36 papers
LongRCA Bench: Diagnosing Responsible Roles and Root Causes in Long-Horizon Agent Failures
Yunfei Zhang, Boyu Feng, Changhua Pei +14
When a long-horizon agent execution fails, outcome-level evaluation reveals the unsuccessful result but not where the decisive error entered the trajectory. Developers must then in…
Does It Render Everywhere? A Study of Cross-Environment Compatibility in MLLM-Generated Webpages
Ziyun Guo, Jingyu Xiao, Yuqiang Sun +1
Multimodal Large Language Models (MLLMs) have been increasingly adopted to automate webpage generation from visual designs (e.g., screenshots). However, existing evaluations are li…
CodeShrink: Adaptive Visual Compression for Efficient Multimodal Code Understanding
Wenxin Tang, Jingyu Xiao, Zhenyu Liu +6
Rendering source code as images offers a promising way to reduce the input costs of Multimodal Large Language Models (MLLMs). Adjusting image resolution can trade visual token cost…
Graph Is the Verifier: Agentic Reinforcement Learning for Interprocedural Vulnerability Detection
Yikun Li, Ting Zhang, Jiakun Liu +9
The paper presents VulAgentRL, an agentic reinforcement learning framework that leverages code property graphs to collect interprocedural evidence and verify its own reasoning for…
VisualRepair: Dynamic Tool Calling and Region Focusing for Visual Software Issue Repair
Jingyu Xiao, Zhongyi Zhang, Haoran Hou +4
VisualRepair is a multimodal LLM framework that classifies bug‑related images, dynamically calls specialized tools, and focuses on relevant screenshot regions to improve automated…
TrajAudit: Automated Failure Diagnosis for Agentic Coding Systems
Minxing Wang, Xiaofei Xie, Yintong Huo
Agentic systems have been widely studied to automate coding tasks such as bug fixing and feature implementation. As these systems increasingly operate on complex codebases, underst…