arXiv subjects

Hanchen Wang

Publications and source records attributed to Hanchen Wang.

At least 37 records · Page 2Linked to original sources

arXiv2026

Multi-Agent Coordination Adaptation via Structure-Guided Orchestration

As large language model (LLM)-based multi-agent systems scale to handle increasingly complex tasks, balancing structural stability and dynamic adaptability becomes increasingly challenging. Existing systems typically adopt either structure-centric methods, committing to structures determined upfront that limit fine-grained control, or orchestration-centric methods, adapting decisions dynamically while leaving coordination structure implicit and unstable. To address this challenge, we revisit multi-agent coordination from a probabilistic perspective, casting it as posterior inference over the joint distribution of structure and orchestration. We introduce MACA, an automated coordination framework that learns a task- and budget-conditioned structural prior over agent participation and interactions. This prior guides a policy-based orchestration as an approximation to posterior inference, enabling efficient solutions with fine-grained control. Across benchmarks, MACA outperforms adaptive multi-agent baselines by an average of 8.42% while using 43.19% fewer tokens. Further investigation reveals that joint adaptation of structure and orchestration suppresses redundant interactions, converging coordination toward task-effective execution.

cs.MA↗

arXiv2026

EXG: Self-Evolving Agents with Experience Graphs

Large language model (LLM)-based agents have demonstrated strong capabilities in complex reasoning and problem solving through multi-step interactions, yet most deployed agents remain behaviorally static, with knowledge acquired during execution rarely translating into systematic improvement over time. In response, a growing line of work on self-evolving agents explores how agents can improve through experience during deployment, but most existing approaches either rely on ad hoc reflection limited to single-task correction or adopt unstructured memory that accumulates fragmented experience with delayed usability. To address this limitation, we introduce EXG, an experience graph framework for self-evolving agents that explicitly organizes accumulated successes and failures into a structured, relational representation. EXG is the first experience graph designed for self-evolving agents, supporting both online, real-time graph growth during execution for immediate cross-task experience reuse, and offline reuse of a consolidated experience graph as an external memory module. This design also enables EXG to serve as a plug-and-play component for existing self-evolving agents, organizing prior experience into a unified experience graph and improving both solution quality and resource efficiency as deployment progresses. Extensive experiments across code generation and reasoning benchmarks show that EXG attains more favorable performance-efficiency trade-offs than reflection- and memory-based baselines in both online and offline evaluations. Our results suggest that structuring experience as a graph provides a principled foundation for scalable and transferable self-evolving agent behavior.

cs.AI↗

arXiv2026

GCCM: Enhancing Generative Graph Prediction via Contrastive Consistency Model

Conditional generative models, particularly diffusion-based methods, have recently been applied to graph prediction by modeling the target as a conditional distribution given the input graph, yielding competitive results compared to deterministic predictor. However, existing diffusion-based prediction methods typically require expensive iterative denoising at inference and often suffer from unstable sampling, which motivates recent efforts to reduce inference denoising steps and enable stable sampling via techniques such as consistency training. Despite this progress, we find that existing consistency training methods for graph prediction could potentially fall into a shortcut solution: the model may attempt to satisfy the self-consistency constraint by ignoring the noisy target (i.e., assigning it negligible weight), ultimately collapsing into a purely deterministic predictor. To mitigate such shortcut solution, we propose GCCM, a graph contrastive consistency model that goes beyond isolated pairwise matching between the same target at different noise levels by introducing negative pairs into a contrastive consistency objective. This adds an additional separation requirement, making the shortcut solution no longer trivially sufficient to satisfy the proposed objective. Moreover, we apply feature perturbation to the input node/edge features to break identical conditioning on the input graph, so that the shortcut no longer yields the same predictions across noise levels and becomes less attractive. Extensive experiments on benchmark datasets demonstrate that GCCM mitigates the shortcut solution and yields consistent performance improvements in graph prediction compared to deterministic predictors.

cs.AI↗

arXiv2026

Coherent Microwave Driving of Domain Wall Depinning in a Ferrimagnetic Garnet

Coherent control of domain wall dynamics offers a route to fast manipulation of magnetic textures beyond thermally activated motion. We demonstrate resonant excitation of linear and nonlinear dynamics of a pinned domain wall in a ferrimagnetic garnet thin film driven by a microwave field. Using scanning nitrogen-vacancy magnetometry and nonlocal spin-pumping measurements, we identify a low-frequency mode inside the magnon gap, originating from the localized oscillatory motion of a domain wall across a pinning line defined by a Pt stripline. Upon increasing the microwave drive into the nonlinear regime, this mode enables domain wall depinning at reduced external magnetic fields. Micromagnetic simulations reveal a progression from localized oscillations to partial relocation between pinning sites and, ultimately, complete escape from the pinning region with increasing driving power. These results establish resonant excitation of domain walls at engineered pinning sites as a mechanism for manipulating magnetic textures via localized nonlinear dynamics.

