arXiv subjects

Rui Zheng

Publications and source records attributed to Rui Zheng.

At least 19 recordsLinked to original sources

arXiv2026

NorthCUA Technical Report: Turbocharging Computer-Use Agents through Experience at Scale

Scaling computer-use agents from individual actions to complex software work requires experience that connects decisions to complete outcomes. We present NorthCUA, an integrated system for turbocharging computer-use agents through experience at scale. Its Experience Flywheel supplies diverse executable tasks to the NorthCUA Harness, which sustains long interactions, records decisions, and checks task outcomes. The Flywheel uses these records to curate verified trajectories. For unsolved tasks, recursive self-improvement evolves reusable skills and preserves verified milestones so later attempts build on earlier progress. Staged Learning combines this experience with grounding data from the Flywheel to develop GUI competence through mid-training and long-horizon supervised fine-tuning. The policy then learns from fresh attempts in the same Harness through joint desktop-web reinforcement learning, closing the loop between experience production and policy improvement. The resulting Nano, Mini, and Pro family achieves state-of-the-art results among open-source models across GUI grounding, desktop execution, and Web interaction under the reported evaluation settings. For more responsive Web workflows, NorthCUA-Ultrafast pairs direct action selection with open-ended generation on pre-RL Nano, offering a measured quality-latency tradeoff. Together, these advances establish NorthCUA as a high-performing model family and a reusable foundation for agents that carry complex software work from intent to completion.

cs.LG↗

arXiv2026

WebAnything: From the Wild Web to Scalable Agent Environments

Web agents require diverse, executable, and resettable website environments for reproducible training and evaluation. Human-assisted mirrors demand per-site engineering, while generative construction can diverge from specified real websites. Capture-and-replay preserves observations, with interaction coverage constrained by captured content and replay capabilities. We present WebAnything, a fully automated framework that reconstructs source-grounded, reusable Web environments from real URLs without per-site manual implementation or repair after initial setup and authorization. An Explorer-Builder collects browser-observable structures, resources, and interaction outcomes; an independent verifier checks frozen candidates and guides local repair or targeted source recapture. We construct 244 website artifacts across 14 application domains and 53 categories, supporting 12,984 executed and accepted tasks. Compared with human-assisted WebHarbor, WebAnything achieves higher aggregate scores on three fidelity metrics, with 12 wins, two ties, and no losses in a blind audit. Fine-tuning Qwen3.5-9B on 5,856 interaction trajectories improves REAL success by 9.9 percentage points, Odysseys-Easy Rubric Avg and Task Avg by 6.25 and 6.32 percentage points, and WebArena-Verified Overall success by 13.33 percentage points under the fixed harness. Code: https://github.com/china-qijizhifeng/Web-Anything

cs.AI↗

arXiv2026

AGORA: An Archive-Grounded Benchmark for Agentic Workplace Document Reasoning

Large language models are increasingly deployed as agents that reason over documents rather than answer from parametric knowledge. We study archive-grounded reasoning: locating sparse evidence across a large, messy collection of workplace files, reconciling inconsistent terminology, units, and time conventions, and computing an answer. Existing benchmarks address only parts of this setting and none jointly stresses archive-groundedness, agentic exploration, and cross-domain coverage. We introduce Agora, a benchmark pairing 362 questions with eight domain collections of 9,664 authentic documents and 372M tokens, far exceeding any model's context window, so agents must explore deliberately rather than scan exhaustively. Agora is built by an agentic pipeline combining cross-document task synthesis, leakage-preventing obfuscation, and difficulty filtering. Evaluating eight models, we find the task far from solved: even the strongest reaches only 59.4% accuracy, with notable variation across domains.

cs.CL↗

arXiv2026

WorkRover: Scaling Long-Horizon Cowork Agent Training Via Recursive Environment Evolution

