影响力指数
论文质量、代表作、近期表现、广度与样本量置信度综合计算
37.74/100
前 16.1%
全站排名 #10,386
发表论文5 篇
平均评分
年均产出1.7 篇/年
Andrew Zhao
研究方向
Language Agents · Reinforcement Learning
23
Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?
NeurIPS 2025Oral
20
Absolute Zero: Reinforced Self-play Reasoning with Zero Data
NeurIPS 2025Spotlight
一作26
Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning
NeurIPS 2025Poster