cond-mat.mes-hall↗

arXiv2026

Advancing AI Research Assistants with Expert-Involved Learning

Large language models (LLMs) and large multimodal models (LMMs) promise to accelerate biomedical discovery, yet their reliability remains unclear. We introduce ARIEL (AI Research Assistant for Expert-in-the-Loop Learning), an open-source evaluation and optimization framework that pairs a curated multimodal biomedical corpus with expert-vetted tasks to probe two capabilities: full-length article summarization and fine-grained figure interpretation. Using uniform protocols and blinded PhD-level evaluation, we find that state-of-the-art models generate fluent but incomplete summaries, whereas LMMs struggle with detailed visual reasoning. We later observe that prompt engineering and lightweight fine-tuning substantially improve textual coverage, and a compute-scaled inference strategy enhances visual question answering. We build an ARIEL agent that integrates textual and visual cues, and we show it can propose testable mechanistic hypotheses. ARIEL delineates current strengths and limitations of foundation models, and provides a reproducible platform for advancing trustworthy AI in biomedicine.

cs.AI↗

arXiv2026

RLMiner: Finding the Most Frequent k-sized Subgraph via Reinforcement Learning

Identifying the most frequent induced subgraph of size $k$ in a target graph is a fundamental graph mining problem with direct implications for Web-related data mining and social network analysis. Despite its importance, finding the most frequent induced subgraph remains computationally expensive due to the NP-hard nature of the subgraph counting task. Traditional exact enumeration algorithms often suffer from high time complexity, especially for a large graph size $k$. To mitigate this, existing approaches often utilize frequency measurement with the Downward Closure Property to reduce the search space, imposing additional constraints on the task. In this paper, we first formulate this task as a Markov Decision Process and approach it using a multi-task reinforcement learning framework. Specifically, we introduce RLMiner, a novel framework that integrates reinforcement learning with our proposed task-state-aware Graph Neural Network to find the most frequent induced subgraph of size $k$ with a time complexity linear to $k$. Extensive experiments on real-world datasets demonstrate that our proposed RLMiner effectively identifies subgraphs with frequencies closely matching the ground-truth most frequent induced subgraphs, while achieving significantly shorter and more stable running times compared to traditional methods.

cs.DB↗

arXiv2026

TwinWeaver: An LLM-Based Foundation Model Framework for Pan-Cancer Digital Twins

Precision oncology requires forecasting clinical events and trajectories, yet modeling sparse, multi-modal clinical time series remains a critical challenge. We introduce TwinWeaver, an open-source framework that serializes longitudinal patient histories into text, enabling unified event prediction as well as forecasting with large language models, and use it to build Genie Digital Twin (GDT) on 93,054 patients across 20 cancer types. In benchmarks, GDT significantly reduces forecasting error, achieving a median Mean Absolute Scaled Error (MASE) of 0.87 compared to 0.97 for the strongest time-series baseline (p<0.001). Furthermore, GDT improves risk stratification, achieving an average concordance index (C-index) of 0.703 across survival, progression, and therapy switching tasks, surpassing the best baseline of 0.662. GDT also generalizes to out-of-distribution clinical trials, matching trained baselines at zero-shot and surpassing them with fine-tuning, achieving a median MASE of 0.75-0.88 and outperforming the strongest baseline in event prediction with an average C-index of 0.672 versus 0.648. Finally, TwinWeaver enables an interpretable clinical reasoning extension, providing a scalable and transparent foundation for longitudinal clinical modeling.

cs.LG↗

arXiv2026

OpenPros: A Large-Scale Dataset for Limited View Prostate Ultrasound Computed Tomography

