Searcharxiv⌕ Search

arXiv subjects

Jian Zhang

Publications and source records attributed to Jian Zhang.

At least 145 records · Page 8Linked to original sources
arXiv2026

Relatron: Automating Relational Machine Learning over Relational Databases

Predictive modeling over relational databases (RDBs) powers applications, yet remains challenging due to capturing both cross-table dependencies and complex feature interactions. Relational Deep Learning (RDL) methods automate feature engineering via message passing, while classical approaches like Deep Feature Synthesis (DFS) rely on predefined non-parametric aggregators. Despite performance gains, the comparative advantages of RDL over DFS and the design principles for selecting effective architectures remain poorly understood. We present a comprehensive study that unifies RDL and DFS in a shared design space and conducts architecture-centric searches across diverse RDB tasks. Our analysis yields three key findings: (1) RDL does not consistently outperform DFS, with performance being highly task-dependent; (2) no single architecture dominates across tasks, underscoring the need for task-aware model selection; and (3) validation accuracy is an unreliable guide for architecture choice. This search yields a model performance bank that links architecture configurations to their performance; leveraging this bank, we analyze the drivers of the RDL-DFS performance gap and introduce two task signals -- RDB task homophily and an affinity embedding that captures size, path, feature, and temporal structure -- whose correlation with the gap enables principled routing. Guided by these signals, we propose Relatron, a task embedding-based meta-selector that chooses between RDL and DFS and prunes the within-family search. Lightweight loss-landscape metrics further guard against brittle checkpoints by preferring flatter optima. In experiments, Relatron resolves the "more tuning, worse performance" effect and, in joint hyperparameter-architecture optimization, achieves up to 18.5% improvement over strong baselines with 10x lower cost than Fisher information-based alternatives.

cs.LG↗
arXiv2026

Magnetic anisotropic pinning and symmetric breaking induced by interfacial coupling in topological-like ruthenate superlattices

Interfacial engineering enables various emergent effects such as spin reorientations and transport anisotropy. Noncollinear spin textures are essential for realizing many emergent quantum transport phenomena. However, driving such spin structures requires precise control of the interfacial magnetic coupling in complex oxide heterostructures. Here, by utilizing competing exchange interactions at the interface between ferromagnetic metal SrRuO3 and ferromagnetic insulator LaCoO3, we discovered a noncollinear spin configuration in SrRuO3 sublayers. Magnetic stripes were induced by out-of-plane rather than in-plane magnetic fields, indicating strong anisotropy pinning in our superlattices. The observed magneto-transport anisotropy is well explained by our proposed spin configurations, accounting for contributions from both bulk and interface of the SrRuO3 layers. More interestingly, magnetic skymionic textures were absent even at high magnetic fields. The interfacial exchange interaction overwhelms the Dzyaloshinskii-Moriya interaction (DMI) that stabilizes skyrmions, featuring a higher exchange coupling energy than that for the topological spin textures. Our work highlights the potential of interfacial engineering in tuning the spintronic properties by designing proper interfacial interactions.

cond-mat.str-el↗
arXiv2026

GeoChallenge: A Multi-Answer Multiple-Choice Benchmark for Geometric Reasoning with Diagrams

Evaluating the symbolic reasoning of large language models (LLMs) calls for geometry benchmarks that require multi-step proofs grounded in both text and diagrams. However, existing benchmarks are often limited in scale and rarely provide visually grounded multiple-choice questions, limiting reliable evaluation of complex reasoning. We introduce GeoChallenge, a dataset of 90K automatically generated multiple-choice geometry proof problems, each requiring multi-step reasoning over aligned textual descriptions and diagrams. GeoChallenge provides fine-grained complexity ratings and formal language annotations to enable controlled evaluation. Experiments on multiple advanced LLMs show a clear performance gap between models and humans (the best-performing model, GPT-5-nano, achieves 75.89 exact match vs. 94.74 for humans). Further analysis also reveals three common failure patterns of LLMs: (1) exact match failures under the multiple-choice setting; (2) weak visual reliance; and (3) overextended reasoning without convergence.

