Well as far as agentic training goes, this is still *very early*
2:12 AM · Jun 28, 2026 · 896 Views
Well as far as agentic training goes, this is still *very early*
No Digg Deeper questions have been answered for this story yet.
Some good pieces in the open now but still remote from a workable general agent (*cough* conversational multi-turn *cough*)
Well as far as agentic training goes, this is still *very early*
And I still think that generally people are asking too much of RL. Should only come once whole agentic system is modeled. Less about exploration and more about streamlining accuracy.
Some good pieces in the open now but still remote from a workable general agent (*cough* conversational multi-turn *cough*)