Matei A. Zaharia

发表论文 43 篇 · 总被引 1845 次 · h-index 15

代表论文

• Why Do Multi-Agent LLM Systems Fail? (2025 · Neural Information Processing Systems · 被引 610)
• Reasoning Models Can Be Effective Without Thinking (2025 · arXiv.org · 被引 195)
• LLMs Can Easily Learn to Reason from Demonstrations Structure, not content, is what matters! (2025 · arXiv.org · 被引 139)
• Are More LLM Calls All You Need? Towards the Scaling Properties of Compound AI Systems (2024 · Neural Information Processing Systems · 被引 105)
• Establishing Best Practices for Building Rigorous Agentic Benchmarks (2025 · arXiv.org · 被引 89)
• Barbarians at the Gate: How AI is Upending Systems Research (2025 · arXiv.org · 被引 57)