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
11.86/100
超过 36.6%
全站排名 #40,797
发表论文3 篇
平均评分
年均产出3.0 篇/年
10
Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces
ICLR 2026Poster
17
HARDTESTGEN: A High-Quality RL Verifier Generation Pipeline for LLM Algorithimic Coding
ICLR 2026Poster
5
HexMachina: Self-Evolving Multi-Agent System for Continual Learning of Catan
ICLR 2026Withdrawn