Multimodal Large Language Models (MLLMs) have been increasingly adopted to automate webpage generation from visual designs (e.g., screenshots). However, existing evaluations are limited to visual fidelity assessment under a fixed browser-device configuration. Such a setting overlooks the cross-environment rendering com...
Ziyun Guo, Jingyu Xiao, Yu-Qiang Sun et al.· 0 citations
This work introduces Path2Spec, a divide-and-conquer framework that leverages LLMs to extract all execution paths from an input program, generates path-specific specifications for each, and merges them into a comprehensive overall specification.
Dan Huang, Zhensu Sun, Hui-Hui Huang et al.· 0 citations
Multimodal Large Language Models (MLLMs) have demonstrated strong performance on the UI-to-code task, which aims to generate UI code from design mock-ups. However, when applied to long and complex websites, they often struggle with fragmented segmentation, redundant code generation for repetitive components, and freque...
Jingyu Xiao, Jiantong Qin, ShuoQiu Li et al.· Proceedings of the 32nd ACM...· 1 citation
System logs are critical for software reliability. While many automated log-based anomaly detection methods exist, they often falter in large-scale cloud systems due to high resource consumption and poor adaptability to evolving logs. In this paper, we present SeaLog, an accurate, lightweight, and adaptive log-based an...
Jinyang Liu, Junjie Huang, Zhihan Jiang et al.· ACM Transactions on Software...· 0 citations
Real-world vulnerabilities often span multiple functions, yet most learning-based detectors classify each function in isolation: on a sample of real CVEs, we find that 71.7% of vulnerable functions require evidence from outside the function to be classified correctly. Agentic reinforcement learning (RL) could close thi...
Yikun Li, Ting Zhang, Jiakun Liu et al.· arXiv.org· 2 citations
Results show that combining layout compaction, adaptive configuration, and instruction-aware pruning can make multimodal code understanding more efficient, and propose CodeShrink, an adaptive visual compression framework with three components.
Wenxin Tang, Jingyu Xiao, Zhen-Yu Liu et al.· arXiv.org· 1 citation
This work introduces LongRCA Bench, comprising 1,140 failed trajectories across five domains without injected errors, and presents Root-Cause Trajectory Attribution (RCTA), a training-free method that retrieves candidate error steps from segment summaries and traces them to available earlier handoff instructions.
Yunfei Zhang, Boyu Feng, Changhua Pei et al.· 1 citation
VisualRepair is proposed, an MLLM-based framework for visual software issue repair comprising two core modules: Image Type-aware Tool Calling (ITTC), which classifies input images and dynamically invokes a tailored tool-calling chain for robust visual interpretation, and Dynamic Test-time Region Focusing (DTRF), which...
This work proposes ComUICoder, a component-based UI code generation framework that emphasizes semantic-aware segmentation, code reuse, and fine-grained refinement and significantly improves overall generation quality and code reusability on complex multipage websites.
Jingyu Xiao, Jiantong Qin, ShuoQiu Li et al.· Proceedings of the 32nd ACM...· 1 citation
It is argued that risk-free deployment must be grounded in the agent's trajectory: the recorded sequence of reasoning steps, tool invocations, and environmental observations, and the absence of adequacy metrics.
