Apodex 1.1：以可验证工作成果为单位的AI Agent训练
Most AI agents are still judged by the answer they return.
Agent 评测范式的重要转变，从关注单点回答转向全流程工作流与可验证产出，对构建复杂 Agent 有直接参考价值。
Most AI agents are still judged by the answer they return.
大多数 AI 智能体仍以其返回的答案来评判。
Apodex 1.1 from @Apodex_AI is training for something harder: whether the model can take over the entire job, keep a real workspace alive across 100s of steps, recover when parts fail, and deliver artifacts that can actually be verified.
@Apodex_AI 的 Apodex 1.1 正在训练更艰巨的目标：模型能否接管整个工作，在数百个步骤中维持真实工作空间的运行，在部分环节失败时恢复，并交付可实际验证的成果。
Apodex 1.1 is built around a different unit of AI capability: completed, checkable work, rather than a polished answer.
Apodex 1.1 围绕不同的 AI 能力单元构建：已完成且可核查的工作，而非精美的答案。
A task can start with raw files, datasets, spreadsheets, papers, images, or code. The system can inspect them, choose a method, run code, keep task state, recover from failures, and produce outputs that can be checked.
任务可以始于原始文件、数据集、电子表格、论文、图片或代码。系统可以检查这些内容，选择方法，运行代码，保持任务状态，从失败中恢复，并生成可被核查的输出。
Underneath that are 2 scaling paths. Environment Scaling expands the executable file, search, and code situations the model learns from. Agentic Coordination Scaling trains it to split long tasks across agents, bring partial results back into shared state, and revise the plan when evidence changes.
其底层有两条扩展路径。环境扩展（Environment Scaling）扩大了模型从中学习的可执行文件、搜索和代码情境。智能体协调扩展（Agentic Coordination Scaling）训练它将长任务拆分给多个智能体，将部分结果带回共享状态，并在证据变化时修订计划。
AgentOS keeps files, tool state, artifacts, dependencies, and coordination state persistent across that work. Subagents can return useful results before every branch finishes, so the main agent can redirect unfinished work without discarding progress that is still valid.
AgentOS 使文件、工具状态、成果、依赖项和协调状态在该工作过程中保持持久。子智能体可以在每个分支完成之前返回有用结果，因此主智能体可以重定向未完成的工作，而不会丢弃仍然有效的进展。
Officially published results place Apodex 1.1 with Agent Team in the leading performance band across professional work, finance, science, reasoning, and search.
官方发布的结果显示，Apodex 1.1 配合 Agent Team 在专业工作、金融、科学、推理和搜索领域均处于领先性能区间。
🧵 1.
🧵 1.
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