arXiv subjects

Zhiwei Ma

Publications and source records attributed to Zhiwei Ma.

7 recordsLinked to original sources

arXiv2026

$R^3$-Bench: LLMs Struggle with Resource-Rational Reasoning under Shared Budgets

In cognitive science, resource rationality asks how an agent should allocate limited computation to maximize expected value. Most reasoning and agent benchmarks use independent per-task budgets; existing shared-budget studies do not calibrate suite performance against the same model's demonstrated single-problem competence. We introduce $R^3$-Bench, which evaluates six-problem suites under shared budgets across mathematics, competitive programming, and abstract reasoning in tool-free and agentic settings. Matched single-problem response curves define an offline empirical oracle over observed successes. Across 72 main-table cells for six models, the oracle mean matches or exceeds the contest mean in all cells and is strictly higher in 71. Under moderate tool-free pressure, equal-allocation replay also exceeds contest performance for four of six models. Trajectory diagnostics reveal limited strategy updating and pressure-dependent failure patterns. In a three-model diagnostic under strong agentic pressure, at least one fixed scheduler exceeds the contest mean in six of nine cells, but no policy dominates across domains. These results expose a persistent gap between demonstrated competence and shared-budget realization.

cs.CL↗

arXiv2026

CP-Agent: A Calibrated Risk-Controlled Agent for Feedback-Driven Competitive Programming

Large language models still struggle with contest-level programming, while many agentic remedies rely on massive inference-time sampling or expensive multi-stage post-training. We study when execution feedback reliably helps an LLM CP solver and which mechanisms govern the gains. We model feedback-driven solving as a calibrated stopped process and identify three quantities: false-admission risk, program-level evidence against bad programs, and the active-state success hazard. Under held-out trace calibration and selection from a pre-declared finite controller manifest, the resulting structural certificate lower-bounds the clean success probability before false admission. We instantiate mechanisms targeting these quantities as Dual-Granularity Verification, Test Augmentation, and Experience-Driven Self-Evolving, yielding CP-Agent. Without updating any parameters, CP-Agent raises Pass@1 from 25.8\% to 48.5\% on LiveCodeBench Pro and improves Refine@5 by 11.0\% on ICPC-Eval. Across three LLM backbones, CP-Agent lies on the cost--accuracy efficiency frontier, and ablations show that each component primarily affects its corresponding certificate quantity.

cs.CL↗

arXiv2026

Development of a Reduced Multi-Fluid Equilibrium Model and Its Application to Proton-Boron Spherical Tokamaks

Proton-Boron fusion requires extreme ion temperatures and robust confinement, making Spherical Tokamaks (ST) with high-power neutral beam injection primary candidates. In these devices, strong toroidal rotation and the large mass disparity between protons and boron ions drive complex multi-fluid effects - specifically centrifugal species separation and electrostatic polarization - that standard single-fluid magnetohydrodynamic (MHD) models fail to capture. While comprehensive multi-fluid models are often numerically stiff, we develop a reduced model balancing physical fidelity with computational robustness. By retaining dominant toroidal rotation and self-consistent potential while neglecting poloidal inertia and pressure anisotropy, the model couples a generalized Grad-Shafranov equation with species-specific Bernoulli relations and a quasi-neutrality constraint. The model is applied to two representative p-B ST configurations: the experimental EHL-2 and reactor-scale EHL-3B. Simulation results demonstrate that equilibrium modifications are governed by the ion Mach number ($M$). In the low-rotation regime ($M < 0.5$), multi-fluid effects are weak and solutions approach the single-fluid limit. However, at $M > 2$, strong centrifugal forces drive significant boron accumulation at the low-field side (LFS) and generate an internal electrostatic potential on the order of 10 kV. These findings confirm the necessity of multi-fluid modeling for accurate p-$^{11}$B reactor design and establish a theoretical foundation for future investigations into stability, transport, and free-boundary dynamics.

