Towards Self-Improvement of LLMs via MCTS: Leveraging Stepwise Knowledge with Curriculum Preference Learning Paper • 2410.06508 • Published 8 days ago • 9
DOTS: Learning to Reason Dynamically in LLMs via Optimal Reasoning Trajectories Search Paper • 2410.03864 • Published 12 days ago • 9
HDFlow: Enhancing LLM Complex Problem-Solving with Hybrid Thinking and Dynamic Workflows Paper • 2409.17433 • Published 21 days ago • 8