13 papers
XRepoSkill: Learning Transferable Skills for Software Engineering Agents
Yaoqi Guo, Haoyang Zhou, Jiayi Zhang +7
Software engineering agents increasingly use reusable skills distilled from prior experience to resolve repository-level issues, yet such skills often fail to transfer across repos…
Securing Code Understanding: Detecting Natural Backdoor Vulnerability in Code Language Models
Yuchen Chen, Weisong Sun, Haocheng Huang +11
Code Language Models (CodeLMs) have become integral to software engineering, significantly advancing code intelligence tasks. However, their widespread adoption has raised critical…
Bridging Requirements and Architecture: Multi-Agent Orchestration with External Knowledge and Hierarchical Memory
Ruiyin Li, Yiran Zhang, Xiyu Zhou +6
Software architecture design is a critical yet inherently complex and knowledge-intensive phase that requires balancing competing quality attributes and adapting to evolving requir…
CODESKILL: Learning Self-Evolving Skills for Coding Agents
Yanzhou Li, Yiran Zhang, Xiaoyu Zhang +2
Coding agents produce rich trajectories while solving software-engineering tasks. To enable agent self-evolution, these trajectories can be distilled into reusable procedural skill…
RealBench: A Repo-Level Code Generation Benchmark Aligned with Real-World Software Development Practices
Jia Li, Hongyi Deng, Yiran Zhang +9
Writing code requires significant time and effort in software development. To automate this process, researchers have made substantial progress using Large Language Models (LLMs) f…
Knowledge-Guided Multi-Agent Framework for Application-Level Software Code Generation
Qian Xiong, Bo Yang, Weisong Sun +4
Automated code generation driven by Large Lan- guage Models (LLMs) has enhanced development efficiency, yet generating complex application-level software code remains challenging.…
UserTrace: User-Level Requirements Generation and Traceability Recovery from Software Project Repositories
Dongming Jin, Zhi Jin, Yiran Zhang +5
Software maintainability critically depends on high-quality requirements descriptions and explicit traceability between requirements and code. Although automated code summarization…
Requirements Development and Formalization for Reliable Code Generation: A Multi-Agent Vision
Xu Lu, Weisong Sun, Yiran Zhang +4
Automated code generation has long been considered the holy grail of software engineering. The emergence of Large Language Models (LLMs) has catalyzed a revolutionary breakthrough…
From Context to Intent: Reasoning-Guided Function-Level Code Completion
Yanzhou Li, Tianlin Li, Yiran Zhang +4
The growing capabilities of Large Language Models (LLMs) have led to their widespread adoption for function completion within code repositories. Recent studies on such tasks show p…
MAAD: Automate Software Architecture Design through Knowledge-Driven Multi-Agent Collaboration
Ruiyin Li, Yiran Zhang, Xiyu Zhou +5
Software architecture design is a critical, yet inherently complex and knowledge-intensive phase of software development. It requires deep domain expertise, development experience,…
Knowledge-Based Multi-Agent Framework for Automated Software Architecture Design
Yiran Zhang, Ruiyin Li, Peng Liang +2
Architecture design is a critical step in software development. However, creating a high-quality architecture is often costly due to the significant need for human expertise and ma…
Commenting Higher-level Code Unit: Full Code, Reduced Code, or Hierarchical Code Summarization
Weisong Sun, Yiran Zhang, Jie Zhu +8
Commenting code is a crucial activity in software development, as it aids in facilitating future maintenance and updates. To enhance the efficiency of writing comments and reduce d…
Demonstration Attack against In-Context Learning for Code Intelligence
Yifei Ge, Weisong Sun, Yihang Lou +7
Recent advancements in large language models (LLMs) have revolutionized code intelligence by improving programming productivity and alleviating challenges faced by software develop…