90/30 Club Reading: Self-Evolving Curriculum for LLM Reasoning

​How should an LLM choose what to learn next? Join us to discuss Self-Evolving Curriculum for LLM Reasoning, which treats training-data selection as a multi-armed bandit problem, using signals from RL training to adapt the mix of problem types and difficulty levels as the model improves.

​We’ll unpack the method, examine its results across planning, puzzles, and mathematics, and discuss whether its learning-progress signal could help select tasks for more complex agent environments.

Paper link: https://arxiv.org/abs/2505.14970

​Event Schedule:

​7pm-8pm: Quiet reading time, grab a snack and read! (optional)

​8pm-9pm: Group discussion about the paper 📝

​9pm-10pm: We have our space for a bit longer, stay to socialize or network!

​Our event is hosted within Mox SF, the gracious donors of the space where we will meet.