Scaling interactive environments is important for training long-horizon agents through reinforcement learning. These environments often require further testing and refinement after initial generation, and correcting defects in a task may also require updating its work context and verifier. However, existing construction pipelines offer limited support for such iterative refinement while keeping these components aligned. We introduce WorkRover, a framework for training long-horizon cowork agents through recursive environment evolution. Its harness-driven synthesis enables construction agents to jointly build and validate semantically aligned work contexts, executable tasks, and evidence-grounded verifiers, adapting their actions to workspace state and execution feedback rather than following a fixed construction workflow. To support environment evolution, we introduce Factorial Compatibility Replay (FCR), which uses rollout feedback to evaluate combinations of component revisions through dependency-closed replay and selects the smallest validated repair among tested candidates while preserving task requirements and evaluation constraints. To provide finer-grained training signals, we propose Verifier-to-Turn Credit Assignment (VTCA), which augments trajectory-level GRPO advantages with signals from deterministic workspace-progress checks and assigns a bounded share of positive-progress credit to prerequisite turns using recorded tool-output and artifact dependencies. Using WorkRover, we post-train Qwen3.5-35B-A3B to obtain WorkRover-35B-A3B and evaluate it on several cowork-agent benchmarks. Its reported scores exceed those of Qwen3.5-35B-A3B by 26.27 percentage points on JobBench, 29.32 percentage points on OfficeQA Pro, and 413.25 Elo points on GDPval v2. These results suggest that WorkRover offers a promising foundation for scalable training of long-horizon cowork agents.

cs.AI↗

arXiv2026

Work2Skill: Capturing Human GUI Experience for Reusable Agent Skill Induction

Computer-use agents can perform increasingly complex GUI tasks, yet unfamiliar software and workflows requiring human domain knowledge remain challenging. Human demonstrations convey procedural knowledge through the same GUI interaction space, but reuse requires interpreting actions in context and separating workflow rules from task-specific details. We thus introduce Work2Skill, a framework that captures human GUI experience for reusable agent skill induction. WorkRecorder provides the framework's infrastructure for collecting this experience, aligning screen recordings, mouse and keyboard events, and available accessibility-tree information. Using WorkRecorder, we construct WorkDemo-350, the first synchronized multimodal dataset of human desktop GUI demonstrations for reusable agent skill induction and downstream evaluation. Its 350 demonstrations are screened for completeness and task success. We then propose an agentic skill-induction method that inspects evidence on demand to produce reusable skills capturing workflow rules, step dependencies, and completion checks. When the same four execution models are equipped with skills induced by each method under shared execution settings, Work2Skill achieves the highest scores and success rates. Mean score improvements over the corresponding No Skill baseline are 4.67--10.54 points on MyPCBench Bounded Action and 3.11--7.50 points on a 286-task subset of OSWorld-Verified. Our code and data are available at https://github.com/china-qijizhifeng/Work2Skill.

cs.AI↗

arXiv2026

Recognizing Signomial Convexity is Hard

Signomials---finite sums of generalized monomials with real exponents---are a natural machine learning model, combining parsimonious representations of power laws, inverse relationships, and multiplicative interactions with universal approximation and interpretable parameters. In fact, 45 of the 100 equations in the AI Feynman benchmark admit signomial representations. Moreover, signomial optimization is widely used in engineering design, communications, economics, and machine learning, but is computationally intractable in general. Convexity, the gold standard for efficient optimization, offers three routes to tractability for signomials: a signomial may be convex in its original variables, become convex after a logarithmic change of variables, or, when positive, become convex after additionally taking the logarithm of its value---the structure underlying disciplined geometric programming. We show that recognizing each form is strongly NP-hard, both on compact domains and globally. Our proofs start from gap-promise variants of polynomial convexity and develop polynomial-to-signomial reductions that preserve curvature gaps under the relevant logarithmic transformations.

math.OC↗

arXiv2026

WEFT: Scaling Tool-Use Post-Training for General-Purpose Agents

Recent efforts to scale tool-use post-training have largely centered on the synthesis of executable environments, which constitute only one component of a broader agentic interaction system comprising the environment, task, agent harness, and evaluator. Scaling environments in isolation, however, does not guarantee commensurate gains in model performance, because reliable learning signals depend on coherent interactions among all components of the agentic interaction system. To address this problem, we introduce WEFT (Whole-system Evolution For Tool-use Post-training), which couples scalable agentic interaction system construction, execution-driven self-evolution, and stable post-training. WEFT scales agentic interaction system construction across environment breadth, task complexity, and interaction diversity. Execution-driven self-evolution iteratively uses execution traces and state evidence to attribute failures and revise the responsible components, with fresh rollouts evaluating the changes and providing evidence for subsequent evolution rounds. For stable post-training at scale, WEFT addresses both optimization and execution reliability: prefix-preserving sampling retains verified progress and atomic-turn credit assignment localizes learning signals, while MegaMCP maintains isolated, recoverable state across concurrent rollouts over shared tool services. Extensive experiments across various models and benchmarks demonstrate the effectiveness of WEFT for tool-use post-training. WEFT-8B and WEFT-14B outperform all evaluated matched-size environment-scaling baselines on BFCL V4, $τ^2$-Bench, and Claw-Eval. In particular, WEFT-14B improves over Agent-World-14B by 6.41, 2.23, and 12.27 percentage points. WEFT-35B-A3B further extends these gains to more challenging long-horizon workflow benchmarks, including Toolathlon-Verified and AutomationBench.

