arXiv subjects

Yu Zhang

Publications and source records attributed to Yu Zhang.

At least 325 records · Page 18Linked to original sources

arXiv2026

Adaptation of Agentic AI: A Survey of Post-Training, Memory, and Skills

Large language model (LLM) agents are moving beyond prompting alone. ChatGPT marked the rise of general-purpose LLM assistants, DeepSeek showed that on-policy reinforcement learning with verifiable rewards can improve reasoning and tool use, and OpenClaw highlights a newer direction in which agents accumulate persistent memory and reusable skills. Yet the research landscape remains fragmented across post-training, retrieval, memory, and skill systems. This survey studies these developments under a single notion of \emph{adaptation}: improving an agent, its tools, or their interaction after pretraining. We organize the field with a four-paradigm framework spanning agent adaptation and tool adaptation. On the agent side, A1 (tool-execution-signaled) and A2 (agent-output-signaled) improve the agent itself through supervised fine-tuning, preference optimization, and reinforcement learning with verifiable rewards. On the tool side, T1 (agent-agnostic) provides reusable pre-trained modules any agent can call, while T2 (agent-supervised) uses the agent's outputs to train memory systems, skill libraries, or lightweight subagents. Using this framework, we review post-training methods, adaptive memory architectures, and agent skills; compare their trade-offs in cost, flexibility, and generalization; and summarize evaluation practices across deep research, software development, computer use, and drug discovery. We conclude by outlining open problems in agent-tool co-adaptation, continual learning, safety, and efficient deployment.

cs.AI↗

arXiv2026

$L^3$:Scene-agnostic Visual Localization in the Wild

Standard visual localization methods typically require offline pre-processing of scenes to obtain 3D structural information for better performance. This inevitably introduces additional computational and time costs, as well as the overhead of storing scene representations. Can we visually localize in a wild scene without any off-line preprocessing step? In this paper, we leverage the online inference capabilities of feed-forward 3D reconstruction networks to propose a novel map-free visual localization framework $L^3$. Specifically, by performing direct online 3D reconstruction on RGB images, followed by two-stage metric scale recovery and pose refinement based on 2D-3D correspondences, $L^3$ achieves high accuracy without the need to pre-build or store any offline scene representations. Extensive experiments demonstrate $L^3$ not only that the performance is comparable to state-of-the-art solutions on various benchmarks, but also that it exhibits significantly superior robustness in sparse scenes (fewer reference images per scene).

cs.CV↗

arXiv2026

HMR-1: Hierarchical Massage Robot with Vision-Language-Model for Embodied Healthcare

The rapid advancement of Embodied Intelligence has opened transformative opportunities in healthcare, particularly in physical therapy and rehabilitation. However, critical challenges remain in developing robust embodied healthcare solutions, such as the lack of standardized evaluation benchmarks and the scarcity of open-source multimodal acupoint massage datasets. To address these gaps, we construct MedMassage-12K - a multimodal dataset containing 12,190 images with 174,177 QA pairs, covering diverse lighting conditions and backgrounds. Furthermore, we propose a hierarchical embodied massage framework, which includes a high-level acupoint grounding module and a low-level control module. The high-level acupoint grounding module uses multimodal large language models to understand human language and identify acupoint locations, while the low-level control module provides the planned trajectory. Based on this, we evaluate existing MLLMs and establish a benchmark for embodied massage tasks. Additionally, we fine-tune the Qwen-VL model, demonstrating the framework's effectiveness. Physical experiments further confirm the practical applicability of the framework.Our dataset and code are publicly available at https://github.com/Xiaofeng-Han-Res/HMR-1.

