arXiv subjects

Jialing Li

Publications and source records attributed to Jialing Li.

3 recordsLinked to original sources

arXiv2026

SchemaGUI: A Schema-Driven Benchmark for Controllable GUI Generation Evaluation

Large language models (LLMs) have demonstrated strong potential in graphical user interface (GUI) generation, but reliable evaluation remains challenging due to uncontrolled data distributions, noisy annotations, and limited layout scenario coverage. To address this, we propose SchemaGUI, a template-based benchmark for controllable GUI generation evaluation. By synthesizing paired natural language instructions and deterministic function-call references from parameterized interface schemas, SchemaGUI can generate thousands of deterministically annotated tasks in seconds without human labeling. Based on 1,000 evaluated instances per scenario and language across six representative bilingual scenarios, we benchmark five mainstream models, including the Qwen3.5 family, Qwen3-Coder-30B, and DeepSeek-R1. Our extensive analysis reveals three key insights. First, precise geometric spatial control remains an important bottleneck; while scaling Qwen3.5 from 4B to 27B improves Schema Feasibility from 91.56% to 99.63%, the Geometry score improves more modestly (from 67.05% to 75.30%). Second, generation difficulty is highly sensitive to layout complexity, with current LLMs excelling at simple sequential arrangements but suffering severe coordinate drift in dense grids and multi-region compositions. Third, thinking mode increases token consumption while generally reducing GUI Score, particularly for smaller models.

cs.CL↗

arXiv2026

Scaling Behavior of Single LLM-Driven Multi-Agent Systems

The burgeoning field of LLM-based Multi-Agent Systems (MAS) promises to tackle complex tasks through collaborative intelligence, yet fundamental questions regarding their scaling behavior and intrinsic collective dynamics remain underexplored. This paper systematically investigates how the performance of a homogeneous MAS evolves as the number of agents increases, isolating the variable of collaboration from model or knowledge heterogeneity. We propose the Sequential Iterative Multi-Agent System (SIMAS) framework, a minimalist architecture centered on sequential inter-agent communication, to clearly observe scaling effects. Through extensive experiments across diverse tasks and model scales, we establish that MAS performance does not scale monotonically with agent count but follows a pattern of diminishing returns, governed by a trade-off between collaborative synergy and coordination overhead. Our findings reveal that effective MAS requires a sufficiently capable base LLM, that task type critically modulates the optimal agent count, and that collective intelligence is an emergent property contingent on strategic interaction design rather than a guaranteed outcome of agent plurality. The performance degradation stems coordination overhead rather than merely long-context failure, and the scaling tendency generalizes across interaction architectures like structured debate topologies. This work provides a foundational understanding of MAS scaling laws, offering practical guidance for designing efficient collaborative systems and challenging the prevailing assumption that more agents invariably lead to better performance.

cs.MA↗

arXiv2025

Volume-Based Space-Time Cube for Large-Scale Continuous Spatial Time Series

Spatial time series visualization offers scientific research pathways and analytical decision-making tools across various spatiotemporal domains. Despite many advanced methodologies, the seamless integration of temporal and spatial information remains a challenge. The space-time cube (STC) stands out as a promising approach for the synergistic presentation of spatial and temporal information, with successful applications across various spatiotemporal datasets. However, the STC is plagued by well-known issues such as visual occlusion and depth ambiguity, which are further exacerbated when dealing with large-scale spatial time series data. In this study, we introduce a novel technical framework termed VolumeSTCube, designed for continuous spatiotemporal phenomena. It first leverages the concept of the STC to transform discretely distributed spatial time series data into continuously volumetric data. Subsequently, volume rendering and surface rendering techniques are employed to visualize the transformed volumetric data. Volume rendering is utilized to mitigate visual occlusion, while surface rendering provides pattern details by enhanced lighting information. Lastly, we design interactions to facilitate the exploration and analysis from temporal, spatial, and spatiotemporal perspectives. VolumeSTCube is evaluated through a computational experiment, a real-world case study with one expert, and a controlled user study with twelve non-experts, compared against a baseline from prior work, showing its superiority and effectiveness in largescale spatial time series analysis.

cs.HC↗