Prostate cancer is one of the most prevalent and deadly cancers among men, motivating the development of accurate and accessible imaging technologies for early detection. Ultrasound computed tomography (USCT) reconstructs quantitative tissue parameters such as speed-of-sound (SOS) and is a promising low-cost alternative to existing modalities. However, prostate USCT remains challenging due to limited-angle acquisition, strong tissue heterogeneity, bone-induced wave distortion, and the lack of large-scale, anatomically realistic datasets for method development and evaluation. We introduce OPENPROS, the first large-scale benchmark dataset for limited-angle prostate USCT, designed to systematically evaluate machine learning methods for quantitative inverse problems. OPENPROS contains over 280,000 paired samples of realistic 2D SOS maps and corresponding ultrasound full-waveform data, generated from anatomically accurate 3D digital prostate models derived from 4 clinical MRI/CT scans and 62 ex vivo prostate specimens with experimental ultrasound measurements. Wave propagation is simulated under clinically realistic configurations using open-source finite-difference time-domain and Runge-Kutta solvers. We provide standardized training, in-distribution, and out-of-distribution benchmarks and evaluate representative deep learning baselines. While learning-based methods substantially improve inference speed and reconstruction accuracy over physics-based approaches, results highlight persistent challenges in robustness, generalization, and high-resolution reconstruction quality. By publicly releasing OPENPROS, we establish a rigorous benchmark to support research in inverse problems, physics-guided learning, and operator learning, and to bridge the gap between machine learning research and practical USCT deployment. The dataset is available at https://open-pros.github.io/.

physics.med-ph↗

arXiv2026

Small Shifts, Large Gains: Unlocking Traditional TSP Heuristic Guided-Sampling via Unsupervised Neural Instance Modification

The Traveling Salesman Problem (TSP) is one of the most representative NP-hard problems in route planning and a long-standing benchmark in combinatorial optimization. Traditional heuristic tour constructors, such as Farthest or Nearest Insertion, are computationally efficient and highly practical, but their deterministic behavior limits exploration and often leads to local optima. In contrast, neural-based heuristic tour constructors alleviate this issue through guided-sampling and typically achieve superior solution quality, but at the cost of extensive training and reliance on ground-truth supervision, hindering their practical use. To bridge this gap, we propose TSP-MDF, a novel instance modification framework that equips traditional deterministic heuristic tour constructors with guided-sampling capability. Specifically, TSP-MDF introduces a neural-based instance modifier that strategically shifts node coordinates to sample multiple modified instances, on which the base traditional heuristic tour constructor constructs tours that are mapped back to the original instance, allowing traditional tour constructors to explore higher-quality tours and escape local optima. At the same time, benefiting from our instance modification formulation, the neural-based instance modifier can be trained efficiently without any ground-truth supervision, ensuring the framework maintains practicality. Extensive experiments on large-scale TSP benchmarks and real-world benchmarks demonstrate that TSP-MDF significantly improves the performance of traditional heuristics tour constructors, achieving solution quality comparable to neural-based heuristic tour constructors, but with an extremely short training time.

cs.AI↗

arXiv2026

Loop-gap resonators achieving strong magnon-photon coupling in magnetic insulator thin films

Magnon-photon hybrid systems consisting of a three-dimensional electromagnetic resonator and a bulk magnetic insulator constitute the standard experimental platform in cavity magnonics. Here, we demonstrate a modular loop-gap resonator design optimized to couple with thin films of magnetic insulators. We achieve the strong-coupling regime using this loop-gap resonator coupled to a 75~nm-thick epitaxial film of yttrium iron garnet at room temperature. We further show how to perform field-differential spectroscopy of the hybrid magnon-photon system, which eliminates the unwanted signal from other loop-gap modes uncoupled to the magnetic film. In addition to the uniform ferromagnetic resonance mode, the loop-gap resonator enables an hybridization with the standing spin-wave modes forming across the thickness of the film. Our approach unlocks the use of epitaxial films and multilayers of magnetic insulators to tune the magnon band structure in cavity magnonics experiments.

cond-mat.mes-hall↗

arXiv2026

Dynamical Stabilization of Inverted Magnetization and Antimagnons by Spin Injection in an Extended Magnetic System

Dynamical perturbations can modify the energy landscape of a physical system, such that unstable equilibrium configurations become stable when subject to an external drive. The magnetic analog of such dynamical stabilization corresponds to saturation of the magnetization against an external field. Here we report dynamical stabilization of the magnetization in thin film bismuth-substituted yttrium iron garnet by spin current injection from an adjacent Pt layer. Magneto-optical Kerr effect measurements demonstrate magnetization reversal against magnetic fields up to 3000 times larger than the film's coercivity once the spin injection surpasses a critical threshold associated with negative damping. Micromagnetic simulations reveal that this process is mediated by the excitation of a large population of incoherent magnons with non-zero wave vector, leading to a transient shortening and subsequent stabilization of the inverted magnetization. The elementary excitations of the high-energy inverted magnetization state are shown to be antimagnons, quasi-particles carrying opposite energy and spin relative to magnons. Our results further reveal how the system's size and minimization of nonlinear magnon scattering processes play a key role in dynamical stabilization, opening new avenues for magnetic state control beyond conventional magnetization switching. Dissipation-driven phase transitions in large-area magnetic systems provide a solid-state platform to study magnonic analogs of relativistic phenomena, such as Klein tunneling and black holes, as well as spin-wave amplification and lasing.

