arXiv subjects

Wenting Yang

Publications and source records attributed to Wenting Yang.

6 recordsLinked to original sources

arXiv2026

Harbor Adapters and Harbor-Index: Infrastructure and a Curated Meta-Dataset for Large-Scale Agentic Evaluation

Evaluating agents on the growing number of agentic benchmarks is challenging because they often require complex environments and agent integrations. We introduce Harbor Adapters, a unified evaluation infrastructure for agentic benchmarks. Our work makes three contributions. First, we develop benchmark adapters that port more than 80 benchmarks to evaluate arbitrary agents, and validate them through rigorous code review and parity experiments. Second, we conduct a large-scale evaluation of 8 models spanning capability tiers across 54 benchmarks; every model is run with Terminus-2 and with one of 3 native harnesses. This enables a broader analysis of agent capabilities and failure modes than was previously possible. Third, we introduce Harbor-Index, a curated set of 82 difficult, diverse, and high-quality tasks spanning 29 benchmarks, refined from the adapted suite through difficulty filtering, AI and human audit, and an audit-and-fix loop. Harbor-Index preserves the challenge and breadth of large-scale agentic evaluations while being affordable to run; no evaluated model-harness configuration exceeds 30% pass rate, and the strongest (GPT-5.5 with Codex) reaches 28.0%. We release the adapters, evaluation results, in-depth analysis, and Harbor-Index as open-source artifacts to support more reliable and comprehensive evaluation of language-model agents.

cs.AI↗

arXiv2026

CommBench: Can LLMs Write Correct and Efficient GPU Communication Code?

Training and serving large language models (LLMs) rely heavily on high-performance GPU communication, yet implementing efficient GPU communication primitives requires deep expertise in GPU architectures, networking hardware, and distributed communication patterns, making them particularly challenging for code generation models. We present CommBench, a comprehensive benchmark for GPU communication programming, consisting of over 100 expert-curated tasks spanning point-to-point communication, collective operations, expert-parallel communication, compute--communication fusion, and communication utility functions, with reference implementations either written by GPU communication experts or distilled from production codebases. We further introduce a cheat-resistant evaluation framework that automatically compiles, executes, and validates generated code on multi-GPU systems, and a unified metric that jointly measures functional correctness and communication performance. Evaluating leading frontier and open-source code generation models on both intra-node NVLink and inter-node RDMA platforms reveals that even the strongest model, GPT-5.5, correctly implements and achieves competitive performance on only 30.7\% of the benchmark tasks. Our results expose a substantial gap between current LLMs and expert-written GPU communication code, establishing CommBench as a challenging benchmark for advancing AI-assisted systems programming.

cs.DC↗

arXiv2026

PolycubeNet: A Dual-latent Diffusion Model for Polycube-Based Hexahedral Mesh Generation

Hexahedral meshes are widely used in simulation pipelines, yet automatic generation remains challenging for complex CAD geometries. Polycube-based hexahedral meshing is a representative approach due to its regular, parameterization-friendly structure, but existing polycube construction methods often rely on intricate surface segmentation and local heuristics, which can produce artifacts or fail on difficult shapes. In this paper, we propose an end-to-end framework for polycube generation based on conditional diffusion models. Given an input geometry represented as a point cloud, our method directly produces a corresponding polycube point cloud, eliminating the need for explicit surface segmentation or predefined polycube templates. At the core of our approach is a dual-latent conditional diffusion architecture that confines computationally expensive self-attention operations to a fixed-capacity, low-dimensional latent space. This design effectively decouples computational complexity from the resolution of both the input geometry and the output polycube, thereby avoiding the quadratic cost typical of point cloud self-attention mechanisms while supporting flexible input and output resolutions. To obtain a hexahedral mesh, the generated polycube is aligned to the input shape via rigid and non-rigid point cloud registration to establish surface correspondence, followed by a polycube-to-hex pipeline. We additionally create and release a paired dataset of CAD meshes and their corresponding polycube meshes, together with the core implementation of our model. Experiments show that PolycubeNet generalizes to complex CAD models with arbitrary genus and produces high-quality polycube structures within seconds, improving robustness and efficiency over prior learning-based approaches.

