Real-world software engineering rarely consists of isolated changes. Features, migrations, and systematic fixes often unfold across multiple pull requests (PRs), requiring coordinated modifications across a repository. Yet most executable repository-level benchmarks retain a single issue or PR as the task unit, while e...
Wei-Hao Li, Zi-Hang Xu, Zhong-Qiu Wang et al.· 0 citations
Reliable repository-level coding requires agents not only to generate correct code but also to preserve constraints and respond to tool feedback across long interactions. However, our diagnostic analysis shows that agents often fail to act on relevant information already available in context, while final Pass/Fail outc...
Yu-Jia Luo, Zhi-Yi Lai, Zi-Qi Miao et al.· 0 citations
SWE-Nexus enables task construction from validated behavior beyond individual historical changes, a fully automated pipeline that constructs repository-level implementation tasks from test execution from test execution.
Song-Wei Yu, Zi-Qi Miao, Jing-Xuan Xu et al.· 0 citations
TailSieve, a partial-rollout-guided framework that jointly controls tail routing and replica allocation for LLM rollouts, and shows that makespan-optimal routing in the long-tail regime combines tail isolation with load balancing, and that a simple top-k policy closely approximates this offline optimum.
Tianqi Xu, Lu Lv, Hao-Yang Huang et al.· 3 citations· ⚡1
We present KAT-Coder-V2.5, a coding-focused agentic model trained to act autonomously inside real, executable repositories rather than as a single-turn code generator. Its capability is bottlenecked less by model scale than by the scarcity of reproducible environments, verifiable rewards, and high-value trajectories, w...
Bofeng Huang, Fengxiang Li, Hao Xu et al.· 2 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
