arXiv subjects

Huayang Wang

Publications and source records attributed to Huayang Wang.

4 recordsLinked to original sources

arXiv2026

Externalizing Research Synthesis and Validation in AI Scientists through a Research Harness

AI systems can increasingly automate scientific workflows, but the reasoning that links prior evidence, generated ideas, experiments and final claims often remains implicit inside model inference. Here we introduce Xcientist, a research harness that externalizes research synthesis and experimental validation into inspectable, contract-governed processes. Xcientist organizes literature evidence, idea states, implementation plans, ablation records and repair traces as persistent research artifacts, so that generated mechanisms can be grounded, executed, tested and revised without losing their evidential basis. We identify claim drift as a failure mode of automated research, where runnable artifacts no longer support the mechanism originally claimed. Across training-free memory systems, graph-structured traffic forecasting and multi-scale physics-informed neural networks, Xcientist preserves traceable trajectories from problem formulation to mechanism design, validation and bounded revision. These results suggest that AI scientists should be evaluated not only by their final artifacts, but by whether their synthesis and validation processes remain attributable, inspectable and scientifically accountable.

cs.AI↗

arXiv2026

ChemDFM-R: A Chemical Reasoning LLM Enhanced with Atomized Chemical Knowledge

Atomized chemical knowledge, such as functional group information of molecules and reactions, plays a pivotal intermediate role in the reasoning process that connects molecular structures with their properties and reactivities. While large language models (LLMs) have achieved impressive progress, the absence of atomized chemical knowledge results in their superficial understanding of chemistry and limited chemical reasoning capabilities. In this work, to tackle this problem, we develop a Chemical Reasoning LLM, ChemDFM-R. We first construct a comprehensive dataset of atomized chemical knowledge, ChemFG, annotating the presence of functional groups in molecules and the changes of functional groups during chemical reactions, to enhance the model's understanding of the fundamental principles and internal logic of chemistry. Then, we propose a mixed-source distillation method that initializes the model's reasoning capability with limited distilled data, and develop a four-stage training pipeline to equip the model with atomized chemical knowledge and chemical reasoning logic. Experiments on diverse chemical benchmarks demonstrate that ChemDFM-R achieves cutting-edge performance while providing interpretable, rationale-driven outputs, surpassing both the general-domain LLMs and domain-specific chemical LLMs. Moreover, ChemDFM-R achieves comparable or superior performance compared with cutting-edge commercial LLMs, such as o4-mini. Further case studies illustrate how explicit reasoning chains significantly improve the model's reliability, transparency, and practicality in real-world human-AI collaboration scenarios.

cs.CE↗

arXiv2026

DREAMuS: Dark matter REsearch with Advanced Muon Source

We propose DREAMuS, a fixed-target experiment at the High Intensity Heavy-Ion Accelerator Facility (HIAF), to search for muon-philic dark matter mediated by light flavor-violating bosons. DREAMuS is designed to probe the parameter space of a muon-philic dark matter (DM) mediated by a light flavor-violating boson, specifically a vector $Z'$ (or a scalar $ϕ$) which is produced in muon-nucleus interactions and decays into dark matter particles with a distinctive detector signature. Precision tracking and time-of-flight measurements are used to suppress the Standard Model backgrounds. We find that DREAMuS can achieve competitive sensitivity in the GeV-scale muon-philic dark matter parameter space, reaching sensitivity to couplings at the $10^{-4}$, especially in the few-hundred-MeV region.In addition to a $μ^-$ run, we highlight the potential of a complementary $μ^+$ beam option, further improving sensitivity to dark matter below 200 $\mathrm{MeV}$ by an order of magnitude.

hep-ph↗

arXiv2023

Nonrelativistic Limit of Normalized Solutions to a class of nonlinear Dirac equations

In this paper, we investigate the nonrelativistic limit of normalized solutions to a nonlinear Dirac equation as given below: \begin{equation*} \begin{cases} &-i c\sum\limits_{k=1}^3α_k\partial_k u +mc^2 β{u}- Γ* (K |{u}|^κ) K|{u}|^{κ-2}{u}- P |{u}|^{s-2}{u}=ω{u}, \\ &\displaystyle\int_{\mathbb{R}^3}\vert u \vert^2 dx =1. \end{cases} \end{equation*} Here, $c>0$ represents the speed of light, $m > 0$ is the mass of the Dirac particle, $ω\in\mathbb{R}$ emerges as an indeterminate Lagrange multiplier, $Γ$, $K$, $P$ are real-valued function defined on $\mathbb{R}^3$, also known as potential functions. Our research first confirms the presence of normalized solutions to the Dirac equation under high-speed light conditions. We then illustrate that these solutions progress to become the ground states of a system of nonlinear Schrödinger equations with a normalized constraint, exhibiting uniform boundedness and exponential decay irrespective of the light speed. Our results form the first discussion on nonrelativistic limit of normalized solutions to nonlinear Dirac equations. This not only aids in the study of normalized solutions of the nonlinear Schrödinger equations, but also physically explains that the normalized ground states of high-speed particles and low-speed motion particles are consistent.

math.AP↗