cs.RO↗

arXiv2026

Graph2Video: Leveraging Video Models to Model Dynamic Graph Evolution

Dynamic graphs are common in real-world systems such as social media, recommender systems, and traffic networks. Existing dynamic graph models for link prediction often fall short in capturing the complexity of temporal evolution. They tend to overlook fine-grained variations in temporal interaction order, struggle with dependencies that span long time horizons, and offer limited capability to model pair-specific relational dynamics. To address these challenges, we propose \textbf{Graph2Video}, a video-inspired framework that views the temporal neighborhood of a target link as a sequence of "graph frames". By stacking temporally ordered subgraph frames into a "graph video", Graph2Video leverages the inductive biases of video foundation models to capture both fine-grained local variations and long-range temporal dynamics. It generates a link-level embedding that serves as a lightweight and plug-and-play link-centric memory unit. This embedding integrates seamlessly into existing dynamic graph encoders, effectively addressing the limitations of prior approaches. Extensive experiments on benchmark datasets show that Graph2Video outperforms state-of-the-art baselines on the link prediction task in most cases. The results highlight the potential of borrowing spatio-temporal modeling techniques from computer vision as a promising and effective approach for advancing dynamic graph learning.

cs.CV↗

arXiv2026

Diffusion-Guided Pretraining for Brain Graph Foundation Models

With the growing interest in foundation models for brain signals, graph-based pretraining has emerged as a promising paradigm for learning transferable representations from connectome data. However, existing contrastive and masked autoencoder methods typically rely on naive random dropping or masking for augmentation, which is ill-suited for brain graphs and hypergraphs as it disrupts semantically meaningful connectivity patterns. Moreover, commonly used graph-level readout and reconstruction schemes fail to capture global structural information, limiting the robustness of learned representations. In this work, we propose a unified diffusion-based pretraining framework that addresses both limitations. First, diffusion is designed to guide structure-aware dropping and masking strategies, preserving brain graph semantics while maintaining effective pretraining diversity. Second, diffusion enables topology-aware graph-level readout and node-level global reconstruction by allowing graph embeddings and masked nodes to aggregate information from globally related regions. Extensive experiments across multiple neuroimaging datasets with over 25,000 subjects and 60,000 scans involving various mental disorders and brain atlases demonstrate consistent performance improvements.

cs.LG↗

arXiv2026

RM-R1: Reward Modeling as Reasoning

Reward modeling is essential for aligning large language models with human preferences through reinforcement learning. To provide accurate reward signals, a reward model (RM) should stimulate deep thinking and conduct interpretable reasoning before assigning a score or a judgment. Inspired by recent advances of long chain-of-thought on reasoning-intensive tasks, we hypothesize and validate that integrating reasoning into reward modeling significantly enhances RM's interpretability and performance. We introduce a new class of generative reward models, Reasoning Reward Models (ReasRMs), which formulate reward modeling as a reasoning task. We propose a reasoning-oriented training pipeline and train a family of ReasRMs, RM-R1. RM-R1 features a chain-of-rubrics (CoR) mechanism -- self-generating sample-level chat rubrics or math/code solutions, and evaluating candidate responses against them. The training of RM-R1 consists of two key stages: (1) distillation of high-quality reasoning chains and (2) reinforcement learning with verifiable rewards. Empirically, our models achieve superior performance across three reward model benchmarks on average, outperforming much larger open-weight models (e.g., INF-ORM-Llama3.1-70B) and proprietary ones (e.g., GPT-4o) by up to 4.9%. Beyond final performance, we perform thorough analyses to understand the key ingredients of successful ReasRM training.

cs.CL↗

arXiv2026

Assigning Multi-Robot Tasks to Multitasking Robots

One simplifying assumption in existing and well-performing task allocation methods is that the robots are single-tasking: each robot operates on a single task at any given time. While this assumption is harmless to make in some situations, it can be inefficient or even infeasible in others. In this paper, we consider assigning multi-robot tasks to multitasking robots. The key contribution is a novel task allocation framework that incorporates the consideration of physical constraints introduced by multitasking. This is in contrast to the existing work where such constraints are largely ignored. After formulating the problem, we propose a compilation to weighted MAX-SAT, which allows us to leverage existing solvers for a solution. A more efficient greedy heuristic is then introduced. For evaluation, we first compare our methods with a modern baseline that is efficient for single-tasking robots to validate the benefits of multitasking in synthetic domains. Then, using a site-clearing scenario in simulation, we further illustrate the complex task interaction considered by the multitasking robots in our approach to demonstrate its performance. Finally, we demonstrate a physical experiment to show how multitasking enabled by our approach can benefit task efficiency in a realistic setting.

