arXiv subjects

Zhiqian Zhang

Publications and source records attributed to Zhiqian Zhang.

4 recordsLinked to original sources

arXiv2026

HiMA-Ecom: Enabling Joint Training of Hierarchical Multi-Agent E-commerce Assistants

Hierarchical multi-agent systems based on large language models (LLMs) have become a common paradigm for building AI assistants in vertical domains such as e-commerce, where a master agent coordinates multiple specialized sub-agents. Despite their practical importance, realistic benchmarks for training and evaluating such systems remain scarce, and joint optimization across functionally distinct agents is still challenging. To address this gap, we introduce HiMA-Ecom, the first hierarchical multi-agent benchmark tailored for e-commerce scenarios. HiMA-Ecom contains 22.8K instances, including agent-specific supervised fine-tuning samples with memory and system-level input-output pairs for joint multi-agent reinforcement learning. Building upon it, a joint training method named HiMA-R1 is proposed. It presents Variance-Reduction Group Relative Policy Optimization (VR-GRPO), which employs initial trajectory-based Monte Carlo sampling to mitigate the exponential joint action space and selects informative agent groups for efficient updates based on reward variance. Furthermore, an adaptive memory evolution mechanism that repurposes GRPO rewards as cost-free supervisory signals is designed to eliminate repetitive reasoning and accelerate convergence. Experiments on HiMA-Ecom demonstrate that our method, built upon smaller 3B/7B open-source models, achieves performance comparable to that of larger LLMs, such as DeepSeek-R1, and surpasses DeepSeek-V3 by an average of 6\%.

cs.AI↗

arXiv2026

Xuanwu: Evolving General Multimodal Models into an Industrial-Grade Foundation for Content Ecosystems

In recent years, multimodal large models have continued to improve on general benchmarks. However, in real-world content moderation and adversarial settings, mainstream models still suffer from degraded generalization and catastrophic forgetting because of limited fine-grained visual perception and insufficient modeling of long-tail noise. In this paper, we present Xuanwu VL-2B as a case study of how general multimodal models can be developed into an industrial-grade foundation model for content ecosystems. The model adopts a compact InternViT-300M + MLP + Qwen3 1.7B architecture, balancing fine-grained visual perception, language-semantic alignment, and deployment cost within an approximately 2B-parameter budget. To balance business specialization with the retention of general capabilities, we developed a data iteration and curation mechanism and trained the model through a progressive three-stage pipeline: pre-training, mid-training, and post-training. Ablation studies and offline business evaluations show that Xuanwu VL-2B achieves an average score of 67.90 across seven OpenCompass multimodal metrics (vs. 64.27 for InternVL 3.5 2B), an average recall of 94.38% over seven independent business moderation tasks, and a weighted overall recall of 82.82% on policy-violating text in challenging adversarial OCR scenarios, outperforming Gemini-2.5-Pro (76.72%). These results show that, under a limited parameter budget, Xuanwu VL-2B achieves a practical balance among business alignment, visual perception, general capability retention, and deployment cost.

cs.AI↗

arXiv2024

An Effective Current Limiting Strategy to Enhance Transient Stability of Virtual Synchronous Generator

VSG control has emerged as a crucial technology for integrating renewable energy sources. However, renewable energy have limited tolerance to overcurrent, necessitating the implementation of current limiting (CL)strategies to mitigate the overcurrent. The introduction of different CL strategies can have varying impacts on the system. While previous studies have discussed the effects of different CL strategies on the system, but they lack intuitive and explicit explanations. Meanwhile, previous CL strategy have failed to effectively ensure the stability of the system. In this paper, the Equal Proportional Area Criterion (EPAC) method is employed to intuitively explain how different CL strategies affect transient stability. Based on this, an effective current limiting strategy is proposed. Simulations are conducted in MATLAB/Simulink to validate the proposed strategy. The simulation results demonstrate that, the proposed effective CL strategy exhibits superior stability.

eess.SY↗

arXiv2017

NEXT: A Neural Network Framework for Next POI Recommendation

The task of next POI recommendation has been studied extensively in recent years. However, developing an unified recommendation framework to incorporate multiple factors associated with both POIs and users remains challenging, because of the heterogeneity nature of these information. Further, effective mechanisms to handle cold-start and endow the system with interpretability are also difficult topics. Inspired by the recent success of neural networks in many areas, in this paper, we present a simple but effective neural network framework for next POI recommendation, named NEXT. NEXT is an unified framework to learn the hidden intent regarding user's next move, by incorporating different factors in an unified manner. Specifically, in NEXT, we incorporate meta-data information and two kinds of temporal contexts (i.e., time interval and visit time). To leverage sequential relations and geographical influence, we propose to adopt DeepWalk, a network representation learning technique, to encode such knowledge. We evaluate the effectiveness of NEXT against state-of-the-art alternatives and neural networks based solutions. Experimental results over three publicly available datasets demonstrate that NEXT significantly outperforms baselines in real-time next POI recommendation. Further experiments demonstrate the superiority of NEXT in handling cold-start. More importantly, we show that NEXT provides meaningful explanation of the dimensions in hidden intent space.

cs.IR↗