Dan Klein

发表论文 8 篇 · 总被引 612 次 · h-index 2

代表论文

• Why Do Multi-Agent LLM Systems Fail? (2025 · Neural Information Processing Systems · 被引 596)
• GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning (2025 · arXiv.org · 被引 369)
• Composing Policy Gradients and Prompt Optimization for Language Model Programs (2025 · CAIS · 被引 4)
• Automatically Learning Skills for Coding Agents (2026 · CAIS · 被引 3)
• LangProBe: a Language Programs Benchmark (2025 · arXiv.org · 被引 3)
• optimize_anything: Unified Text Optimization can Outperform Specialized Systems (2026 · CAIS · 被引 2)