cs.GR↗

arXiv2026

An AI-Driven Framework for Energy-Efficient Environmental Monitoring in Smart Cities Using Edge Intelligence

Environmental monitoring is a crucial component of the smart city infrastructure. It enables informed decision making which enhances sustainability, public health and urban planning. However, the large-scale deployments of the smart sensors have raised concerns on excessive energy consumption and redundant data collection as well as limited sensor lifespan. To resolve these issues, we present an AI-driven framework for energy-efficient environmental monitoring in smart cities utilizing edge intelligence. Our proposed framework leverages TinyML-enabled edge devices and context-aware adaptive decision-making in order to dynamically activate the sensors based on the spatiotemporal conditions, environmental statistics and energy constraints. The sensors will be dynamically activated based on a utility function that takes in factors such as real-time environmental conditions, sensor location, and remaining battery lifespan. Our framework will reduce unnecessary sensing and communication while maintaining high coverage for monitoring. We introduce a hierarchical Edge Intelligence architecture to support deployments in city-wide scales. We conducted evaluation using a city-scale simulation driven by real multi-sensor environmental traces, which demonstrates that the proposed mechanism significantly reduces energy consumption and extends sensor lifespan when compared to static, periodic, and UCB-based adaptive sensing strategies. The results highlight the potential of edge intelligence and adaptive AI techniques for building sustainable and efficient smart city monitoring systems.

cs.DC↗

arXiv2026

SOK: A Taxonomy of Attack Vectors and Defense Strategies for Agentic Supply Chain Runtime

Agentic systems based on large language models (LLMs) operate not merely as text generators but as autonomous entities that dynamically retrieve information and invoke tools. This execution model shifts the attack surface from traditional build-time artifacts to inference-time dependencies, exposing agents to manipulation through untrusted data and probabilistic capability resolution. While prior work has examined model-level vulnerabilities, security risks arising from the complex, cyclic runtime behavior of agents remain fragmented. This paper systematizes existing research into a unified runtime framework. We categorize threats into data supply chain attacks (distinguishing between transient context injection and persistent memory poisoning) and tool supply chain attacks (spanning discovery, implementation, and invocation phases). Crucially, we identify the emergence of the Viral Agent Loop, where agents effectively become vectors for self-propagating generative worms that require no code vulnerabilities to spread. We argue for a transition to a Zero-Trust Runtime Architecture, where context is treated as untrusted control flow, and tool execution is bounded by cryptographic provenance rather than semantic likelihood.

cs.CR↗

arXiv2014

Active control of magnetoresistance of organic spin valves using ferroelectricity

Organic spintronic devices have been appealing because of the long spin life time of the charge carriers in the organic materials and their low cost, flexibility and chemical diversity. In previous studies, the control of resistance of organic spin valves is generally achieved by the alignment of the magnetization directions of the two ferromagnetic electrodes, generating magnetoresistance.1 Here we employ a new knob to tune the resistance of organic spin valves by adding a thin ferroelectric interfacial layer between the ferromagnetic electrode and the organic spacer. We show that the resistance can be controlled by not only the spin alignment of the two ferromagnetic electrodes, but also by the electric polarization of the interfacial ferroelectric layer: the MR of the spin valve depends strongly on the history of the bias voltage which is correlated with the polarization of the ferroelectric layer; the MR even changes sign when the electric polarization of the ferroelectric layer is reversed. This new tunability can be understood in terms of the change of relative energy level alignment between ferromagnetic electrode and the organic spacer caused by the electric dipole moment of the ferroelectric layer. These findings enable active control of resistance using both electric and magnetic fields, opening up possibility for multi-state organic spin valves and shed light on the mechanism of the spin transport in organic spin valves.

cond-mat.mtrl-sci↗