跳到正文
@AravSrinivas· @AravSrinivas · X·· 2026-08-25AI 评分36
AI 导读

本地模型距离前沿仍相当远,无法完全摆脱对前沿模型的依赖。通过顾问升级到云端前沿模型的方式解决了这一问题,实现了混合式智能体推理系统。在 Terminal Bench 2.1 上,升级将得分从 59.6% 提升至 73.0%,每次 rollout 成本为 $0.415,以三分之二的成本弥补了约五分之三的前沿差距。

正文

Local models are still quite far from the frontier for complete zero dependence on the frontier. The advisor escalation to a cloud-based frontier model approach addresses this issue, allowing for a hybrid agentic inference system. On Terminal Bench 2.1, escalation lifts the score from 59.6% to 73.0% at $0.415 per rollout, recovering about three-fifths of the frontier gap at two-thirds of the cost.

来源:@AravSrinivas · x.com