natural policy gradient method, and the Gauss-Newton method. Moreover, we provide proof that the vanilla policy gradient method exhibits linear convergence towards local minima when initialized near such minima. The paper concludes by presenting numerical examples that validate our theoretical findings. These results not only characterize the performance of gradient descent for optimizing the SOF problem but also provide insights into the effectiveness of general policy gradient methods within the realm of reinforcement learning.

Guojian Wang, Jianxiang Liu, Xinyuan Li et al.

In this paper, we investigate preference-based reinforcement learning (PbRL), which enables reinforcement learning (RL) agents to learn from human feedback. This is particularly valuable when defining a fine-grain reward function is not feasible. However, this approach is inefficient and impractical for promoting deep exploration in hard-exploration tasks with long horizons and sparse rewards. To tackle this issue, we introduce LOPE: \textbf{L}earning \textbf{O}nline with trajectory \textbf{P}reference guidanc\textbf{E}, an end-to-end preference-guided RL framework that enhances exploration efficiency in hard-exploration tasks. Our intuition is that LOPE directly adjusts the focus of online exploration by considering human feedback as guidance, thereby avoiding the need to learn a separate reward model from preferences. Specifically, LOPE includes a two-step sequential policy optimization technique consisting of trust-region-based policy improvement and preference guidance steps. We reformulate preference guidance as a trajectory-wise state marginal matching problem that minimizes the maximum mean discrepancy distance between the preferred trajectories and the learned policy. Furthermore, we provide a theoretical analysis to characterize the performance improvement bound and evaluate the effectiveness of the LOPE. When assessed in various challenging hard-exploration environments, LOPE outperforms several state-of-the-art methods in terms of convergence rate and overall performance.The code used in this study is available at https://github.com/buaawgj/LOPE.

Xuyang Chen, Lin Zhao

Actor-critic methods have achieved significant success in many challenging applications. However, its finite-time convergence is still poorly understood in the most practical single-timescale form. Existing works on analyzing single-timescale actor-critic have been limited to i.i.d. sampling or tabular setting for simplicity. We investigate the more practical online single-timescale actor-critic algorithm on continuous state space, where the critic assumes linear function approximation and updates with a single Markovian sample per actor step. Previous analysis has been unable to establish the convergence for such a challenging scenario. We demonstrate that the online single-timescale actor-critic method provably finds an $ε$-approximate stationary point with $\widetilde{\mathcal{O}}(ε^{-2})$ sample complexity under standard assumptions, which can be further improved to $\mathcal{O}(ε^{-2})$ under the i.i.d. sampling. Our novel framework systematically evaluates and controls the error propagation between the actor and critic. It offers a promising approach for analyzing other single-timescale reinforcement learning algorithms as well.

Xuyang Chen, Conglang Zhang, Chuanheng Fu et al.

Driven by the emergence of Controllable Video Diffusion, existing Sim2Real methods for autonomous driving video generation typically rely on explicit intermediate representations to bridge the domain gap. However, these modalities face a fundamental Consistency-Realism Dilemma. Low-level signals (e.g., edges, blurred images) ensure precise control but compromise realism by "baking in" synthetic artifacts, whereas high-level priors (e.g., depth, semantics, HDMaps) facilitate photorealism but lack the structural detail required for consistent guidance. In this work, we present Driving with DINO (DwD), a novel framework that leverages Vision Foundation Module (VFM) features as a unified bridge between the simulation and real-world domains. We first identify that these features encode a spectrum of information, from high-level semantics to fine-grained structure. To effectively utilize this, we employ Principal Subspace Projection to discard the high-frequency elements responsible for "texture baking," while concurrently introducing Random Channel Tail Drop to mitigate the structural loss inherent in rigid dimensionality reduction, thereby reconciling realism with control consistency. Furthermore, to fully leverage DINOv3's high-resolution capabilities for enhancing control precision, we introduce a learnable Spatial Alignment Module that adapts these high-resolution features to the diffusion backbone. Finally, we propose a Causal Temporal Aggregator employing causal convolutions to explicitly preserve historical motion context when integrating frame-wise DINO features, which effectively mitigates motion blur and guarantees temporal stability. Project page: https://albertchen98.github.io/DwD-project/

Guojian Wang, Quinson Hon, Xuyang Chen et al.