cs.CL↗
arXiv2026

CDRL: A Reinforcement Learning Framework Inspired by Cerebellar Circuits and Dendritic Computational Strategies

Reinforcement learning (RL) has achieved notable performance in high-dimensional sequential decision-making tasks, yet remains limited by low sample efficiency, sensitivity to noise, and weak generalization under partial observability. Most existing approaches address these issues primarily through optimization strategies, while the role of architectural priors in shaping representation learning and decision dynamics is less explored. Inspired by structural principles of the cerebellum, we propose a biologically grounded RL architecture that incorporate large expansion, sparse connectivity, sparse activation, and dendritic-level modulation. Experiments on noisy, high-dimensional RL benchmarks show that both the cerebellar architecture and dendritic modulation consistently improve sample efficiency, robustness, and generalization compared to conventional designs. Sensitivity analysis of architectural parameters suggests that cerebellum-inspired structures can offer optimized performance for RL with constrained model parameters. Overall, our work underscores the value of cerebellar structural priors as effective inductive biases for RL.

cs.LG↗
arXiv2026

TraceCoder: A Trace-Driven Multi-Agent Framework for Automated Debugging of LLM-Generated Code

Large Language Models (LLMs) often generate code with subtle but critical bugs, especially for complex tasks. Existing automated repair methods typically rely on superficial pass/fail signals, offering limited visibility into program behavior and hindering precise error localization. In addition, without a way to learn from prior failures, repair processes often fall into repetitive and inefficient cycles. To overcome these challenges, we present TraceCoder, a collaborative multi-agent framework that emulates the observe-analyze-repair process of human experts. The framework first instruments the code with diagnostic probes to capture fine-grained runtime traces, enabling deep insight into its internal execution. It then conducts causal analysis on these traces to accurately identify the root cause of the failure. This process is further enhanced by a novel Historical Lesson Learning Mechanism (HLLM), which distills insights from prior failed repair attempts to inform subsequent correction strategies and prevent recurrence of similar mistakes. To ensure stable convergence, a Rollback Mechanism enforces that each repair iteration constitutes a strict improvement toward the correct solution. Comprehensive experiments across multiple benchmarks show that TraceCoder achieves up to a 34.43\% relative improvement in Pass@1 accuracy over existing advanced baselines. Ablation studies verify the significance of each system component, with the iterative repair process alone contributing a 65.61\% relative gain in accuracy. Furthermore, TraceCoder significantly outperforms leading iterative methods in terms of both accuracy and cost-efficiency.

cs.SE↗
arXiv2026

TIDE: Trajectory-based Diagnostic Evaluation of Test-Time Improvement in LLM Agents

Recent advances in autonomous LLM agents demonstrate their ability to improve performance through iterative interaction with the environment. We define this paradigm as Test-Time Improvement (TTI). However, the mechanisms under how and why TTI succeed or fail remain poorly understood, and existing evaluation metrics fail to capture their task optimization efficiency, behavior adaptation after erroneous actions, and the specific utility of working memory for task completion. To address these gaps, we propose Test-time Improvement Diagnostic Evaluation (TIDE), an agent-agnostic and environment-agnostic framework that decomposes TTI into three comprehensive and interconnected dimensions. The framework measures (1) the overall temporal dynamics of task completion and (2) identifies whether performance is primarily constrained by recursive looping behaviors or (3) by burdensome accumulated memory. Through extensive experiments across diverse agents and environments, TIDE highlights that improving agent performance requires more than scaling internal reasoning, calling for explicitly optimizing the interaction dynamics between the agent and the environment.

