让贵AI干一半就下班，便宜AI接手，省65%成本
现在跑一个多步骤的AI任务，比如让智能体自己查资料、做计划、执行，通常全程都用最贵最强的模型，因为便宜模型一接手就容易出错。这篇论文发现一个反直觉的点：不是让便宜模型先干、贵模型收尾，而是反过来——让贵模型先干到任务中段，再交给便宜模型收尾，准确率几乎不掉，甚至还能涨，成本却省了65.9%。研究者据此做了个轻量检测器，专门判断“该交接了”这个时机，在11组模型搭配和两个基准测试上都验证了效果。它不是你明天就能装进自己工具链的东西，但如果你在跑长流程AI任务、被API账单吓到过，这个“先贵后便宜、一次交接就够”的思路，值得记下来。
📄 原文摘要(英文)
Solving long-horizon agentic tasks requires language agents to interact with their environments over multiple steps, and reliable performance often comes from the expensive capable models available through cloud providers. Meanwhile, alternative efficient models with inferior performance but a much lower cost are emerging, including lower-tier cloud models and smaller open-weights models deployable on local hardware. This raises a natural question that remains less explored than traditional query-level routing: can capable and efficient models collaborate within a single long-horizon agentic task to substantially reduce cost while preserving task accuracy? In this paper, we systematically investigate key design choices for such collaboration through model handoffs, where one model takes over from another, focusing on handoff direction and context transfer. We find that efficient-to-capable handoffs generally underperform capable-only execution with limited or even no cost reduction, whereas capable-to-efficient handoffs at suitable stages of task progress largely preserve or even improve accuracy while substantially reducing cost. These findings suggest that a one-time, simple, well-timed handoff strategy is good enough for cost-effective agent collaboration, motivating AgentBaton, a lightweight detector that learns when to hand off from recurring patterns in task progress. Across 11 model pairs and two representative benchmarks, AgentBaton reduces API costs by 65.9% on average while largely preserving task accuracy, with accuracy gains of up to 8.8 percentage points over capable-only execution. Experiments across various reasoning-effort settings further show that AgentBaton extends the empirical accuracy-cost Pareto frontier.