1
A-Evolve-Training: Autonomous Post-Training of a 30B Model
没有人类干预，AI自己迭代训练自己：30B模型在多轮自主后训练中完成调优，展示大模型自动进化新范式。
arXiv:2606.20657v1 Announce Type: new Abstract: Post-training a frontier model is normally weeks of human work: proposing data and recipe changes, lau…