cs.AI↗
arXiv2026

End-to-End Agentic RAG System Training for Traceable Diagnostic Reasoning

The integration of Large Language Models (LLMs) into healthcare is constrained by knowledge limitations, hallucinations, and a disconnect from Evidence-Based Medicine (EBM). While Retrieval-Augmented Generation (RAG) offers a solution, current systems often rely on static workflows that miss the iterative, hypothetico-deductive reasoning of clinicians. To address this, we introduce Deep-DxSearch, an agentic RAG system trained end-to-end via reinforcement learning (RL) for traceable diagnostic reasoning. Deep-DxSearch acts as an active investigator, treating the LLM as an agent within an environment of 16,000+ guideline-derived disease profiles, 150,000+ patient records for case-based reasoning, and over 27 million biomedical documents. Using soft verifiable rewards that co-optimize retrieval and reasoning, the model learns to formulate queries, evaluate evidence, and refine searches to close diagnostic gaps. Experiments show our end-to-end RL framework consistently outperforms prompt-engineering and training-free RAG methods. On in-distribution (ID) and out-of-distribution (OOD) benchmarks for common and rare diseases, Deep-DxSearch surpasses strong baselines-including GPT-4o, DeepSeek-R1, and medical-specific frameworks-achieving an average accuracy gain of 22.7% over the second-best model. In validation with 150 real-world cases, Deep-DxSearch boosts physicians' average diagnostic accuracy from 45.6% to 69.1%. These results indicate that evolving agentic systems to leverage statistical regularities in large-scale healthcare data is key for trustworthy diagnostic assistants. All data, code, and checkpoints are available at https://qiaoyu-zheng.github.io/Deep-DxSearch.

cs.CL↗
arXiv2026

ReGlove: A Soft Pneumatic Glove for Activities of Daily Living Assistance via Wrist-Mounted Vision

This paper presents ReGlove, a system that converts low-cost commercial pneumatic rehabilitation gloves into vision-guided assistive orthoses. Chronic upper-limb impairment affects millions worldwide, yet existing assistive technologies remain prohibitively expensive or rely on unreliable biological signals. Our platform integrates a wrist-mounted camera with an edge-computing inference engine (Raspberry Pi 5) to enable context-aware grasping without requiring reliable muscle signals. By adapting real-time YOLO-based computer vision models, the system achieves 96.73% grasp classification accuracy with sub-40.00 millisecond end-to-end latency. Physical validation using standardized benchmarks shows 82.71% success on YCB object manipulation and reliable performance across 27 Activities of Daily Living (ADL) tasks. With a total cost under $250 and exclusively commercial components, ReGlove provides a technical foundation for accessible, vision-based upper-limb assistance that could benefit populations excluded from traditional EMG-controlled devices.

cs.RO↗
arXiv2026

Scalable Fair Influence Blocking Maximization via Approximately Monotonic Submodular Optimization

Influence Blocking Maximization (IBM) aims to select a positive seed set to suppress the spread of negative influence. However, existing IBM methods focus solely on maximizing blocking effectiveness, overlooking fairness across communities. To address this issue, we formalize fairness in IBM and justify Demographic Parity (DP) as a notion that is particularly well aligned with its semantics. Yet enforcing DP is computationally challenging: prior work typically formulates DP as a Linear Programming (LP) problem and relies on costly solvers, rendering them impractical for large-scale networks. In this paper, we propose a DP-aware objective while maintaining an approximately monotonic submodular structure, enabling efficient optimization with theoretical guarantees. We integrate this objective with blocking effectiveness through a tunable scalarization, yielding a principled fairness-effectiveness trade-offs. Building on this structure, we develop CELF-R, an accelerated seed selection algorithm that exploits approximate submodularity to eliminate redundant evaluations and naturally supports Pareto front construction. Extensive experiments demonstrate that CELF-R consistently outperforms state-of-the-art baselines, achieving a $(1-1/e-ψ)$-approximate solution while maintaining high efficiency.

cs.DS↗
arXiv2026

Decomposing and Composing: Towards Efficient Vision-Language Continual Learning via Rank-1 Expert Pool in a Single LoRA

