Papers5

#Mathematical Reasoning

Learn Hard Problems During RL with Reference Guided Fine-tuning

ReGFT is a simple pre-RL step that shows the model partial human hints, then makes it solve problems in its own words, creating correct, model-style solutions for hard questions.

#Reference-Guided Fine-Tuning#ReGFT#ReFT

iGRPO: Self-Feedback-Driven LLM Reasoning

Beginner

Ali Hatamizadeh, Shrimai Prabhumoye et al.Feb 9arXiv

This paper teaches a language model to improve its own math answers by first writing several drafts and then learning to beat its best draft.

#iGRPO#GRPO#Reinforcement Learning

Adaptive Ability Decomposing for Unlocking Large Reasoning Model Effective Reinforcement Learning

Intermediate

Zhipeng Chen, Xiaobo Qin et al.Jan 31arXiv

This paper teaches a model to make its own helpful hints (sub-questions) and then use those hints to learn better with reinforcement learning that checks answers automatically.

#RLVR#Large Reasoning Models#Sub-question Guidance

Your Group-Relative Advantage Is Biased

Intermediate

Fengkai Yang, Zherui Chen et al.Jan 13arXiv

Group-based reinforcement learning for reasoning (like GRPO) uses the group's average reward as a baseline, but that makes its 'advantage' estimates biased.

#Reinforcement Learning from Verifier Rewards#GRPO#GSPO

OPV: Outcome-based Process Verifier for Efficient Long Chain-of-Thought Verification

Intermediate

Zijian Wu, Lingkai Kong et al.Dec 11arXiv

Big AI models often write very long step-by-step solutions, but usual checkers either only check the final answer or get lost in the long steps.

#Outcome-based Process Verifier#Chain-of-Thought#Process Verification