In long agent executions, an early error can persist through later actions and checks, while evidence needed to trace its origin is dispersed across the history. Short histories offer limited tests of recovering error origins across substantial subsequent execution. We introduce LongRCA Bench: 1,140 complete failed tra...
Yun-Fei Zhang, Bo-Yu Feng, Chang-Hua Pei et al.· 0 citations
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
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, Shuo-Qiu 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, Jun-Jie Huang, Zhihan Jiang et al.· ACM Transactions on Software...· 0 citations
VulAgentRL is proposed, an agentic RL framework for interprocedural vulnerability detection built on a Code Property Graph (CPG), which outperforms state-of-the-art baselines, including frontier models, on the strict pair-wise-correct metric while issuing fewer tool calls, and its advantage persists on an out-of-distri...
Yi-Kun Li, Ting Zhang, Jia-Kun 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.
Yun-Fei Zhang, Bo-Yu 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.