cs.AI↗

arXiv2026

In-plane optimal qubit operation with control fidelities exceeding 99 %

Hole spin qubits based on semiconductor quantum dots are promising for building future large-scale quantum computers owing to their all-electrical manipulation. However, abundant physical mechanisms of valence band holes lead to anisotropic qubit properties. There is an opportunity to prolong the coherence time and achieve high-fidelity qubit manipulations. Here, we report a single-hole spin qubit in a planar germanium quantum dot and investigate its anisotropic susceptibility to charge noise under an in-plane magnetic field. By correlating the longitudinal spin-electric susceptibility with qubit coherence and control performance, we identify an optimal operating point where the sensitivity to charge noise is minimized. We find that optimizing the magnetic-field orientation reduces the spin-electric susceptibility, resulting in a five-fold enhancement of the Hahn-echo coherence time and a nearly tenfold suppression of control infidelity. At the optimal operating point, gate set tomography demonstrates the maximum gate fidelity of 99.82 %. Our finding enhances the prospects of hole spin qubits for scalable quantum information processing.

quant-ph↗

arXiv2026

UBone3D: Physics-Rectified Conditional Flow Matching for Anatomical 3D Shape Completion from Ultrasound

Three-dimensional ultrasound (US) is a safe, radiation-free complementary modality to CT and X-rays for longitudinal monitoring, yet its segmentation-derived partial point clouds are extremely artifact-laden. Consequently, it is challenging to recover a clean and complete anatomical structure from such US point clouds. In this paper, we present UBone3D, a novel framework based on physics-rectified conditional flow matching (CFM) that performs point cloud completion directly from partial US observations. UBone3D models deterministic physics artifacts (e.g., surface thickening, streaking, dropouts) via a simulated physics proxy, and introduces test-time physics rectification to steer the shape completion. At inference, the completion is jointly steered by two decoupled forces: (1) anatomical plausibility enforced by a CT-trained generative shape prior, BoneFM, and (2) physics consistency enforced by USimNet in the ultrasound formation space. Extensive experiments on simulated and in-vivo data demonstrate significant improvements in reconstruction accuracy and anatomical fidelity over existing baselines.

cs.CV↗

arXiv2026

NexForge: Scaling Agent Capabilities through Requirement-Driven Task Synthesis for LLMs

Scaling executable agent training data for LLM post-training is bottlenecked by substrate-bound methods that tie task generation to predefined tools, repositories, or skill graphs: expanding coverage requires manual substrate engineering, each new domain demands a bespoke pipeline, and the resulting task distributions often reflect substrate biases rather than real-world demand. We introduce NexForge, a requirement-driven framework that takes high-level capability requirements as input and synthesizes diverse, executable agent tasks and expert trajectories for SFT. NexForge first investigates real-world demand to construct scenarios and task profiles, then performs distribution-aware compilation to generate task directives. For each directive, NexForge automatically retrieves or constructs the required files, dependencies, and runtime configurations, and finally collects expert rollouts to produce training trajectories. Without domain-specific infrastructure, NexForge produces 3.6K terminal and 2K office tasks, improving Qwen3.5-35B-A3B Base from 22.5\% to 52.0\% on Terminal-Bench 2.0 and from 813 to 1338 Elo on GDPval; scaling further to 43.2K terminal tasks yields 58.4\%, on par with Claude Opus 4.6 equipped with Claude Code. Scaled further, NexForge-synthesized data contributes to the training of Nex-N2, a family of publicly available agent models that lift Qwen3.5-397B-A17B to 75.3\% on Terminal-Bench 2.1 and to 1585 Elo on GDPval---achieving state-of-the-art open-source performance and surpassing several frontier proprietary systems. Nex-N2 models are available at https://nex.sii.edu.cn/.

