9 papers
SWE-Nexus: Automated Composition of Software Engineering Tasks from Test Execution
Songwei Yu, Ziqi Miao, Jingxuan Xu +10
Historical code changes provide convenient task boundaries, but do not identify which production functions selected tests exercise or support composing validated behaviors beyond a…
ANCHOR: Assessing Naturalistic Constraint Hierarchies and Ordering in Repository-Grounded Agentic Coding
Wenqiang Zhu, Xinping Lei, Zhiyi Lai +17
For repository-grounded coding agents, a functionally correct patch is not necessarily an acceptable one: developers also constrain how the task must be carried out-modification sc…
FLARE: A Full-Lifecycle Dense Supervision Paradigm for Long-Horizon Coding Agents via Generative Reward Model
Jingxuan Xu, Gang Wu, Yanan Wu +13
While test-time scaling enhances Large Language Model (LLM) agents in long-horizon software engineering (SWE), sparse binary rewards (Pass/Fail) create a severe credit assignment c…
EGSS: Entropy-guided Stepwise Scaling for Reliable Software Engineering
Chenhui Mao, Yuanting Lei, Zhixiang Wei +6
Agentic Test-Time Scaling (TTS) has delivered state-of-the-art (SOTA) performance on complex software engineering tasks such as code generation and bug fixing. However, its practic…
SVRepair: Structured Visual Reasoning for Automated Program Repair
Jincheng Wang, Liwei Luo, Xiaoxuan Tang +5
Large language models (LLMs) have recently been applied to Automated Program Repair (APR), yet most existing approaches remain unimodal and fail to use diagnostic signals contained…
Learning Adaptive Parallel Execution for Efficient Code Localization
Ke Xu, Siyang Xiao, Ming Liang +6
Code localization constitutes a key bottleneck in automated software development pipelines. While concurrent tool execution can enhance discovery speed, current agents demonstrate…
CRAFT-GUI: Curriculum-Reinforced Agent For GUI Tasks
Songqin Nong, Xiaoxuan Tang, Jingxuan Xu +4
As autonomous agents become adept at understanding and interacting with graphical user interface (GUI) environments, a new era of automated task execution is emerging. Recent studi…
Agent That Debugs: Dynamic State-Guided Vulnerability Repair
Zhengyao Liu, Yunlong Ma, Jingxuan Xu +4
In recent years, more vulnerabilities have been discovered every day, while manual vulnerability repair requires specialized knowledge and is time-consuming. As a result, many dete…
Transferable and Principled Efficiency for Open-Vocabulary Segmentation
Jingxuan Xu, Wuyang Chen, Yao Zhao +1
Recent success of pre-trained foundation vision-language models makes Open-Vocabulary Segmentation (OVS) possible. Despite the promising performance, this approach introduces heavy…