Agentic Post-Training
PulseAugur coverage of Agentic Post-Training — every cluster mentioning Agentic Post-Training across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
New APT framework automates text-to-image model post-training
Researchers have introduced APT (Agentic Post-Training), a novel, fully automated framework designed to enhance text-to-image models. This system adaptively refines models by using three coordinated agents that construc…
-
Wang Yunhe's startup releases NeoHorse, an Agent-Native model trained on execution experience
JiYuan LüDòng, a startup founded by former Huawei Noah's Ark Lab director Wang Yunhe, has released its first Agent-Native model, NeoHorse. This model, developed with support from Wuxin Qiong and research contributions f…
-
AI agents explore recursive self-improvement with new frameworks · 7 sources tracked
Researchers are exploring recursive self-improvement (RSI) in AI agents, a process where AI systems enhance their own capabilities and the methods for future improvement. New frameworks like Dream-RSI and RSIAgent lever…