Continual learning (CL) in vision-language models (VLMs) faces significant challenges in improving task adaptation and avoiding catastrophic forgetting. Existing methods usually have heavy inference burden or rely on external knowledge, while Low-Rank Adaptation (LoRA) has shown potential in reducing these issues by enabling parameter-efficient tuning. However, considering directly using LoRA to alleviate the catastrophic forgetting problem is non-trivial, we introduce a novel framework that restructures a single LoRA module as a decomposable Rank-1 Expert Pool. Our method learns to dynamically compose a sparse, task-specific update by selecting from this expert pool, guided by the semantics of the [CLS] token. In addition, we propose an Activation-Guided Orthogonal (AGO) loss that orthogonalizes critical parts of LoRA weights across tasks. This sparse composition and orthogonalization enable fewer parameter updates, resulting in domain-aware learning while minimizing inter-task interference and maintaining downstream task performance. Extensive experiments across multiple settings demonstrate state-of-the-art results in all metrics, surpassing zero-shot upper bounds in generalization. Notably, it reduces trainable parameters by 96.7% compared to the baseline method, eliminating reliance on external datasets or task-ID discriminators. The merged LoRAs retain less weights and incur no inference latency, making our method computationally lightweight.

cs.LG↗
arXiv2026

Differential Dynamic Causal Nets: Model Construction, Identification and Group Comparisons

Pathophysiolpgical modelling of brain systems from microscale to macroscale remains difficult in group comparisons partly because of the infeasibility of modelling the interactions of thousands of neurons at the scales involved. Here, to address the challenge, we present a novel approach to construct differential causal networks directly from electroencephalogram (EEG) data. The proposed network is based on conditionally coupled neuronal circuits which describe the average behaviour of interacting neuron populations that contribute to observed EEG data. In the network, each node represents a parameterised local neural system while directed edges stand for node-wise connections with transmission parameters. The network is hierarchically structured in the sense that node and edge parameters are varying in subjects but follow a mixed-effects model. A novel evolutionary optimisation algorithm for parameter inference in the proposed method is developed using a loss function derived from Chen-Fliess expansions of stochastic differential equations. The method is demonstrated by application to the fitting of coupled Jansen-Rit local models. The performance of the proposed method is evaluated on both synthetic and real EEG data. In the real EEG data analysis, we track changes in the parameters that characterise dynamic causality within brains that demonstrate epileptic activity. We show evidence of network functional disruptions, due to imbalance of excitatory-inhibitory interneurons and altered epileptic brain connectivity, before and during seizure periods.

q-bio.NC↗
arXiv2026

A Low-mass Model of The Milky Way: The Disk Warp Resulting from A Galaxy Merger

Previous studies have shown that disk warps can result from galaxy mergers. Recent research indicates a noticeable decline in the rotation curve (RC) of the Milky Way (MW), suggesting the need for a new low-mass model to describe its dynamical features. This study constructs a new Gaia-Sausage-Enceladus (GSE) merger model to characterize the RC features of our galaxy. We use the GIZMO code to simulate mergers with various orbital parameters to investigate how the disk warp evolves under different conditions. This simulation demonstrates the evolutionary mechanism of disk warp, which arises due to the asymmetric gravitational potential of the dark matter (DM) halo generated universally by galaxy mergers. The results indicate that the tilt angle of the DM halo partly reflects the gravitational strength at the $Z=0$ plane, while the gravitational strength on the disk plane reflects the amplitude of disk warp. We identify a dual-regime interaction mechanism driven by the asymmetric halo potential. On short timescales, we find a distinct anti-correlation between the halo's tilt angle and the disk's warp amplitude, indicating a `seesaw' mechanism of angular momentum exchange. On secular timescales, however, dynamical friction drives a global alignment, causing both the halo tilt and the warp amplitude to decay simultaneously. Furthermore, we demonstrate that high-inclination mergers can sustain long-lived prograde precession, where the persistent yet decaying gravitational torque maintains the prograde bending mode against differential wind-up.

astro-ph.GA↗
arXiv2026

GraphSB: Boosting Imbalanced Node Classification on Graphs through Structural Balance

