BookNavigator: RL Framework Lets LLMs Self-Learn from Textbooks

Shanghai AI Lab and collaborators introduced BookNavigator, an RL framework that lets LLMs autonomously retrieve, study, and apply knowledge from long textbooks, boosting proof accuracy from 51.5% to 79.5%.

2026-11-12 ~ 2026-11-13 · 2 related posts

• Shanghai AI Lab: RL self-learning lifts Intern-S2 proof accuracy from 51.5% to 79.5% — internlm · 2026-11-12
• RL framework teaches LLMs to self-learn from textbooks, lifting proof accuracy 51.5%→79.5% — _akhaliq · 2026-11-13