精选理由
Tmax把终端智能体的RL训练配方全开源了，65k token里就跑赢之前的工作，想自己训智能体的可以抄作业。
Hamish Ivison等人发布了Tmax，一个基于强化学习的开源终端智能体模型。在默认设置和65k token预算下，Tmax优于之前的开源终端使用工作。团队公开了所有训练数据、模型权重和rollouts，方便复现和进一步研究。
原文 · Suhail
This is a very good entry into post training LLMs with RL. The whole recipe and data is open. Highly...
This is a very good entry into post training LLMs with RL. The whole recipe and data is open. Highly recommend! Hamish Ivison @hamishivi Trained some terminal agents with friends! Introducing Tmax, open RL terminal agent models. Under default settings and shorter length (65k) token budgets, tmax outperforms prior open work on terminal use. We are releasing all data+weights+rollouts publically! 🔗 View Quoted Tweet 💬 3 🔄 9 ❤️ 126 👀 20702 📊 30 ⚡