长时程智能体可靠性未随模型提升而到来
Long-horizon agent reliability has not arrived yet with better models.
Long-horizon agent reliability has not arrived yet with better models.
长时程智能体的可靠性并未随模型改进而实现。
On WeaveBench's 114 hybrid GUI-CLI tasks, the best officially reported pass rate is 41.2%.
在WeaveBench的114项混合GUI-CLI任务中，官方报告的最佳通过率为41.2%。
Current models can handle local steps, but need explicit audited state to keep the full task on track.
当前模型能处理局部步骤，但需明确审计的状态来保持整个任务不偏离轨道。
Long-horizon agents can solve individual steps and still fail because history becomes unreliable about what is finished, what failed, and what remains.
长时程智能体能解决单个步骤，但仍可能失败，因为历史记录对已完成、失败及剩余任务变得不可靠。
LongHorizon-Harness treats this as a task-state problem.
LongHorizon-Harness将此视为任务状态问题。
this paper argues that reliability over that span depends as much on the harness around the model as on the model itself.
本文认为，在该跨度上的可靠性既取决于模型本身，也取决于围绕模型的框架。
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