普林斯顿与 Google 论文：4B 决策模型分担智能体工具选择，成本降 81.1% 至 89.0%
New Princeton Univ + Google paper finds that the decision model most accurate on isolated questions solved only 69.5% of agent tasks, while a 4B model trained
普林斯顿大学与 Google 的新论文发现，在孤立问题上最准确的决策模型只解决了 69.5% 的智能体任务，而在智能体状态上训练的 4B 模型解决了 91.5%。其 harness 把每一步的工具选择交给快速决策模型，只有置信度超过在智能体自身运行上拟合的阈值时才采用其答案，并用智能体实际到达的状态（包括犯错之后的状态）训练了 AgentDecision-4B。在类似训练数据的任务上，这类 4B 模型让智能体成本降低 81.1% 至 89.0%、速度最高提升 2.5x，成功率差距在 3 个百分点以内；若不加阈值把所有工具选择都交出去，成功率下降 19.0 个百分点。论文地址为 arxiv.org/abs/2610.21412。
推荐理由
AI 评分 56
论文给出用小模型分担智能体工具选择的具体做法，以及置信阈值对成功率的影响数据。
主题
正文
New Princeton Univ + Google paper finds that the decision model most accurate on isolated questions solved only 69.5% of agent tasks, while a 4B model trained on agent states solved 91.5%.
Agent harnesses call a big LLM at every step, which makes long tasks slow and costly. Yet most of those calls just pick from a list, like which tool to use next.
Their harness asks a fast decision model each multiple-choice question and uses its answer only above a confidence threshold fitted on the agent's own runs. They also trained AgentDecision-4B on states the agent actually reaches, including after its own mistakes.
On tasks like their training data, 4B models trained this way made agents 81.1% to 89.0% cheaper and up to 2.5x faster. Success stayed within 3 points, while handing over every tool choice with no threshold lowered success by 19.0 points.
To hand routine agent choices to a small model, train it and set its confidence threshold on your agent's own runs.
– arxiv. org/abs/2610.21412