arXiv subjects

Shusheng Li

Publications and source records attributed to Shusheng Li.

8 recordsLinked to original sources

arXiv2026

LongSearchEval: Evaluating Long-Horizon Web Search Capabilities of Large Language Models via a Trajectory-Aware Agent Framework with Failure-Node Localization

Long-horizon web search requires LLM-based agents to integrate information across web pages through extended interactions under task-specific constraints. Evaluating this capability is important not only for measuring final answer quality, but also for assessing whether an agent acquires, verifies, and uses evidence reliably over extended interactions. Existing evaluations, however, mainly rely on simulated trajectories or on post-hoc trajectories reconstructed from final answers, rather than on retained real interaction traces, which limits the fidelity of behavioral assessment and weakens support for fine-grained error localization. To address this gap, we introduce LONGSEARCHEVAL, a trajectory-aware agent evaluation framework that combines a unified agent execution protocol with source constrained outcome verification and retrospective failure-node localization. Stage 1 verifies answer groups against agent-cited webpages without human-authored gold answers; Stage 2 audits normalized rounds and links flagged failure nodes to incorrect answer groups. We evaluate 16 models from eight families on 100 tasks, yielding 1,600 retained runs and 6,545 automatically flagged failure nodes. Trajectory collection and evaluation required 1,037 and 318 hours of cumulative runtime, respectively. Human validation yields 94.50% agreement on supplied answer-group labels and 98.11% feature-correspondence precision for audited round-group links. Together, outcome scores and linked trajectory evidence support controlled model comparison and retrospective inspection of answer-related content.

cs.AI↗

arXiv2026

A linear dual-field finite element method for incompressible MHD, part I: cross-helicity and Alfvénic alignment in periodic domains

Cross helicity, together with total energy, determines the Elsässer energies and thus quantifies departures from Alfvénic alignment in incompressible MHD. Building on the dual-field method in [Mao and Xi, \emph{J. Comput. Phys.}, 2025], we construct a linear finite element method for periodic domains that reproduces the cross-helicity balance. We connect the discrete energy and cross-helicity conservation laws to Alfvénic alignment through a nonnegative Elsässer-energy representation, establishing preservation of the corresponding exact relation when either Elsässer energy is initially zero in the unforced ideal case. We reassign the two discrete approximations of the magnetic field to the integer and half-integer time levels and redesign the Lorentz and induction couplings within the Mao-Xi formulation. The resulting scheme uses linear staggered updates and retains the energy balances, strong and weak divergence-free properties, and magnetic- and fluid-helicity balances. Numerical experiments illustrate the role of the cross-helicity balance in preserving an aligned state in the ideal case and in alignment dynamics under weak dissipation.

math.NA↗

arXiv2026

AcupunctureBench: A Multimodal Benchmark for Evaluating Generative Models in the Acupuncture Domain

As large language models (LLMs) are increasingly applied in the field of traditional Chinese medicine (TCM), standardized benchmark evaluations for TCM have gradually emerged. Acupuncture is a crucial component of TCM. However, existing evaluation benchmarks are lacking in this domain. To address this gap, this paper proposes AcupunctureBench, the first independently constructed large-scale multimodal benchmark for the acupuncture domain, covering text, image, and video modalities. The AcupunctureBench spans multidimen sional knowledge in acupuncture, including acupuncture theory, meridians and acupoints, clinical reasoning, TCM syndromes, and practical acupoint operation. To achieve large-scale construction while ensuring medical professionalism, this work designs a human-machine collaborative data construction pipeline and proposes efficient deduplication strategies to reduce redundant samples, while extensively adopting data synthesis to mitigate data leak age risks. AcupunctureBench contains a total of 58,526 question samples and 1,216 video samples, covering multiple task types including objective questions, subjective question answering, case analysis, image understanding, image reasoning, and video understanding. Based on this benchmark, this paper evaluates 14 large language models, 14 large multimodal models, and 4 video foundation models, and further releases the first dedicated evaluation website for the acupuncture domain.

q-bio.QM↗

arXiv2025

Lightweight Remote Sensing Scene Classification on Edge Devices via Knowledge Distillation and Early-exit

