ResearchTrend.AI
How Much Backtracking is Enough? Exploring the Interplay of SFT and RL in Enhancing LLM Reasoning

How Much Backtracking is Enough? Exploring the Interplay of SFT and RL in Enhancing LLM Reasoning

Hongyi Cai
Junlin Wang
Xiaoyin Chen
Bhuwan Dhingra
    LRM
ArXiv (abs)PDFHTML

Papers citing "How Much Backtracking is Enough? Exploring the Interplay of SFT and RL in Enhancing LLM Reasoning"

Title
No papers