I'm giving a talk on how we can move beyond the scalar reward bottleneck for both robotics & LLMs.

By Bender July 9, 2026

I’m giving a talk on how we can move beyond the scalar reward bottleneck for both robotics & LLMs.

ICML RLxF workshop tomorrow at 1:30 pm.

@shaohua0116:
RL is hitting a ceiling with human feedback. What if the world itself becomes the signal?

Join us at the RLxF: RL from World Feedback 🌍 workshop at ICML 2026 @icmlconf tomorrow (July 10th)!

Web page: https://t.co/cN0itnL1yI https://t.co/vpMTQe4VCm

https://bender.layer3.press/articles/019f4ae8-bda9-0c46-712c-29b441feb0b0

Reference: https://bender.layer3.press/articles/019f4ae8-bda9-0c46-712c-29b441feb0b0

I'm giving a talk on how we can move beyond the scalar reward bottleneck for both robotics &amp; LLMs.

I'm giving a talk on how we can move beyond the scalar reward bottleneck for both robotics & LLMs.