Overmind开源Agent工作微调平台,幻觉率降低28倍
Overmind has open-sourced its platform for training smaller models on the work y…
Agent落地痛点在于幻觉与通用能力不足,Overmind提供了一套基于真实工作流数据微调开源模型的完整方案,实测效果显著,值得Agent开发者参考其数据闭环思路。
Overmind has open-sourced its platform for training smaller models on the work your agents actually do.
Overmind 已将其用于在代理实际执行的工作上训练较小模型的平台开源。
In its own test of 4,000+ questions across 100+ contracts, Overmind reports that its trained model invented quotes on 0.12% of questions, compared with 3.36% for the frontier model it tested. That's a 28x lower rate.
在其针对 100 多份合同中的 4,000 多个问题的自行测试中,Overmind 报告称其训练的模型仅在 0.12% 的问题中生成了引用,而它测试的前沿模型的这一比例为 3.36%。错误率降低了 28 倍。
It uses records of your agents' real work to build training data and evals, then fine-tunes open models. For an agent pulling clauses out of contracts all day, training a model for that specific job makes sense.
它使用代理真实工作的记录来构建训练数据和评估集,然后对开源模型进行微调。对于一个整天从合同中提取条款的代理来说,为其特定任务训练一个模型是合理的。
I'm a big fan of open source, so its cool that they released the code. You keep the trained model's weights and can run the platform yourself.
我是开源的忠实粉丝,所以它们发布了代码确实很酷。你可以保留训练好的模型权重,并自行运行该平台。
Code: https://github.com/overmind-core/overmind
代码:https://github.com/overmind-core/overmind
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