cond-mat.mes-hall↗

arXiv2026

Ultrathin bismuth-yttrium iron garnet films with tunable magnetic anisotropy

We report on the epitaxial growth of nm-thick films of bismuth-substituted yttrium iron garnet (BiYIG) by high-temperature off-axis radio-frequency magnetron sputtering. We demonstrate accurate control of the magnetic properties by tuning of the sputtering parameters and epitaxial strain on various (111)-oriented garnet substrates. BiYIG films with up to -0.80\% lattice mismatch with the substrate remain fully strained up to 60~nm-thick, maintaining a high crystalline quality. Transmission electron microscopy and energy-dispersive X-ray spectroscopy confirm coherent epitaxial growth, the absence of defects, and limited interdiffusion at the BiYIG/substrate interface. Varying the tensile or compressive strain between -0.80\% and +0.56\% in BiYIG allows for accurate compensation of the total magnetic anisotropy through magneto-elastic coupling. The effective magnetic anisotropy of sputtered BiYIG films can be further tuned via the off-axis deposition angle and the oxygen flow during growth, which determine the cation stoichiometry. Under optimized growth conditions, a ferromagnetic resonance (FMR) linewidth of 1~mT at 10~GHz is reliably obtained even for thicknesses as low as 10~nm. We also report small FMR linewidths in ultrathin (2-5~nm) BiYIG films grown on diamagnetic substrate yttrium scandium gallium garnet. These findings highlight the promise of low-damping, strain-engineered nm-thick BiYIG films for implementing advanced functionalities in spin-orbitronic and magnonic devices. Specifically, the magnetic-anisotropy compensation and low damping enable large cone-angle magnetization dynamics immune to magnon-magnon nonlinear scattering.

cond-mat.mtrl-sci↗

arXiv2026

Muse: Towards Reproducible Long-Form Song Generation with Fine-Grained Style Control

Recent commercial systems such as Suno demonstrate strong capabilities in long-form song generation, while academic research remains largely non-reproducible due to the lack of publicly available training data, hindering fair comparison and progress. To this end, we release a fully open-source system for long-form song generation with fine-grained style conditioning, including a licensed synthetic dataset, training and evaluation pipelines, and Muse, an easy-to-deploy song generation model. The dataset consists of 116k fully licensed synthetic songs with automatically generated lyrics and style descriptions paired with audio synthesized by SunoV5. We train Muse via single-stage supervised finetuning of a Qwen-based language model extended with discrete audio tokens using MuCodec, without task-specific losses, auxiliary objectives, or additional architectural components. Our evaluations find that although Muse is trained with a modest data scale and model size, it achieves competitive performance on phoneme error rate, text--music style similarity, and audio aesthetic quality, while enabling controllable segment-level generation across different musical structures. All data, model weights, and training and evaluation pipelines will be publicly released, paving the way for continued progress in controllable long-form song generation research. The project repository is available at https://github.com/yuhui1038/Muse.

cs.SD↗

arXiv2026

WaveDiffusion: Joint Latent Diffusion for Physically Consistent Seismic and Velocity Generation

Full Waveform Inversion (FWI) is a critical technique in subsurface imaging, aiming to reconstruct high-resolution subsurface properties from surface measurements. Acoustic FWI involves two physical modalities, seismic waveforms and velocity maps, which are governed by the acoustic wave equation. Prior works primarily focus on the inverse problem, modeling the relationship between seismic and velocity as an image-to-image translation task. In this work, we study their relationship from a generative perspective. Our aim is to explore and characterize the latent space structure, and identify latent vectors that generate seismic-velocity pairs consistent with the governing partial differential equation (PDE). Specifically, we model seismic and velocity data jointly from a shared latent space via a diffusion process. In experiments, we find that diffusion progressively refines arbitrary latent vectors into ones that yield approximately physics-consistent seismic-velocity pairs, even without explicit physics constraints. This provides empirical evidence of PDE-consistency in latent diffusion, where sampling is biased toward PDE-valid solutions. In latent space, satisfying the acoustic wave equation can be approximated through sampling and gradient descent. We formalize this physics-consistent latent modeling task and quantify it through extensive experiments. On large-scale OpenFWI benchmarks, our approach produces high-fidelity, diverse, and physically consistent seismic-velocity pairs, demonstrating the potential of a data-driven latent diffusion for physically consistent generation in a complex scientific domain.

physics.geo-ph↗

arXiv2025

UniCom: Towards a Unified and Cohesiveness-aware Framework for Community Search and Detection