cs.RO↗

arXiv2026

Entanglement measures and Bell-type spin-correlation observables in tau-lepton pairs at the Super Tau-Charm Facility

Within the framework of quantum field theory and the Standard Model (SM), we investigate the prospects of studying entanglement measures and Bell-type spin-correlation observables in the electroweak process $e^- e^+\to τ^-τ^+$ at the center-of-mass (COM) energies of $\sqrt{s}=3.670,4.630$, and $7.000$ GeV at the proposed Super Tau-Charm Facility (STCF) in China. Focusing on the hadronic decay channel $τ^\pm\to π^\pm ν$, we determine the spin-correlation coefficients of the $τ^-τ^+$ system within the SM framework using measurable production kinematics, namely the $τ$ velocities and scattering angles in the COM frame. From these correlation coefficients, we construct concurrence and a Bell-type correlation combination as defined in the literature. Assuming an integrated luminosity of 1 ab$^{-1}$ for each considered COM energy, and incorporating realistic detector efficiencies as well as statistical and systematic uncertainties, we estimate the expected sensitivity to these observables at STCF. Our results indicate that, under the SM hypothesis, the corresponding Bell-type correlation combinations could be resolved with high statistical significance at STCF.

hep-ph↗

arXiv2026

Dynamic Momentum Recalibration in Online Gradient Learning

Stochastic Gradient Descent (SGD) and its momentum variants form the backbone of deep learning optimization, yet the underlying dynamics of their gradient behavior remain insufficiently understood. In this work, we reinterpret gradient updates through the lens of signal processing and reveal that fixed momentum coefficients inherently distort the balance between bias and variance, leading to skewed or suboptimal parameter updates. To address this, we propose SGDF (SGD with Filter), an optimizer inspired by the principles of Optimal Linear Filtering. SGDF computes an online, time-varying gain to dynamically refine gradient estimation by minimizing the mean-squared error, thereby achieving an optimal trade-off between noise suppression and signal preservation. Furthermore, our approach could extend to other optimizers, showcasing its broad applicability to optimization frameworks. Extensive experiments across diverse architectures and benchmarks demonstrate SGDF surpasses conventional momentum methods and achieves performance on par with or surpassing state-of-the-art optimizers.

cs.LG↗

arXiv2026

SLO-Aware Compute Resource Allocation for Prefill-Decode Disaggregated LLM Inference

Prefill-Decode (P/D) disaggregation has emerged as a widely adopted optimization strategy for Large Language Model (LLM) inference. However, there currently exists no well-established methodology for determining the optimal number of P/D hardware resources, subject to constraints on total throughput, service level objectives (SLOs), and request characteristics - specifically input and output lengths. To address this gap, we propose a hybrid approach that combines theoretical modeling with empirical benchmarking. First, we present a theoretical model for calculating P/D resource counts, which is based on total throughput requirements, request input and output lengths, as well as prefill and decode throughput. Then, to obtain the actual prefill and decode throughput under SLO constraints, we model the prefill process using M/M/1 queuing theory, deriving the achieved prefill throughput from the benchmarked maximum prefill throughput and Time-To-First-Token (TTFT). For the decode phase, we determine the decode batch sizes that meet Time-Per-Output-Token (TPOT) requirements and obtain the corresponding decode throughput through empirical measurements. Our experimental results demonstrate that the proposed method can accurately predict optimal P/D resource allocation in real-world LLM inference scenarios.

cs.DC↗

arXiv2026

Graph Negative Feedback Bias Correction Framework for Adaptive Heterophily Modeling

Graph Neural Networks (GNNs) have emerged as a powerful framework for processing graph-structured data. However, conventional GNNs and their variants are inherently limited by the homophily assumption, leading to degradation in performance on heterophilic graphs. Although substantial efforts have been made to mitigate this issue, they remain constrained by the message-passing paradigm, which is inherently rooted in homophily. In this paper, a detailed analysis of how the underlying label autocorrelation of the homophily assumption introduces bias into GNNs is presented. We innovatively leverage a negative feedback mechanism to correct the bias and propose Graph Negative Feedback Bias Correction (GNFBC), a simple yet effective framework that is independent of any specific aggregation strategy. Specifically, we introduce a negative feedback loss that penalizes the sensitivity of predictions to label autocorrelation. Furthermore, we incorporate the output of graph-agnostic models as a feedback term, leveraging independent node feature information to counteract correlation-induced bias guided by Dirichlet energy. GNFBC can be seamlessly integrated into existing GNN architectures, improving overall performance with comparable computational and memory overhead.