Cross-domain shifts present a significant challenge for decision transformer (DT) policies. Existing cross-domain policy adaptation methods typically rely on a single simple filtering criterion to select source trajectory fragments and stitch them together. They match either state structure or action feasibility. However, the selected fragments still have poor stitchability: state structures can misalign, the return-to-go (RTG) becomes incomparable when the reward or horizon changes, and actions may jump at trajectory junctions. As a result, RTG tokens lose continuity, which compromises DT's inference ability. To tackle these challenges, we propose Data Fusion-Enhanced Decision Transformer (DFDT), a compact pipeline that restores stitchability. Particularly, DFDT fuses scarce target data with selectively trusted source fragments via a two-level data filter, maximum mean discrepancy (MMD) mismatch for state-structure alignment, and optimal transport (OT) deviation for action feasibility. It then trains on a feasibility-weighted fusion distribution. Furthermore, DFDT replaces RTG tokens with advantage-conditioned tokens, which improves the continuity of the semantics in the token sequence. It also applies a $Q$-guided regularizer to suppress junction value and action jumps. Theoretically, we provide bounds that tie state value and policy performance gaps to the MMD-mismatch and OT-deviation measures, and show that the bounds tighten as these two measures shrink. We show that DFDT improves return and stability over strong offline RL and sequence-model baselines across gravity, kinematic, and morphology shifts on D4RL-style control tasks, and further corroborate these gains with token-stitching and sequence-semantics stability analyses.

Xuyang Chen, Dong Wang, Konrad Schindler et al.

Recently, Transformer-based text detection techniques have sought to predict polygons by encoding the coordinates of individual boundary vertices using distinct query features. However, this approach incurs a significant memory overhead and struggles to effectively capture the intricate relationships between vertices belonging to the same instance. Consequently, irregular text layouts often lead to the prediction of outlined vertices, diminishing the quality of results. To address these challenges, we present an innovative approach rooted in Sparse R-CNN: a cascade decoding pipeline for polygon prediction. Our method ensures precision by iteratively refining polygon predictions, considering both the scale and location of preceding results. Leveraging this stabilized regression pipeline, even employing just a single feature vector to guide polygon instance regression yields promising detection results. Simultaneously, the leverage of instance-level feature proposal substantially enhances memory efficiency (>50% less vs. the state-of-the-art method DPText-DETR) and reduces inference speed (>40% less vs. DPText-DETR) with minor performance drop on benchmarks.

Madhumitha Venkatesan, Xuyang Chen, Dongyu Liu

Time-series classification (TSC) has advanced significantly with deep learning, yet most models rely solely on raw numerical inputs, overlooking alternative representations. While texture-based encodings such as Gramian Angular Fields (GAF) and Recurrence Plots (RP) convert time series into 2D images, they often require heavy preprocessing and yield less intuitive representations. In contrast, chart-based visualizations offer more interpretable alternatives and show promise in specific domains; however, their effectiveness remains underexplored, with limited systematic evaluation across chart types, visual encoding choices, and datasets. In this work, we introduce VTBench, a systematic and extensible framework that re-examines TSC through multimodal fusion of raw sequences and chart-based visualizations. VTBench generates lightweight, human-interpretable plots -- line, area, bar, and scatter, providing complementary views of the same signal. We develop a modular architecture supporting multiple fusion strategies, including single-chart visual-numerical fusion, multi-chart visual fusion, and full multimodal fusion with raw inputs. Through experiments across 31 UCR datasets, we show that: (1) chart-only models are competitive in selected settings, particularly on smaller datasets; (2) combining multiple chart types can improve accuracy by capturing complementary visual cues; and (3) multimodal models improve or maintain performance when visual features provide non-redundant information, but may degrade accuracy when they introduce redundancy. We further distill practical guidelines for selecting chart types, fusion strategies, and configurations. VTBench establishes a unified foundation for interpretable and effective multimodal time-series classification.