Imbalanced node classification is a critical challenge in graph learning, where most existing methods typically utilize Graph Neural Networks (GNNs) to learn node representations. These methods can be broadly categorized into the data-level and the algorithm-level. The former aims to synthesize minority-class nodes to mitigate quantity imbalance, while the latter tries to optimize the learning process to highlight minority classes. However, neither of them addresses the inherently imbalanced graph structure, which is a fundamental factor that incurs majority-class dominance and minority-class assimilation in GNNs. Our theoretical analysis further supports this critical insight. Therefore, we propose GraphSB (Graph Structural Balance), a novel framework that incorporates Structural Balance as a key strategy to address the underlying imbalanced graph structure before node synthesis. Structural Balance performs a two-stage structure optimization: Structure Enhancement that mines hard samples near decision boundaries through dual-view analysis and enhances connectivity for minority classes through adaptive augmentation, and Relation Diffusion that propagates the enhanced minority context while simultaneously capturing higher-order structural dependencies. Thus, GraphSB balances structural distribution before node synthesis, enabling more effective learning in GNNs. Extensive experiments demonstrate that GraphSB significantly outperforms the state-of-the-art methods. More importantly, the proposed Structural Balance can be seamlessly integrated into state-of-the-art methods as a simple plug-and-play module, increasing their accuracy by an average of 4.57%.

cs.LG↗
arXiv2026

A Survey of Quantized Graph Representation Learning: Connecting Graph Structures with Large Language Models

Recent years have witnessed rapid advances in graph representation learning, with the continuous embedding approach emerging as the dominant paradigm. However, such methods encounter issues regarding parameter efficiency, interpretability, and robustness. Thus, Quantized Graph Representation (QGR) learning has recently gained increasing interest, which represents the graph structure with discrete codes instead of conventional continuous embeddings. Given its analogous representation form to natural language, QGR also possesses the capability to seamlessly integrate graph structures with large language models (LLMs). As this emerging paradigm is still in its infancy yet holds significant promise, we undertake this thorough survey to promote its rapid future prosperity. We first present the background of the general quantization methods and their merits. Moreover, we provide an in-depth demonstration of current QGR studies from the perspectives of quantized strategies, training objectives, distinctive designs, knowledge graph quantization, and applications. We further explore the strategies for code dependence learning and integration with LLMs. At last, we give discussions and conclude future directions, aiming to provide a comprehensive picture of QGR and inspire future research.

cs.LG↗
arXiv2026

A0: An Affordance-Aware Hierarchical Model for General Robotic Manipulation

Robotic manipulation faces critical challenges in understanding spatial affordances--the "where" and "how" of object interactions--essential for complex manipulation tasks like wiping a board or stacking objects. Existing methods, including modular-based and end-to-end approaches, often lack robust spatial reasoning capabilities. Unlike recent point-based and flow-based affordance methods that focus on dense spatial representations or trajectory modeling, we propose A0, a hierarchical affordance-aware diffusion model that decomposes manipulation tasks into high-level spatial affordance understanding and low-level action execution. A0 leverages the Embodiment-Agnostic Affordance Representation, which captures object-centric spatial affordances by predicting contact points and post-contact trajectories. A0 is pre-trained on 1 million contact points data and fine-tuned on annotated trajectories, enabling generalization across platforms. Key components include Position Offset Attention for motion-aware feature extraction and a Spatial Information Aggregation Layer for precise coordinate mapping. The model's output is executed by the action execution module. Experiments on multiple robotic systems (Franka, Kinova, Realman, and Dobot) demonstrate A0's superior performance in complex tasks, showcasing its efficiency, flexibility, and real-world applicability.

cs.RO↗
arXiv2026

Towards Efficient and Robust Linguistic Emotion Diagnosis for Mental Health via Multi-Agent Instruction Refinement