cs.LG↗

arXiv2026

Markovian Scale Prediction: A New Era of Visual Autoregressive Generation

Visual AutoRegressive modeling (VAR) based on next-scale prediction has revitalized autoregressive visual generation. Although its full-context dependency, i.e., modeling all previous scales for next-scale prediction, facilitates more stable and comprehensive representation learning by leveraging complete information flow, the resulting computational inefficiency and substantial overhead severely hinder VAR's practicality and scalability. This motivates us to develop a new VAR model with better performance and efficiency without full-context dependency. To address this, we reformulate VAR as a non-full-context Markov process, proposing Markov-VAR. It is achieved via Markovian Scale Prediction: we treat each scale as a Markov state and introduce a sliding window that compresses certain previous scales into a compact history vector to compensate for historical information loss owing to non-full-context dependency. Integrating the history vector with the Markov state yields a representative dynamic state that evolves under a Markov process. Extensive experiments demonstrate that Markov-VAR is extremely simple yet highly effective: Compared to VAR on ImageNet, Markov-VAR reduces FID by 10.5% (256 $\times$ 256) and decreases peak memory consumption by 83.8% (1024 $\times$ 1024). We believe that Markov-VAR can serve as a foundation for future research on visual autoregressive generation and other downstream tasks.

cs.CV↗

arXiv2026

Multi-Scale Adaptive Neighborhood Awareness Transformer For Graph Fraud Detection

Graph fraud detection (GFD) is crucial for identifying fraudulent behavior within graphs, benefiting various domains such as financial networks and social media. Existing methods based on graph neural networks (GNNs) have succeeded considerably due to their effective expressive capacity for graph-structured data. However, the inherent inductive bias of GNNs, including the homogeneity assumption and the limited global modeling ability, hinder the effectiveness of these models. To address these challenges, we propose Multi-scale Neighborhood Awareness Transformer (MANDATE), which alleviates the inherent inductive bias of GNNs. Specifically, we design a multi-scale positional encoding strategy to encode the positional information of various distances from the central node. By incorporating it with the self-attention mechanism, the global modeling ability can be enhanced significantly. Meanwhile, we design different embedding strategies for homophilic and heterophilic connections. This mitigates the homophily distribution differences between benign and fraudulent nodes. Moreover, an embedding fusion strategy is designed for multi-relation graphs, which alleviates the distribution bias caused by different relationships. Experiments on three fraud detection datasets demonstrate the superiority of MANDATE.

cs.LG↗

arXiv2026

Federated Agentic AI for Wireless Networks: Fundamentals, Approaches, and Applications

Agentic artificial intelligence (AI) presents a promising pathway toward realizing autonomous and self-improving wireless network services. However, resource-constrained, widely distributed, and data-heterogeneous nature of wireless networks poses significant challenges to existing agentic AI that relies on centralized architectures, leading to high communication overhead, privacy risks, and non-independent and identically distributed (non-IID) data. Federated learning (FL) has the potential to improve the overall loop of agentic AI through collaborative local learning and parameter sharing without exchanging raw data. This paper proposes new federated agentic AI approaches for wireless networks. We first summarize fundamentals of agentic AI and mainstream FL types. Then, we illustrate how each FL type can strengthen a specific component of agentic AI's loop. Moreover, we conduct a case study on using FRL to improve the performance of agentic AI's action decision in low-altitude wireless networks (LAWNs). Finally, we provide a conclusion and discuss future research directions.