Xuyang Chen, Keyu Yan, Wenhan Cao et al.

Offline reinforcement learning (RL) learns policies from fixed datasets without online interactions, but suffers from distribution shift, causing inaccurate evaluation and overestimation of out-of-distribution (OOD) actions. Existing methods counter this by conservatively discouraging all OOD actions, which limits generalization. We propose Advantage-based Diffusion Actor-Critic (ADAC), which evaluates OOD actions via an advantage-like function and uses it to modulate the Q-function update discriminatively. Our key insight is that the (state) value function is generally learned more reliably than the action-value function; we thus use the next-state value to indirectly assess each action. We develop a PointMaze environment to clearly visualize that advantage modulation effectively selects superior OOD actions while discouraging inferior ones. Moreover, extensive experiments on the D4RL benchmark show that ADAC achieves state-of-the-art performance, with especially strong gains on challenging tasks.

Xinke Shen, Lingyi Tao, Xuyang Chen et al.

Neural representations induced by naturalistic stimuli offer insights into how humans respond to stimuli in daily life. Understanding neural mechanisms underlying naturalistic stimuli processing hinges on the precise identification and extraction of the shared neural patterns that are consistently present across individuals. Targeting the Electroencephalogram (EEG) technique, known for its rich spatial and temporal information, this study presents a framework for Contrastive Learning of Shared SpatioTemporal EEG Representations across individuals (CL-SSTER). CL-SSTER utilizes contrastive learning to maximize the similarity of EEG representations across individuals for identical stimuli, contrasting with those for varied stimuli. The network employed spatial and temporal convolutions to simultaneously learn the spatial and temporal patterns inherent in EEG. The versatility of CL-SSTER was demonstrated on three EEG datasets, including a synthetic dataset, a natural speech comprehension EEG dataset, and an emotional video watching EEG dataset. CL-SSTER attained the highest inter-subject correlation (ISC) values compared to the state-of-the-art ISC methods. The latent representations generated by CL-SSTER exhibited reliable spatiotemporal EEG patterns, which can be explained by properties of the naturalistic stimuli. CL-SSTER serves as an interpretable and scalable framework for the identification of inter-subject shared neural representations in naturalistic neuroscience.

Xuyang Chen, Jingliang Duan, Lin Zhao

Actor-critic methods have achieved state-of-the-art performance in various challenging tasks. However, theoretical understandings of their performance remain elusive and challenging. Existing studies mostly focus on practically uncommon variants such as double-loop or two-timescale stepsize actor-critic algorithms for simplicity. These results certify local convergence on finite state- or action-space only. We push the boundary to investigate the classic single-sample single-timescale actor-critic on continuous (infinite) state-action space, where we employ the canonical linear quadratic regulator (LQR) problem as a case study. We show that the popular single-timescale actor-critic can attain an epsilon-optimal solution with an order of epsilon to -2 sample complexity for solving LQR on the demanding continuous state-action space. Our work provides new insights into the performance of single-timescale actor-critic, which further bridges the gap between theory and practice.

Xuyang Chen, Guojian Wang, Keyu Yan et al.

Offline reinforcement learning (RL) learns effective policies from pre-collected datasets, offering a practical solution for applications where online interactions are risky or costly. Model-based approaches are particularly advantageous for offline RL, owing to their data efficiency and generalizability. However, due to inherent model errors, model-based methods often artificially introduce conservatism guided by heuristic uncertainty estimation, which can be unreliable. In this paper, we introduce VIPO, a novel model-based offline RL algorithm that incorporates self-supervised feedback from value estimation to enhance model training. Specifically, the model is learned by additionally minimizing the inconsistency between the value learned directly from the offline data and the one estimated from the model. We perform comprehensive evaluations from multiple perspectives to show that VIPO can learn a highly accurate model efficiently and consistently outperform existing methods. In particular, it achieves state-of-the-art performance on almost all tasks in both D4RL and NeoRL benchmarks. Overall, VIPO offers a general framework that can be readily integrated into existing model-based offline RL algorithms to systematically enhance model accuracy.

