开源 4B 决策模型 AgentDecision-4B 让智能体成本降 81.1%-89.0%
教你怎么把 4B 小模型塞进 agent 框架里替 LLM 做常规决策，成本砍掉八成还更快，做 agent 的都该看看。
一篇新论文把 Jev 这类决策模型集成进智能体框架，发布了 JevAgentHarness。该框架将常规决策路由给蒸馏的 AgentDecision-4B，只在置信度超过按智能体自身轨迹拟合的阈值时才采用其结果。使用拟合阈值后，工具与参数级联在 500 个任务结果完全不变的情况下降低 14.2% 成本，而固定阈值 0.5 会损失 21.5 分。在不同于训练数据的任务上，使用该 4B 模型的智能体解决率达 91.5%，高于直接用 Jev 的 82.0%；在熟悉任务上成本降低 81.1%-89.0%，速度提升最高 2.5 倍，成功率差距保持在 3 分以内。
Must-read paper integrating decision models like Jev into harnesses.
They distilled an open 4B decision model, mostly from Jev's answers on the agent's own states, that beats Jev inside that agent and is much cheaper to run.
Their harness, JevAgentHarness, sends each routine choice to the decision model and uses its answer only when the confidence clears a threshold fitted on the agent's own trajectories. Below the threshold, the LLM decides as usual. With the fitted threshold, tool and argument cascades cut cost by 14.2% without changing the outcome of any of 500 tasks. A fixed threshold of 0.5 lost 21.5 points.
They also train AgentDecision-4B on states the agent reaches after its own mistakes, with Jev's answers as labels. On tasks unlike its training data, the agent solved 91.5% with it and 82.0% with Jev. On familiar tasks, 4B models trained this way made agents 81.1 to 89.0% cheaper and up to 2.5 times faster while staying within 3 points of success.
Paper: https://t.co/WQ5tyTlh5K
