Prime Agent 技术报告:记忆层级让 Opus 5 在
Prime Agent, the harness that put Opus 5 at 95.5% on ARC-AGI-3, now has a techni…
Prime Agent, the harness that put Opus 5 at 95.5% on ARC-AGI-3, now has a technical report.
Prime Agent,这个让 Opus 5 在 ARC-AGI-3 上达到 95.5% 成绩的框架,现在有了技术报告。
The mechanism is a memory hierarchy. Model weights and active context sit underneath a persistent IPython session and a disk-backed store of histories, skills and prompts, and the model moves state between those levels with code instead of having it compacted away.
其机制是一种记忆层级。模型权重和活动上下文位于一个持久的 IPython 会话和磁盘存储的历史、技能和提示库之下,模型通过代码在这些层级之间移动状态,而不是将其压缩掉。
Long inputs stay in the REPL as variables the agent can search and transform, so long-context work becomes an information-management problem rather than a reading problem.
长输入作为变量保留在 REPL 中,代理可以搜索和转换它们,因此长上下文工作变成了信息管理问题,而非阅读问题。
– arxiv. org/abs/2608.23552
– arxiv.org/abs/2608.23552
Title: "Prime Agent: A Self-Improving RLM Harness"
标题:“Prime Agent:一种自我改进的 RLM 框架”
更进一步:量化金融体系
看懂新闻只是起点——沿量化金融路径,把它变成能交付的工程能力