Puzhen Zhang, Xuyang Chen, Yu Feng et al.

Given a map description through global traversal navigation instructions (e.g., visiting each room sequentially with action signals such as north, west, etc.), an LLM can often infer the implicit spatial layout of the environment and answer user queries by providing a shortest path from a start to a destination (for instance, navigating from the lobby to a meeting room via the hall and elevator). However, such context-dependent querying becomes incapable as the environment grows much longer, motivating the need for incremental map construction that builds a complete topological graph from stepwise observations. We propose a framework for LLM-driven construction and map repair, designed to detect, localize, and correct structural inconsistencies in incrementally constructed navigation graphs. Central to our method is the Version Control, which records the full history of graph edits and their source observations, enabling fine-grained rollback, conflict tracing, and repair evaluation. We further introduce an Edge Impact Score to prioritize minimal-cost repairs based on structural reachability, path usage, and conflict propagation. To properly evaluate our approach, we create a refined version of the MANGO benchmark dataset by systematically removing non-topological actions and inherent structural conflicts, providing a cleaner testbed for LLM-driven construction and map repair. Our approach significantly improves map correctness and robustness, especially in scenarios with entangled or chained inconsistencies. Our results highlight the importance of introspective, history-aware repair mechanisms for maintaining coherent spatial memory in LLM agents.

Xuyang Chen, Zhijun Zhai, Kaixuan Zhou et al.

Mesh models have become increasingly accessible for numerous cities; however, the lack of realistic textures restricts their application in virtual urban navigation and autonomous driving. To address this, this paper proposes MeSS (Meshbased Scene Synthesis) for generating high-quality, styleconsistent outdoor scenes with city mesh models serving as the geometric prior. While image and video diffusion models can leverage spatial layouts (such as depth maps or HD maps) as control conditions to generate street-level perspective views, they are not directly applicable to 3D scene generation. Video diffusion models excel at synthesizing consistent view sequences that depict scenes but often struggle to adhere to predefined camera paths or align accurately with rendered control videos. In contrast, image diffusion models, though unable to guarantee cross-view visual consistency, can produce more geometry-aligned results when combined with ControlNet. Building on this insight, our approach enhances image diffusion models by improving cross-view consistency. The pipeline comprises three key stages: first, we generate geometrically consistent sparse views using Cascaded Outpainting ControlNets; second, we propagate denser intermediate views via a component dubbed AGInpaint; and third, we globally eliminate visual inconsistencies (e.g., varying exposure) using the GCAlign module. Concurrently with generation, a 3D Gaussian Splatting (3DGS) scene is reconstructed by initializing Gaussian balls on the mesh surface. Our method outperforms existing approaches in both geometric alignment and generation quality. Once synthesized, the scene can be rendered in diverse styles through relighting and style transfer techniques.

Zhenghao Peng, Xuyang Chen, Chengwen Xu et al.

Neural network based approximate computing is a universal architecture promising to gain tremendous energy-efficiency for many error resilient applications. To guarantee the approximation quality, existing works deploy two neural networks (NNs), e.g., an approximator and a predictor. The approximator provides the approximate results, while the predictor predicts whether the input data is safe to approximate with the given quality requirement. However, it is non-trivial and time-consuming to make these two neural network coordinate---they have different optimization objectives---by training them separately. This paper proposes a novel neural network structure---AXNet---to fuse two NNs to a holistic end-to-end trainable NN. Leveraging the philosophy of multi-task learning, AXNet can tremendously improve the invocation (proportion of safe-to-approximate samples) and reduce the approximation error. The training effort also decrease significantly. Experiment results show 50.7% more invocation and substantial cuts of training time when compared to existing neural network based approximate computing framework.