https://www.mercor.com/blog/training-frontier-knowledge-work-agents-a-397b-rl-tr…
0 viewsОткрыть в Telegram →
Из этого канала
- #7029Всем привет! GPT6 расскатали?
Всем привет! GPT6 расскатали?
- #7030Да, так еще и лимиты на Клод сбросили
Да, так еще и лимиты на Клод сбросили
- #7031Rethinking On-Policy Distillation of Large Language Models II: One Training…
Rethinking On-Policy Distillation of Large Language Models II: One Training Example https://arxiv.org/abs/2609.04172 https://www.alphaxiv.org/ru/abs/2609.04172
- #7026Terminal-Universe: Turning Agent Trajectories into Scalable Terminal…
Terminal-Universe: Turning Agent Trajectories into Scalable Terminal Environments https://arxiv.org/abs/2609.04148 https://www.alphaxiv.org/ru/abs/2609.04148
- #7025Training Agents to Evolve with Their Harness: TaoLive Digital Avatar Agent…
Training Agents to Evolve with Their Harness: TaoLive Digital Avatar Agent Technical Report https://arxiv.org/abs/2608.15763…