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
2.7/100
超过 7.9%
全站排名 #59,318
发表论文4 篇
平均评分
年均产出4.0 篇/年
Brad Kenstler
12
ResearchRubrics: A Benchmark of Prompts and Rubrics For Evaluating Deep Research Agents
ICLR 2026Poster
10
Beyond Truthfulness: Evaluating Honesty in Large Language Models
ICLR 2026Rejected
18
SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?
ICLR 2026Rejected
通讯12
Imitation Learning for Multi-turn LM Agents via On-policy Expert Corrections
ICLR 2026Rejected