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
4.12/100
超过 12.7%
全站排名 #56,203
发表论文5 篇
平均评分
年均产出2.5 篇/年
23
DoVer: Intervention-Driven Auto Debugging for LLM Multi-Agent Systems
ICLR 2026Poster
16
WarriorMath: Empowering Mathematical Reasoning for Large Language Models via Expert Battles
ICLR 2026Rejected
28
TestExplora: Can LLMs Write Tests to Find Potential Problems Existing in Repository?
ICLR 2026Rejected
通讯22
GUI-360° : A Comprehensive Dataset and Benchmark for Computer-Using Agents
ICLR 2026Rejected