Joseph Gonzalez

发表论文 9 篇 · 总被引 436 次 · h-index 3

代表论文

• Why Do Multi-Agent LLM Systems Fail? (2025 · Neural Information Processing Systems · 被引 610)
• Measuring Agents in Production (2025 · arXiv.org · 被引 42)
• How to Train Your Advisor: Steering Black-Box LLMs with Advisor Models (2025 · arXiv.org · 被引 16)
• Continual Learning Bench: Evaluating Frontier AI Systems in Real-World Stateful Environments (2026 · arXiv.org · 被引 6)
• Learning, Fast and Slow: Towards LLMs That Adapt Continually (2026 · arXiv.org · 被引 3)
• Concurrency without Model Changes: Future-based Asynchronous Function Calling for LLMs (2026 · arXiv.org · 被引 2)