arXiv subjects

Mingyi Wang

Publications and source records attributed to Mingyi Wang.

At least 19 recordsLinked to original sources

arXiv2026

Magnetic phases of Kondo lattice materials Ce$_5$RhGe$_2$ and Ce$_5$IrGe$_2$

Single crystals of Ce$_5$RhGe$_2$ and Ce$_5$IrGe$_2$ have been systematically investigated by electrical resistivity, specific heat, and magnetization measurements. Together with Ce$_5$CoGe$_2$, all three compounds crystallize in the orthorhombic \emph{Pnma} structure, with the lattice parameters increasing monotonically from Co to Rh to Ir, consistent with the effect of negative chemical pressure. Magnetization measurements along the three principal crystallographic axes identify the \emph{a} axis as the easy magnetization direction throughout the series. Ce$_5$RhGe$_2$ exhibits ferromagnetic ordering with a Curie temperature of approximately 11.5 K and shows magnetic behavior closely resembling that of Ce$_5$CoGe$_2$. In contrast, Ce$_5$IrGe$_2$ undergoes two successive magnetic transitions at $T_{\rm M1}=12.7$ K and $T_{\rm M2}=11.8$ K, and there are multiple metamagnetic transitions under magnetic fields, giving rise to magnetization plateaus at fractions of the saturation magnetization $M_{\rm s}$ of approximately $M_{\rm s}/5$ and $M_{\rm s}/3$. The low-field metamagnetic transition along the easy axis shifts to lower field with decreasing temperature, and eventually a pronounced hysteresis loop is observed about zero-field, establishing that Ce$_5$IrGe$_2$ exhibits a ferrimagnetic ground state at the lowest measured temperatures.

cond-mat.str-el↗

arXiv2026

A Weighted Integral-Regularized Finite Difference Scheme for the Tempered Fractional Laplacian

The intrinsic singularity of the tempered fractional Laplacian (TFL) remains a major challenge in developing numerical methods that are simultaneously accurate, efficient, and easy to implement. We develop a weighted integral-regularized finite difference (WIRFD) method that regularizes the singular integrand via a multidimensional Taylor expansion incorporating a smooth window function. The resulting integral is decomposed into a regularized term, which is discretized by a punctured trapezoidal rule, and a directly evaluated correction term. For the multidimensional TFL operator, we derive an $O(h^{4-\alpha})$ truncation error bound in the $l^{\infty}$-norm for $\alpha\in(0,2)$ and $u\in C^s(\mathbb{R}^d)$ with $s\geq 8$ by introducing a smooth auxiliary function together with the aliasing formula. For the one-dimensional TFL equation, we establish stability in both the $l^2$- and $l^{\infty}$-norms and optimal $O(h^{4-\alpha})$ convergence for $\alpha\in[1,2)$ based on the strict diagonal dominance of the discrete matrix and a lower bound for its minimum eigenvalue. The Toeplitz structure of the discrete matrix enables FFT-based matrix-vector multiplication, and the resulting linear systems are solved efficiently by a preconditioned conjugate gradient (PCG) method. Numerical experiments corroborate the theoretical results, demonstrating the accuracy, efficiency, and robustness of the proposed method.

math.NA↗

arXiv2026

Remember When It Matters: Proactive Memory Agent for Long-Horizon Agents

In long-horizon tasks, decision-relevant state is often scattered across an expanding trajectory, while the action agent must surface it and act. As trajectories grow, task requirements, environment facts, prior attempts, diagnoses, and open subgoals can be buried in the context window or pushed beyond it, failing to influence decisions when needed. We call this failure mode "behavioral state decay". We study memory as an active intervention mechanism rather than passive retrieval. A separate memory agent runs alongside an unmodified action agent, updating a structured memory bank from the recent trajectory and deciding whether to inject a memory-grounded reminder or remain silent. The module is plug-and-play with frontier action agents and existing agent harnesses. Across Terminal-Bench 2.0 and $\tau^2$-Bench, it improves pass@1 for both weaker and stronger action agents, with gains of +8.3 pp on Terminal-Bench and +6.8 pp on $\tau^2$-Bench. Ablations show that selective intervention outperforms passive bank exposure, always-on injection, advisor-only guidance, and general retrieval. As an early step toward open-weight memory policies, we train Qwen3.5-27B on SETA using SFT and GRPO, improving validation reward and achieving partial transfer to Terminal-Bench.

