Paper recommend for Part 8

[YuxuanJiang1]

Hi, thank you for the great survey! We’d like to suggest our recent work as a relevant reference:
Title: DRP: Distilled Reasoning Pruning with Skill-aware Step Decomposition for Efficient Large Reasoning Models
Link: [arXiv link ]
Summary: DRP employs a teacher model to perform skill-aware step decomposition and content pruning, and distills the pruned reasoning paths into a student model for efficient reasoning.

We believe this work may complement the topics discussed in your survey. Thank you for considering it!

[weiyifan1023]

Thanks for your amazing work! I reached out to introduce a new paper regarding Part 4: MCTS/Tree Search:
Structural Entropy Guided Agent for Detecting and Repairing Knowledge Deficiencies in LLMs (https://arxiv.org/pdf/2505.07184)

Summary: Senator employs the Structure Entropy (SE) metric to quantify uncertainty along knowledge graph paths and leverages Monte Carlo Tree Search (MCTS) to selectively explore regions where the model lacks domain-specific knowledge.