cs.SE↗

arXiv2026

Hierarchical Fault Localization for Autonomous Driving Systems with Hypothesis Validation and Intent Analysis

Comprehensive testing is essential for the safety and reliability of Autonomous Driving Systems (ADS). Existing techniques can detect system-level failures or attribute them to coarse-grained modules, but they often fall short of localizing the root cause in source code. As a result, debugging remains labor-intensive, requiring developers to connect behavioral violations with complex implementation logic. To address this gap, we present HINT, a two-phase framework for hierarchical ADS fault localization based on hypothesis validation and intent analysis. In Phase I, HINT transforms failure-triggering execution recordings into multi-modal abstractions and uses causal reasoning to identify the responsible module. In Phase II, it reconstructs design-side intent and implementation-side behavior, then localizes suspicious code through reliability-aware consistency checking, without costly re-simulation. We evaluate HINT on Apollo across diverse failure modes and modules. The results show that HINT achieves the strongest overall performance across module-level diagnosis and code-level localization metrics, with 77.8% end-to-end Class@5 accuracy on real-world bugs.

cs.SE↗

arXiv2026

Rethinking 3D Shape Generation: Diffusion over Superquadrics

Diffusion models have advanced 3D shape generation, yet most methods still denoise in high-cardinality spaces (e.g., voxel/SDF grids, meshes, or point clouds), which is computationally and memory intensive and makes it difficult to scale in terms of both higher resolution and stronger controllability. We rethink the diffusion representation and propose to move diffusion from dense geometry to compact geometric primitives, representing each shape as a small set of superquadrics. Instead of operating on thousands to millions of geometric representation values, we leverage 7KB superquadric parameters (pose, size, and shape), drastically reducing diffusion-state dimensionality and per-step compute/memory. Our diffusion-over-superquadrics improves scalability by supporting broader capabilities (e.g., resolution-free point-cloud decoding, part-level editing, and constraint-based design) and achieving competitive surface-fidelity and distributional performance on standard benchmarks after point-cloud decoding, while enabling efficient generation within 0.6s per shape for most conditions.

cs.CV↗

arXiv2026

Solving Imperfect-Recall Games via Sum-of-Squares Optimization

Extensive-form games (EFGs) provide a powerful framework for modeling sequential decision making, capturing strategic interaction under imperfect information, chance events, and temporal structure. Most positive algorithmic and theoretical results for EFGs assume perfect recall, where players remember all past information and actions. We study the increasingly relevant setting of imperfect-recall EFGs (IREFGs), where players may forget parts of their history or previously acquired information, and where equilibrium computation is provably hard. We propose sum-of-squares (SOS) hierarchies for computing ex-ante optimal strategies in single-player IREFGs and Nash equilibria in multi-player IREFGs, working over behavioral strategies. Our theoretical results show that (i) these hierarchies converge asymptotically, (ii) under genericity assumptions, the convergence is finite, and (iii) in single-player non-absentminded IREFGs, convergence occurs at a finite level determined by the number of information sets. Finally, we introduce the new classes of (SOS)-concave and (SOS)-monotone IREFGs, and show that in the single-player setting the SOS hierarchy converges at the first level, enabling equilibrium computation with a single semidefinite program (SDP).

cs.GT↗

arXiv2026

HiDream-O1-Image: A Natively Unified Image Generative Foundation Model with Pixel-level Unified Transformer

The evolution of visual generative models has long been constrained by fragmented architectures relying on disjoint text encoders and external VAEs. In this report, we present HiDream-O1-Image, a natively unified generative foundation model via pixel-space Diffusion Transformer, that pioneers a paradigm shift from modular architectures to an end-to-end in-context visual generation engine. By mapping raw image pixels, text tokens, and task-specific conditions into a single shared token space, HiDream-O1-Image achieves a structural unification of multimodal inputs within an Unified Transformer (UiT) architecture. This native encoding paradigm eliminates the need for separate VAEs or disjoint pre-trained text encoders, allowing the model to treat diverse generation and editing tasks as a consistent in-context reasoning process. Extensive experiments show that HiDream-O1-Image excels across various generation tasks, including text-to-image generation, instruction-based editing, and subject-driven personalization. Notably, with only 8B parameters, HiDream-O1-Image (8B) achieves performance parity with or even surpasses established state-of-the-art models with significantly larger parameters (e.g., 27B Qwen-Image). Crucially, to validate the immense scalability of this paradigm, we successfully scale the architecture up to over 200B parameters. Experimental results demonstrate that this massive-scale version HiDream-O1-Image-Pro (200B+) unlocks unprecedented generative capabilities and superior performance, establishing new state-of-the-art benchmarks. Ultimately, HiDream-O1-Image highlights the immense potential of natively unified architectures and charts a highly scalable path toward next-generation multimodal AI.

