Ludwig Schmidt

发表论文 5 篇 · 总被引 358 次 · h-index 3

代表论文

• Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces (2026 · arXiv.org · 被引 352)
• SWE-smith: Scaling Data for Software Engineering Agents (2025 · Neural Information Processing Systems · 被引 220)
• Humans are Missing from AI Coding Agent Research (2026 · 被引 10)
• CodeClash: Benchmarking Goal-Oriented Software Engineering (2025 · arXiv.org · 被引 5)
• Dynamic Summarization Length Control via Model Merging