作者位次 #7/7ACL 2026Poster· Natural Language Processing
From Data-Centric to Sample-Centric: Enhancing LLM Reasoning via Progressive Optimization
Xinjie Chen · Minpeng Liao · Guoxin Chen · Chengxi Li · Biao Fu · Kai Fan · Xinggao Liu
摘要
Reinforcement learning with verifiable rewards (RLVR) has recently advanced the reasoning capabilities of large language models (LLMs). We investigate RLVR from a sample-centric perspective and introduce LPPO (Learning-Progress and Prefix-guided Optimization), a framework of progressive optimizat...