NVIDIA AVO 在 ARC-AGI-3 上达到 100%，展示面向长时程自主智能体的前沿级通用架构
NVIDIA AVO Reaches 100% on ARC-AGI-3, Demonstrating a Frontier-Level General-Purpose Architecture for Long-Horizon Autonomous Agents
NVIDIA 的 AVO 在 ARC-AGI-3 上取得 100% 成绩，展示了一种面向长时程自主智能体的前沿级通用架构。该工作指出前沿语言模型只是 AI 智能体的一部分，外围的 agent harness 才决定模型如何接收上下文、调用工具、维护状态、响应反馈、从失败中恢复并在长任务中持续推进。
A frontier language model is only one component of an AI agent. The surrounding agent system—often called a harness—determines how the model receives...
A frontier language model is only one component of an AI agent. The surrounding agent system—often called a harness—determines how the model receives context, uses tools, maintains state, responds to feedback, recovers from failure, and sustains progress over long-running tasks. The challenge is how to build the agent architecture that makes frontier language models work reliably on extended…
来源：NVIDIA Developer Blog · developer.nvidia.com