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
Results distinguish functional success from constraint compliance, with failures concentrated in workflow ordering, tool-use discipline, and reporting, and substantial interactions between models and scaffolds.
Wen-Ya Zhu, Xin-Ping Lei, Zhi-Yi Lai et al.· 0 citations
Simulation-ready 3D assets are central to robotics and embodied AI. Generating them from a single image is usually framed as a vision-language model that emits a serialized asset for a decoder to turn into geometry and physical fields, leaving the image-to-3D reasoning implicit. We argue the limiting factor is this out...
Jie Huang, Xiao-He Li, Jiahao Li et al.· 0 citations
Lingjing provides a unified testbed that enables reproducible end-to-end evaluation and systematic failure diagnosis in urban multi-agent embodied intelligence and exposes shared physical and structured urban state to agents.
Xiaohe Li, Yi-Ru Wang, Junhao Fan et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.