cs.AI↗

arXiv2026

Thinking More, Harnessing Better: State Machine Guided Harness Automatic Generation with Project Digestion and Workflow Decomposition

High-quality fuzz harnesses are essential for effective gray-box fuzzing. While Large Language Models (LLMs) offer promise for automating this task, existing one-turn generation methods suffer from hallucinations and inadequate coverage due to coarse-grained function targeting and misaligned generation workflows. We present SynapseFlow, an automatic harness generator that addresses these limitations through two key innovations: dataflow-aware function aggregation and a staged, rollback-enabled generation workflow decomposition. SynapseFlow first analyzes source code to construct Structural Flow Graphs and extract coherent Function Triplets. It then synthesizes harnesses via a decomposed four-stage process governed by a staged rollback algorithm to ensure correctness. We evaluated SynapseFlow on 25 real-world open-source software projects. The experimental results indicate that SynapseFlow outperforms state-of-the-art tools (OSS-Fuzz-Gen, CKGFuzzer, PromeFuzz), achieving 3.07$\times$, 1.71$\times$, and 4.26$\times$ higher branch coverage, and 1.77$\times$, 1.51$\times$, and 1.36$\times$ higher bug detection rates, respectively. Most importantly, SynapseFlow discovered 7 previously unreported bugs (5 assigned CVEs), demonstrating its practical effectiveness in real-world bug discovery.

cs.CR↗

arXiv2026

Rethinking AI-Generated Text Detection: A Strong Baseline and the Distribution-Shift Problem That Remains

Recent AI-generated text detection work often introduces a new benchmark together with a specialized detector tailored to it. We revisit this practice from a baseline-first perspective. Across several benchmarks, we show that a plain, fully fine-tuned RoBERTa matches or exceeds the specialized detectors those benchmarks are built around. This suggests that much of the recent architectural complexity is not what drives strong in-distribution detection. The remaining challenge is the distribution shift. The same strong baseline degrades sharply when the topic domain or generating model changes at test time, and simply adding more source data does not close the gap. We identify a key failure mode: under distribution shift, the detector can assign high-confidence machine labels to human-written text from unseen domains. We then study two lightweight domain adaptation methods to address this problem: $K$-shot adaptation with first-order MAML over LoRA adapters, and a per-sample confidence-weighted ensemble built on top of the adapted detector. Overall, our results suggest that progress in AI-generated text detection should be measured not only by in-distribution performance, but also by robustness under distribution shift.

cs.LG↗

arXiv2026

SAGE-OPD: Selective Agent-Guided Intervention for Multi-Turn On-Policy Distillation

On-policy distillation (OPD) improves student models by training them on trajectories induced by their own policy, making it a promising approach for mitigating exposure bias in agent training. However, most OPD studies focus on single-turn settings, while realistic LLM agents interact with environments over multiple turns. In this regime, early errors can alter future observations and compound across the trajectory, and standard dense token-level OPD becomes brittle, as it may over-penalize semantically valid alternatives, reinforce local degeneracies such as repeated actions, and propagate unreliable teacher supervision on off-distribution histories. We propose SAGE-OPD, a verifier-free selective intervention framework specifically designed for multi-turn OPD. Instead of applying teacher supervision uniformly across all turns, SAGE-OPD first observes environment feedback and uses teacher judgment to decide whether each student response should be skipped or intervened on. To further address compounding errors, SAGE-OPD weights token-level distillation by teacher confidence, reducing the influence of uncertain teacher distributions on corrupted or ambiguous histories. Finally, SAGE-OPD applies loss normalization to preserve the overall loss scale of standard OPD while retaining selective turn-level weighting. Experiments on agent tasks show that SAGE-OPD consistently improves over baselines, achieving up to a 13.3% relative improvement in ALFWorld unseen success rate over standard OPD. Ablation studies further demonstrate that turn-level intervention, teacher confidence weighting, and loss normalization provide complementary benefits. Our results suggest that effective multi-turn OPD should remain on-policy, but teacher supervision should be selectively allocated to turns where intervention is necessary and reliable.