As the development of lightweight deep learning algorithms, various deep neural network (DNN) models have been proposed for the remote sensing scene classification (RSSC) application. However, it is still challenging for these RSSC models to achieve optimal performance among model accuracy, inference latency, and energy consumption on resource-constrained edge devices. In this paper, we propose a lightweight RSSC framework, which includes a distilled global filter network (GFNet) model and an early-exit mechanism designed for edge devices to achieve state-of-the-art performance. Specifically, we first apply frequency domain distillation on the GFNet model to reduce model size. Then we design a dynamic early-exit model tailored for DNN models on edge devices to further improve model inference efficiency. We evaluate our E3C model on three edge devices across four datasets. Extensive experimental results show that it achieves an average of 1.3x speedup on model inference and over 40% improvement on energy efficiency, while maintaining high classification accuracy.

cs.CV↗

arXiv2024

A weak Galerkin finite element method for solving the asymptotic lower bound of Maxwell eigenvalue problem

In this paper, we propose a weak Galerkin (WG) finite element method for the Maxwell eigenvalue problem. By restricting subspaces, we transform the mixed form of Maxwell eigenvalue problem into simple elliptic equation. Then we give the WG numerical scheme for the Maxwell eigenvalue problem. Furthermore, we obtain the optimal error estimates of arbitrarily high convergence order and prove the lower bound property of numerical solutions for eigenvalues. Numerical experiments show the accuracy of theoretical analysis and the property of lower bound.

math.NA↗

arXiv2024

The weak Galerkin finite element method for the Steklov eigenvalue problem

This paper introduces the application of the weak Galerkin (WG) finite element method to solve the Steklov eigenvalue problem, focusing on obtaining lower bounds of the eigenvalues. The noncomforming finite element space of the weak Galerkin finite element method is the key to obtain lower bounds of the eigenvalues. The arbitary high order lower bound estimates are given and the guaranteed lower bounds of the eigenvalues are also discussed. Numerical results demonstrate the accuracy and lower bound property of the numerical scheme.

math.NA↗

arXiv2023

Bilateral Network with Residual U-blocks and Dual-Guided Attention for Real-time Semantic Segmentation

When some application scenarios need to use semantic segmentation technology, like automatic driving, the primary concern comes to real-time performance rather than extremely high segmentation accuracy. To achieve a good trade-off between speed and accuracy, two-branch architecture has been proposed in recent years. It treats spatial information and semantics information separately which allows the model to be composed of two networks both not heavy. However, the process of fusing features with two different scales becomes a performance bottleneck for many nowaday two-branch models. In this research, we design a new fusion mechanism for two-branch architecture which is guided by attention computation. To be precise, we use the Dual-Guided Attention (DGA) module we proposed to replace some multi-scale transformations with the calculation of attention which means we only use several attention layers of near linear complexity to achieve performance comparable to frequently-used multi-layer fusion. To ensure that our module can be effective, we use Residual U-blocks (RSU) to build one of the two branches in our networks which aims to obtain better multi-scale features. Extensive experiments on Cityscapes and CamVid dataset show the effectiveness of our method.

cs.CV↗

arXiv2017

Volume Calculation of CT lung Lesions based on Halton Low-discrepancy Sequences

Volume calculation from the Computed Tomography (CT) lung lesions data is a significant parameter for clinical diagnosis. The volume is widely used to assess the severity of the lung nodules and track its progression, however, the accuracy and efficiency of previous studies are not well achieved for clinical uses. It remains to be a challenging task due to its tight attachment to the lung wall, inhomogeneous background noises and large variations in sizes and shape. In this paper, we employ Halton low-discrepancy sequences to calculate the volume of the lung lesions. The proposed method directly compute the volume without the procedure of three-dimension (3D) model reconstruction and surface triangulation, which significantly improves the efficiency and reduces the complexity. The main steps of the proposed method are: (1) generate a certain number of random points in each slice using Halton low-discrepancy sequences and calculate the lesion area of each slice through the proportion; (2) obtain the volume by integrating the areas in the sagittal direction. In order to evaluate our proposed method, the experiments were conducted on the sufficient data sets with different size of lung lesions. With the uniform distribution of random points, our proposed method achieves more accurate results compared with other methods, which demonstrates the robustness and accuracy for the volume calculation of CT lung lesions. In addition, our proposed method is easy to follow and can be extensively applied to other applications, e.g., volume calculation of liver tumor, atrial wall aneurysm, etc.

cs.CV↗