Metis
“By replacing redundant exploration with directed optimization, Metis reduces token costs by an average of 8.2x and up to 11.4x.”
The authors, in the abstract
Learning to Jailbreak LLMs via Self-Evolving Metacognitive Policy Optimization
AI Research Radar
Thursday, May 14: 1 frontier paper out of 256 read.
Frontier
Papers rated as moving the field
How we chooseThis week in research
May 8–14: 64 cleared, 4 frontier
The week’s papers have not been sorted into fields yet.
Models under test
Papers this week that name the model
Labs publishing
Papers this week with an author at the lab
Also cleared
1 paper