cs.CL↗

arXiv2026

OmniOPD: Logit-Free On-Policy Distillation via Speculative Verification

On-Policy Distillation (OPD) trains a student model on its own generative trajectories under dense token-level feedback from a stronger teacher, mitigating both the off-policy distribution shift of Supervised Fine-Tuning (SFT) and the sparse credit assignment of Reinforcement Learning (RL). However, standard OPD faces two coupled limitations. First, it requires direct access to the teacher's token-level logits, excluding a broad class of capable proprietary models from serving as teachers. Second, the token-level logit signal itself is brittle, depending on a narrow overlap of plausible next tokens between teacher and student, and prone to amplifying degenerate patterns such as repetition loops. In this paper, we introduce OmniOPD, a novel framework that addresses both limitations through a logit-free, chunk-level supervision signal. OmniOPD replaces deterministic logit matching with Monte Carlo rollouts that approximate the teacher's local preferences through a continuous semantic similarity metric over multi-token chunks, and concentrates this supervision via a peak-entropy scheduler that audits the student only at its high-uncertainty reasoning forks. A Dirichlet-Multinomial Bayesian prior and a base-model KL anchor further bound the variance of discrete sampling and prevent policy collapse across unaudited tokens. Across competitive benchmarks, OmniOPD surpasses the standard OPD approach by up to +28.64% on math, confirming that chunk-level semantic verification extracts a more reliable learning signal than token-level logit matching, whose high information density is offset by significant noise and brittleness. Furthermore, when paired with stronger black-box teachers such as Claude-4.5-Haiku and Gemini-2.5-Flash, OmniOPD achieves an additional +9.54% relative on math over its open-weight teacher counterpart, advancing the student past the performance of self-exploratory RL.

cs.LG↗

arXiv2026

Detector-Evasive LLM Paraphrasing via Constrained Policy Optimization

AI-text detectors are vulnerable to paraphrasing and detector-guided paraphrasing attacks, but existing detector-evasion methods often lack precise control over semantic preservation. In particular, optimizing directly for detector evasion can degrade fine-grained semantics, whereas scalarized reward designs provide only indirect, weight-sensitive control over the evasion-semantics trade-off. We address this limitation by formulating detector-evasive LLM paraphrasing as a Constrained Markov Decision Process, where detector evasion is the primary objective and semantic preservation is enforced as an explicit constraint. We propose Detector Evasion Policy Optimization (DEPO), a Lagrangian primal-dual reinforcement learning algorithm with a novel GRPO-style group-based policy update. DEPO adaptively balances semantic preservation and detector evasion during training, enabling the policy to improve attack success within a prescribed semantic-preservation region. Experiments on MAGE, M4, RAID, and peer-review datasets, evaluated against MAGE, RoBERTa, RADAR, Binoculars, and Fast-DetectGPT detectors, show that DEPO achieves strong detector evasion while precisely satisfying the semantic preservation constraint. DEPO also exhibits cross-domain, cross-detector, and prompt-level robustness.

cs.LG↗

arXiv2026

LLM-Driven Reasoning for Constraint-Aware Feature Selection in Industrial Systems

Feature selection is a crucial step in large-scale industrial machine learning systems, directly affecting model accuracy, efficiency, and maintainability. Traditional feature selection methods rely on labeled data and statistical heuristics, making them difficult to apply in production environments where labeled data are limited and multiple operational constraints must be satisfied. To address this, we propose Model Feature Agent (MoFA), a model-driven framework that performs sequential, reasoning-based feature selection using both semantic and quantitative feature information. MoFA incorporates feature definitions, importance scores, correlations, and metadata (e.g., feature groups or types) into structured prompts and selects features through interpretable, constraint-aware reasoning. We evaluate MoFA in three real-world industrial applications: (1) True Interest and Time-Worthiness Prediction, where it improves accuracy while reducing feature group complexity, (2) Value Model Enhancement, where it discovers high-order interaction terms that yield substantial engagement gains in online experiments, and (3) Notification Behavior Prediction, where it selects compact, high-value feature subsets that improve both model accuracy and inference efficiency. Together, these results demonstrate the practicality and effectiveness of LLM-based reasoning for feature selection in real production systems.