cs.NI↗

arXiv2026

Radio Study of Vela X Cocoon

The evolution of pulsar Wind Nebulae (PWNe) influences how high energy particles in the vicinity are generated and transport. The Vela PWN (only $\sim300$\,pc away), provides a rather rare case between young and well-evolved systems. We therefore performed new 6 and 16\,cm high-resolution observations of the Vela X Cocoon region with the Australia Telescope Compact Array (ATCA). The observations reveal a complex region with a $\sim0.5^\circ$ major curved filament extending to far south from the pulsar, as well as other intersecting filaments and wisps. Our spectral analysis hints its connection with the PWN. Our results also found strongly linearly polarized emission, ordered and tangential $B$-field to the filaments. We find the rotation measure (RM) and polarization fraction (PF) along the filament are anti-correlated with the total intensity. We develop a simple 3D model of a spiral filament to explain these, while the PF distribution requires external interpretations such as interaction with the reverse shock. Comparison with archival data suggests that large scale features like the major filament are generally stable and large motions near the X-ray filament, all these confirm the distinction between radio and X-ray features.

astro-ph.HE↗

arXiv2026

InterFlow: Designing Unobtrusive AI to Empower Interviewers in Semi-Structured Interviews

Semi-structured interviews are a common method in qualitative research. However, conducting high-quality interviews is cognitively demanding and requires strong interviewing skills. To lower this bar, we propose InterFlow, an AI-powered visual scaffold that helps interviewers manage the interview flow and facilitates real-time data sensemaking. The system dynamically adapts the interview script to the ongoing conversation and provides a visual timer to track interview progress and conversational balance. It further supports information capture with three levels of automation: manual entry, AI-assisted summary with user-specified focus, and a co-interview agent that proactively surfaces potential follow-up points. A within-subject user study ($N=12$) indicates that InterFlow reduces interviewers' cognitive load and facilitates the interview process. Based on the user study findings, we provide design implications for unobtrusive and agency-preserving AI assistance under time-sensitive and cognitively-demanding situations.

cs.HC↗

arXiv2026

One-Token Verification for Reasoning Correctness Estimation

Recent breakthroughs in large language models (LLMs) have led to notable successes in complex reasoning tasks, such as mathematical problem solving. A common strategy for improving performance is parallel thinking, in which multiple reasoning traces are generated and the final prediction is made using aggregation schemes like majority voting or best-of-$N$ decoding. However, two key challenges persist. First, multi-sample decoding incurs substantial inference latency, especially for long-form outputs. Second, effective mechanisms for reliably assessing the correctness of individual reasoning traces are still limited. To address these challenges, we introduce One-Token Verification (OTV), a computational method that estimates reasoning correctness in a single forward pass during generation. OTV is activated by a learnable token and integrated into the LLM via low-rank adaptation to probe internal reasoning signals through the key-value cache, supporting token-level correctness estimation at any stage of generation without disrupting primary reasoning. Experiments on mathematical reasoning benchmarks demonstrate that OTV consistently surpasses existing verifiers. Additionally, OTV reduces token usage by up to $90\%$ through correctness-guided early termination, prioritizing shorter, more reliable solutions.

cs.LG↗

arXiv2026

Unitary Coupled-Cluster based Self-Consistent Electron Propagator Theory for Electron-Detached and Electron-Attached States: A Quadratic Unitary Coupled-Cluster Singles and Doubles Method and Benchmark Calculations

A unitary coupled-cluster (UCC)-based self-consistent electron propagator theory (EPT) is proposed for the description of electron-detached and electron-attached states. Two practical schemes, termed IP/EA-UCC3 and IP/EA-qUCCSD, are developed and implemented within the UCC singles and doubles (UCCSD) framework using the perturbative and commutator-based truncation strategies for the similarity-transformed Hamiltonian $\bar{H}$. The numerical performance of these UCC-based EPT methods is evaluated primarily using full configuration interaction (FCI) reference data and compared with established approaches, including IP/EA-ADC(3), IP/EA-ADC(4) and IP/EA-EOM-CCSD. Benchmark calculations demonstrate that IP-qUCCSD achieves the highest overall accuracy among Hermitian ionized-state methods for one-hole (1h)-dominated IPs of closed-shell systems, with a mean absolute deviation (MAD) of 0.19 eV and standard deviation (SD) of 0.13 eV. Remarkably, despite the absence of triple-excitation contributions, IP-qUCCSD outperforms the higher-order ADC(4) method. For one-particle (1p)-dominated EA calculations, all tested methods exhibit comparable accuracy.

physics.chem-ph↗