Skip to content
The day in AI
Fri 18 Apr 2025
Friday 18 April 2025
←
→
No written reading for this day yet. Here is everything that was logged.
Everything from this day
Research
18 Apr 2025
Tsinghua LeapLab / SJTU
Does RL Really Incentivize Reasoning Beyond the Base Model?
RLVR models win at pass@1 but base models win at large pass@k, suggesting RL sharpens existing ability rather than creating new reasoning paths.