cs.CL↗

arXiv2026

Non-collinear ferromagnetism in the Kondo lattice Ce$_5$CoGe$_2$

The dense Kondo lattice Ce$_5$CoGe$_2$ exhibits superconductivity once the magnetic ordering is suppressed by pressure. Here the ambient pressure magnetic state is investigated via magnetization, heat capacity, powder neutron diffraction, and muon spin relaxation ($\mu$SR) measurements. Neutron diffraction results reveal a noncollinear ferromagnetic structure, where the four inequivalent Ce sites exhibit different magnetic moments. Point-charge model calculations of the crystalline-electric field (CEF) ground states corroborate different moments between the sites, and suggest sizeable components of the moments along different directions, consistent with the non-collinear structure. Analysis of the Dzyaloshinskii-Moriya (DM) interaction for the bonds connecting Ce atoms demonstrates that most of these bonds exhibit a nonzero DM vector, suggesting that competition between intersite magnetic exchange interactions, CEF driven single-ion anisotropy, the Kondo effect and the DM interaction may drive the non-collinear ferromagnetism.

cond-mat.str-el↗

arXiv2026

Higher-Order Finite Difference Methods for the Tempered Fractional Laplacian

This paper presents a general framework of high-order finite difference (HFD) schemes for the tempered fractional Laplacian (TFL) based on new generating functions obtained from the discrete symbols. Specifically, for sufficiently smooth functions, the resulting discretizations achieve high-order convergence with orders $p=4, 6, 8$. The discrete operators lead to Toeplitz stiffness matrices, allowing efficient matrix-vector multiplications via fast algorithms. Building on these approximations, HFD methods are formulated for solving TFL equations, and their stability and convergence are rigorously analyzed. Numerical simulations confirm the effectiveness of the proposed methods, showing excellent agreement with the theoretical predictions.

math.NA↗

arXiv2025

Magnetic properties of $R$Rh$_6$Ge$_4$ ($R$ = Pr, Nd, Sm, Gd-Er) single crystals

Single crystals of $R$Rh$_6$Ge$_4$ ($R$ = Pr, Nd, Sm, Gd - Er) were synthesized using a Bi flux and their physical properties were characterized by magnetization, resistivity, and specific heat measurements. These compounds crystallize in the noncentrosymmetric LiCo$_6$P$_4$-type structure (space group $P\bar{6}m2$), where rare-earth atoms form a triangular lattice in the $ab$-plane and chains along the $c$-axis. PrRh$_6$Ge$_4$ and ErRh$_6$Ge$_4$ do not exhibit magnetic transitions above 0.4 K. NdRh$_6$Ge$_4$ and SmRh$_6$Ge$_4$ are ferromagnets, while GdRh$_6$Ge$_4$ and DyRh$_6$Ge$_4$ show antiferromagnetic transitions, \red{whereas HoRh$_6$Ge$_4$ is a ferrimagnet}. In addition, DyRh$_6$Ge$_4$ shows multiple transitions and magnetization plateaus when a magnetic field is applied along the $c$-axis. In SmRh$_6$Ge$_4$, like the Ce counterpart, the crystalline-electric field (CEF) effect leads to an easy plane anisotropy, while in other compounds it gives rise to a pronounced uniaxial anisotropy.

cond-mat.str-el↗

arXiv2025

Mixture-of-Minds: Multi-Agent Reinforcement Learning for Table Understanding

Understanding and reasoning over tables is a critical capability for many real-world applications. Large language models (LLMs) have shown promise on this task, but current approaches remain limited. Fine-tuning based methods strengthen language reasoning; yet they are prone to arithmetic errors and hallucination. In contrast, tool-based methods enable precise table manipulation but rely on rigid schemas and lack semantic understanding. These complementary drawbacks highlight the need for approaches that integrate robust reasoning with reliable table processing. In this work, we propose Mixture-of-Minds, a multi-agent framework that decomposes table reasoning into three specialized roles: planning, coding, and answering. This design enables each agent to focus on a specific aspect of the task while leveraging code execution for precise table manipulation. Building on this workflow, we introduce a self-improvement training framework that employs Monte Carlo Tree Search (MCTS) rollouts to generate pseudo-gold trajectories and optimize agents with reinforcement learning (RL). Extensive experiments show that Mixture-of-Minds delivers substantial gains, reaching 62.13% on TableBench and surpassing OpenAI-o4-mini-high. These results demonstrate the promise of combining structured multi-agent workflows with RL to advance table understanding.

cs.CL↗

arXiv2025

A note on spectral Monte-Carlo method for fractional Poisson equation on high-dimensional ball