physics.plasm-ph↗

arXiv2024

Information Extraction from Historical Well Records Using A Large Language Model

To reduce environmental risks and impacts from orphaned wells (abandoned oil and gas wells), it is essential to first locate and then plug these wells. Although some historical documents are available, they are often unstructured, not cleaned, and outdated. Additionally, they vary widely by state and type. Manual reading and digitizing this information from historical documents are not feasible, given the high number of wells. Here, we propose a new computational approach for rapidly and cost-effectively locating these wells. Specifically, we leverage the advanced capabilities of large language models (LLMs) to extract vital information including well location and depth from historical records of orphaned wells. In this paper, we present an information extraction workflow based on open-source Llama 2 models and test them on a dataset of 160 well documents. Our results show that the developed workflow achieves excellent accuracy in extracting location and depth from clean, PDF-based reports, with a 100% accuracy rate. However, it struggles with unstructured image-based well records, where accuracy drops to 70%. The workflow provides significant benefits over manual human digitization, including reduced labor and increased automation. In general, more detailed prompting leads to improved information extraction, and those LLMs with more parameters typically perform better. We provided a detailed discussion of the current challenges and the corresponding opportunities/approaches to address them. Additionally, a vast amount of geoscientific information is locked up in old documents, and this work demonstrates that recent breakthroughs in LLMs enable us to unlock this information more broadly.

cs.IR↗

arXiv2022

Technical and Economic Feasibility Analysis of Underground Hydrogen Storage: A Case Study in Intermountain-West Region USA

Hydrogen is an integral component of the current energy transition roadmap to decarbonize the economy and create an environmentally-sustainable future. However, surface storage options (e.g., tanks) do not provide the required capacity or durability to deploy a regional or nationwide hydrogen economy. In this study, we have analyzed the techno-economic feasibility of the geologic storage of hydrogen in depleted gas reservoirs, salt caverns, and aquifers in the Intermountain-West (I-WEST) region. We have identified the most favorable candidate sites for hydrogen storage and estimated the volumetric storage capacity. Our results show that the geologic storage of hydrogen can provide at least 72% of total energy consumption of I-WEST region in 2020. We also calculated the capital and levelized costs of each storage option. We found that a depleted gas reservoir is the most cost-effective candidate among the three geologic storage options. Interestingly, the cushion gas type and volume play a significant role in the storage cost when we consider hydrogen storage in saline aquifers. The levelized costs of hydrogen storage in depleted gas reservoirs, salt caverns, and saline aquifers with large-scale storage capacity are approximately $1.3, $2.3, and $3.4 per kg of H2, respectively. This work provides essential guidance for the geologic hydrogen storage in the I-WEST region.

physics.geo-ph↗

arXiv2021

An Underwater Image Semantic Segmentation Method Focusing on Boundaries and a Real Underwater Scene Semantic Segmentation Dataset

With the development of underwater object grabbing technology, underwater object recognition and segmentation of high accuracy has become a challenge. The existing underwater object detection technology can only give the general position of an object, unable to give more detailed information such as the outline of the object, which seriously affects the grabbing efficiency. To address this problem, we label and establish the first underwater semantic segmentation dataset of real scene(DUT-USEG:DUT Underwater Segmentation Dataset). The DUT- USEG dataset includes 6617 images, 1487 of which have semantic segmentation and instance segmentation annotations, and the remaining 5130 images have object detection box annotations. Based on this dataset, we propose a semi-supervised underwater semantic segmentation network focusing on the boundaries(US-Net: Underwater Segmentation Network). By designing a pseudo label generator and a boundary detection subnetwork, this network realizes the fine learning of boundaries between underwater objects and background, and improves the segmentation effect of boundary areas. Experiments show that the proposed method improves by 6.7% in three categories of holothurian, echinus, starfish in DUT-USEG dataset, and achieves state-of-the-art results. The DUT- USEG dataset will be released at https://github.com/baxiyi/DUT-USEG.

cs.CV↗

arXiv2017

Topological Distances between Networks and Its Application to Brain Imaging

This paper surveys various distance measures for networks and graphs that were introduced in persistent homology. The scope of the paper is limited to network distances that were actually used in brain networks but the methods can be easily adapted to any weighted graph in other fields. The network version of Gromov-Hausdorff, bottleneck, kernel distances are introduced. We also introduce a recently developed KS-test like distance based on monotonic topology features such as the zeroth Betti number. Numerous toy examples and the result of applying many different distances to the brain networks of different clinical status and populations are given.

q-bio.QM↗