cs.CV↗

arXiv2026

Mechanism-Faithful Queueing Simulation Model Translation with Large Language Model Support

Queueing simulation studies often require substantial manual effort to translate conceptual system descriptions into executable programs and to verify that the implemented mechanisms match the intended queueing logic. Although large language models (LLMs) may produce executable scripts, executability alone is insufficient when arrival, routing, interruption, or reporting logic is wrong. This study presents a simulation-oriented support framework for \texttt{SimPy}-based queueing model translation. We propose a category-template framework for mechanism coverage with a staged adaptation workflow that targets structured event logic and common simulation-specific failure modes. On held-out task instances, the adapted models improve executability, output-format compliance, and instruction-mechanism consistency across basic, behavioral, and networked queueing settings, so the generated scripts are more reliable as queueing simulation scripts. Error analysis shows better preservation of routing semantics and interruption-resume logic, while also exposing remaining weaknesses in multi-node transfer and residual-service updates. Overall, the results suggest that the proposed framework can act as a simulation-faithful generator for more standardized and reproducible queueing model construction.

cs.CL↗

arXiv2026

EVPO: Explained Variance Policy Optimization for Adaptive Critic Utilization in LLM Post-Training

Reinforcement learning (RL) for LLM post-training faces a fundamental design choice: whether to use a learned critic as a baseline for policy optimization. Classical theory favors critic-based methods such as PPO for variance reduction, yet critic-free alternatives like GRPO have gained widespread adoption due to their simplicity and competitive performance. We show that in sparse-reward settings, a learned critic can inject estimation noise that exceeds the state signal it captures, increasing rather than reducing advantage variance. By casting baseline selection as a Kalman filtering problem, we unify PPO and GRPO as two extremes of the Kalman gain and prove that explained variance (EV), computable from a single training batch, identifies the exact boundary: positive EV indicates the critic reduces variance, while zero or negative EV signals that it inflates variance. Building on this insight, we propose Explained Variance Policy Optimization (EVPO), which monitors batch-level EV at each training step and adaptively switches between critic-based and batch-mean advantage estimation, provably achieving no greater variance than the better of the two at every step. Across four tasks spanning classical control, agentic interaction, and mathematical reasoning, EVPO consistently outperforms both PPO and GRPO regardless of which fixed baseline is stronger on a given task. Further analysis confirms that the adaptive gating tracks critic maturation over training and that the theoretically derived zero threshold is empirically optimal.

cs.LG↗

arXiv2026

The Eleventh NTIRE 2026 Efficient Super-Resolution Challenge Report

This paper reviews the NTIRE 2026 challenge on efficient single-image super-resolution with a focus on the proposed solutions and results. The aim of this challenge is to devise a network that reduces one or several aspects, such as runtime, parameters, and FLOPs, while maintaining PSNR of around 26.90 dB on the DIV2K_LSDIR_valid dataset, and 26.99 dB on the DIV2K_LSDIR_test dataset. The challenge had 95 registered participants, and 15 teams made valid submissions. They gauge the state-of-the-art results for efficient single-image super-resolution.

cs.CV↗

arXiv2026

Generative Replica-Exchange: A Flow-based Framework for Accelerating Replica Exchange Simulations

Replica exchange (REX) is one of the most widely used enhanced sampling methodologies, yet its efficiency is limited by the requirement for a large number of intermediate temperature replicas. Here we present Generative Replica Exchange (GREX), which integrates deep generative models into the REX framework to eliminate this temperature ladder. Drawing inspiration from reservoir replica exchange (res-REX), GREX utilizes trained normalizing flows to generate high-temperature configurations on demand and map them directly to the target distribution using the potential energy as a constraint, without requiring target-temperature training data. This approach reduces production simulations to a single replica at the target temperature while maintaining thermodynamic rigor through Metropolis exchange acceptance. We validate GREX on three benchmark systems of increasing complexity, highlighting its superior efficiency and practical applicability for molecular simulations.

q-bio.BM↗