Recently, a class of efficient spectral Monte-Carlo methods was developed in \cite{Feng2025ExponentiallyAS} for solving fractional Poisson equations. These methods fully consider the low regularity of the solution near boundaries and leverage the efficiency of walk-on-spheres algorithms, achieving spectral accuracy. However, the underlying formulation is essentially one-dimensional. In this work, we extend this approach to radial solutions in general high-dimensional balls. This is accomplished by employing a different set of eigenfunctions for the fractional Laplacian and deriving new interpolation formulas. We provide a comprehensive description of our methodology and a detailed comparison with existing techniques. Numerical experiments confirm the efficacy of the proposed extension.

math.NA↗

arXiv2025

Do LLM Modules Generalize? A Study on Motion Generation for Autonomous Driving

Recent breakthroughs in large language models (LLMs) have not only advanced natural language processing but also inspired their application in domains with structurally similar problems--most notably, autonomous driving motion generation. Both domains involve autoregressive sequence modeling, token-based representations, and context-aware decision making, making the transfer of LLM components a natural and increasingly common practice. However, despite promising early attempts, a systematic understanding of which LLM modules are truly transferable remains lacking. In this paper, we present a comprehensive evaluation of five key LLM modules--tokenizer design, positional embedding, pre-training paradigms, post-training strategies, and test-time computation--within the context of motion generation for autonomous driving. Through extensive experiments on the Waymo Sim Agents benchmark, we demonstrate that, when appropriately adapted, these modules can significantly improve performance for autonomous driving motion generation. In addition, we identify which techniques can be effectively transferred, analyze the potential reasons for the failure of others, and discuss the specific adaptations needed for autonomous driving scenarios. We evaluate our method on the Sim Agents task and achieve competitive results.

cs.AI↗

arXiv2024

A Joint Prediction Method of Multi-Agent to Reduce Collision Rate

Predicting future motions of road participants is an important task for driving autonomously. Most existing models excel at predicting the marginal trajectory of a single agent, but predicting joint trajectories for multiple agents that are consistent within a scene remains a challenge. Previous research has often focused on marginal predictions, but the importance of joint predictions has become increasingly apparent. Joint prediction aims to generate trajectories that are consistent across the entire scene. Our research builds upon the SIMPL baseline to explore methods for generating scene-consistent trajectories. We tested our algorithm on the Argoverse 2 dataset, and experimental results demonstrate that our approach can generate scene-consistent trajectories. Compared to the SIMPL baseline, our method significantly reduces the collision rate of joint trajectories within the scene.

cs.RO↗

arXiv2023

Tunable Circular Photogalvanic and Photovoltaic Effect in 2D Tellurium with Different Chirality

Chirality arises from the asymmetry of matters, where two counterparts are the mirror image of each other. The interaction between circular-polarization light and quantum materials is enhanced in chiral space groups due to the structural chirality. Tellurium (Te) possesses the simplest chiral crystal structure, with Te atoms covalently bonded into a spiral atomic chain (left- or right-handed) with a periodicity of three. Here, we investigate the tunable circular photo-electric responses in 2D Te field-effect transistor with different chirality, including the longitudinal circular photogalvanic effect induced by the radial spin texture (electron-spin polarization parallel to the electron momentum direction) and the circular photovoltaic induced by the chiral crystal structure (helical Te atomic chains). Our work demonstrates the controllable manipulation of the chirality degree of freedom in materials.

cond-mat.mes-hall↗

arXiv2023

Tunable Chirality-dependent Nonlinear Electrical Responses in 2D Tellurium

Tellurium (Te) is an elemental semiconductor with a simple chiral crystal structure. Te in a two-dimensional (2D) form synthesized by solution-based method shows excellent electrical, optical, and thermal properties. In this work, the chirality of hydrothermally grown 2D Te is identified and analyzed by hot sulfuric acid etching and high-angle tilted high-resolution scanning transmission electron microscopy. The gate-tunable nonlinear electrical responses, including the nonreciprocal electrical transport in the longitudinal direction and the nonlinear planar Hall effect in the transverse direction, are observed in 2D Te under a magnetic field. Moreover, the nonlinear electrical responses have opposite signs in left- and right-handed 2D Te due to the opposite spin polarizations ensured by the chiral symmetry. The fundamental relationship between the spin-orbit coupling and the crystal symmetry in two enantiomers provides a viable platform for realizing chirality-based electronic devices by introducing the chirality degree of freedom into electron transport.

cond-mat.mtrl-sci↗