Linguistic expressions of emotions such as depression, anxiety, and trauma-related states are pervasive in clinical notes, counseling dialogues, and online mental health communities, and accurate recognition of these emotions is essential for clinical triage, risk assessment, and timely intervention. Although large language models (LLMs) have demonstrated strong generalization ability in emotion analysis tasks, their diagnostic reliability in high-stakes, context-intensive medical settings remains highly sensitive to prompt design. Moreover, existing methods face two key challenges: emotional comorbidity, in which multiple intertwined emotional states complicate prediction, and inefficient exploration of clinically relevant cues. To address these challenges, we propose APOLO (Automated Prompt Optimization for Linguistic Emotion Diagnosis), a framework that systematically explores a broader and finer-grained prompt space to improve diagnostic efficiency and robustness. APOLO formulates instruction refinement as a Partially Observable Markov Decision Process and adopts a multi-agent collaboration mechanism involving Planner, Teacher, Critic, Student, and Target roles. Within this closed-loop framework, the Planner defines an optimization trajectory, while the Teacher-Critic-Student agents iteratively refine prompts to enhance reasoning stability and effectiveness, and the Target agent determines whether to continue optimization based on performance evaluation. Experimental results show that APOLO consistently improves diagnostic accuracy and robustness across domain-specific and stratified benchmarks, demonstrating a scalable and generalizable paradigm for trustworthy LLM applications in mental healthcare.

cs.AI↗
arXiv2026

VulnResolver: A Hybrid Agent Framework for LLM-Based Automated Vulnerability Issue Resolution

As software systems grow in complexity, security vulnerabilities have become increasingly prevalent, posing serious risks and economic costs. Although automated detection tools such as fuzzers have advanced considerably, effective resolution still often depends on human expertise. Existing automated vulnerability repair (AVR) methods rely heavily on manually provided annotations (e.g., fault locations or CWE labels), which are often difficult and time-consuming to obtain, while overlooking the rich, naturally embedded semantic context found in issue reports from developers. In this paper, we present VulnResolver, the first LLM-based hybrid agent framework for automated vulnerability issue resolution. VulnResolver unites the adaptability of autonomous agents with the stability of workflow-guided repair through two specialized agents. The Context Pre-Collection Agent (CPCAgent) adaptively explores the repository to gather dependency and contextual information, while the Safety Property Analysis Agent (SPAAgent) generates and validates the safety properties violated by vulnerabilities. Together, these agents produce structured analyses that enrich the original issue reports, enabling more accurate vulnerability localization and patch generation. Evaluations on the SEC-bench benchmark show that VulnResolver resolves 75% of issues on SEC-bench Lite, achieving the best resolution performance. On SEC-bench Full, VulnResolver also significantly outperforms the strongest baseline, the agent-based OpenHands, confirming its effectiveness. Overall, VulnResolver delivers an adaptive and security-aware framework that advances end-to-end automated vulnerability issue resolution through workflow stability and the specialized agents' capabilities in contextual reasoning and property-based analysis.

cs.SE↗
arXiv2026

ErrEval: Error-Aware Evaluation for Question Generation through Explicit Diagnostics

Automatic Question Generation (QG) often produces outputs with critical defects, such as factual hallucinations and answer mismatches. However, existing evaluation methods, including LLM-based evaluators, mainly adopt a black-box and holistic paradigm without explicit error modeling, leading to the neglect of such defects and overestimation of question quality. To address this issue, we propose ErrEval, a flexible and Error-aware Evaluation framework that enhances QG evaluation through explicit error diagnostics. Specifically, ErrEval reformulates evaluation as a two-stage process of error diagnosis followed by informed scoring. At the first stage, a lightweight plug-and-play Error Identifier detects and categorizes common errors across structural, linguistic, and content-related aspects. These diagnostic signals are then incorporated as explicit evidence to guide LLM evaluators toward more fine-grained and grounded judgments. Extensive experiments on three benchmarks demonstrate the effectiveness of ErrEval, showing that incorporating explicit diagnostics improves alignment with human judgments. Further analyses confirm that ErrEval effectively mitigates the overestimation of low-quality questions.

cs.AI↗