Searching and detecting communities in real-world graphs underpins a wide range of applications. Despite the success achieved, current learning-based solutions regard community search, i.e., locating the best community for a given query, and community detection, i.e., partitioning the whole graph, as separate problems, necessitating task- and dataset-specific retraining. Such a strategy limits the applicability and generalization ability of the existing models. Additionally, these methods rely heavily on information from the target dataset, leading to suboptimal performance when supervision is limited or unavailable. To mitigate this limitation, we propose UniCom, a unified framework to solve both community search and detection tasks through knowledge transfer across multiple domains, thus alleviating the limitations of single-dataset learning. UniCom centers on a Domain-aware Specialization (DAS) procedure that adapts on the fly to unseen graphs or tasks, eliminating costly retraining while maintaining framework compactness with a lightweight prompt-based paradigm. This is empowered by a Universal Graph Learning (UGL) backbone, which distills transferable semantic and topological knowledge from multiple source domains via comprehensive pre-training. Both DAS and UGL are informed by local neighborhood signals and cohesive subgraph structures, providing consistent guidance throughout the framework. Extensive experiments on both tasks across 16 benchmark datasets and 22 baselines have been conducted to ensure a comprehensive and fair evaluation. UniCom consistently outperforms all state-of-the-art baselines across all tasks under settings with scarce or no supervision, while maintaining runtime efficiency.

cs.SI↗

arXiv2025

Large Language Models Meet Text-Attributed Graphs: A Survey of Integration Frameworks and Applications

Large Language Models (LLMs) have achieved remarkable success in natural language processing through strong semantic understanding and generation. However, their black-box nature limits structured and multi-hop reasoning. In contrast, Text-Attributed Graphs (TAGs) provide explicit relational structures enriched with textual context, yet often lack semantic depth. Recent research shows that combining LLMs and TAGs yields complementary benefits: enhancing TAG representation learning and improving the reasoning and interpretability of LLMs. This survey provides the first systematic review of LLM--TAG integration from an orchestration perspective. We introduce a novel taxonomy covering two fundamental directions: LLM for TAG, where LLMs enrich graph-based tasks, and TAG for LLM, where structured graphs improve LLM reasoning. We categorize orchestration strategies into sequential, parallel, and multi-module frameworks, and discuss advances in TAG-specific pretraining, prompting, and parameter-efficient fine-tuning. Beyond methodology, we summarize empirical insights, curate available datasets, and highlight diverse applications across recommendation systems, biomedical analysis, and knowledge-intensive question answering. Finally, we outline open challenges and promising research directions, aiming to guide future work at the intersection of language and graph learning.

cs.CL↗

arXiv2025

Evanescent Orbital Pumping by Magnetization Dynamics Free of Spin-Orbit Coupling

Converting magnetization spin to orbital current often relies on strong spin-orbit interaction that may cause additional angular momentum dissipation. We report that coherent magnetization dynamics in magnetic nanostructures can evanescently pump an orbital current into adjacent semiconductors due to the coupling between its stray electromagnetic field and electron orbitals without relying on spin-orbit coupling. The underlying photonic spin of the electromagnetic field governs the orbital polarization that flows along the gradient of the driven field. Due to the joint effect of the electric and magnetic fields, the orbital Hall current that flows perpendicularly to the gradient of the time-varying field is also generated and does not suffer from the orbital torque. These findings extend the paradigm of orbital pumping to include photonic angular momentum and pave the way for developing low-dissipation orbitronic devices.

cond-mat.mes-hall↗

arXiv2025

Towards Unsupervised Training of Matching-based Graph Edit Distance Solver via Preference-aware GAN

Graph Edit Distance (GED) is a fundamental graph similarity metric widely used in various applications. However, computing GED is an NP-hard problem. Recent state-of-the-art hybrid GED solver has shown promising performance by formulating GED as a bipartite graph matching problem, then leveraging a generative diffusion model to predict node matching between two graphs, from which both the GED and its corresponding edit path can be extracted using a traditional algorithm. However, such methods typically rely heavily on ground-truth supervision, where the ground-truth node matchings are often costly to obtain in real-world scenarios. In this paper, we propose GEDRanker, a novel unsupervised GAN-based framework for GED computation. Specifically, GEDRanker consists of a matching-based GED solver and introduces an interpretable preference-aware discriminator. By leveraging preference signals over different node matchings derived from edit path lengths, the discriminator can guide the matching-based solver toward generating high-quality node matching without the need for ground-truth supervision. Extensive experiments on benchmark datasets demonstrate that our GEDRanker enables the matching-based GED solver to achieve near-optimal solution quality without any ground-truth supervision.

cs.LG↗