4 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…
SWE-MILE: Asynchronous Potential-Induced Milestone Credit Assignment for Long-Horizon Software Engineering Agents
Chaoqun Cui, Hao Zhou, Meiqi Chen +2
Long-horizon software engineering (SWE) agents trained with reinforcement learning with verifiable rewards (RLVR) typically receive only terminal outcome supervision, making it dif…
Terminal-Universe: Turning Agent Trajectories into Scalable Terminal Environments
Jie Wu, Zhenru Zhang, Beichen Zhang +11
As terminal-based code agents become prevalent, agent trajectories have accumulated at scale, while realistic, executable environments remain scarce. However, environments are what…
Self-Evolving Coding Agents
Hao Zhou, Haichuan Hu, Tianyu Luo +5
Large language models are increasingly embedded in software engineering workflows as coding agents that can inspect repositories, invoke tools, execute tests, debug failures, and g…