NVIDIA AVO 在 ARC-AGI-3 上达到 100%，展示通用智能体架构
原标题：NVIDIA AVO Reaches 100% on ARC-AGI-3, Demonstrating a Frontier-Level General-Purpose Architecture for Long-Horizon Autonomous Agents
AI 摘要
NVIDIA 研究项目 AVO 在 ARC-AGI-3 基准测试中取得 100.00 分，完成全部 183 个关卡。AVO 是一种通用智能体架构，通过持久记忆和监督机制支持长时间自主运行，此前已在 GPU 内核优化中展现性能提升。该结果表明，智能体系统的整体架构对模型能力转化为实际进展至关重要。
正文节选
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, multistep tasks. The NVIDIA research project Agentic Variation Operators (AVO) addresses this challenge