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
21.14/100
前 38.9%
全站排名 #25,020
发表论文5 篇
平均评分
年均产出5.0 篇/年
Xuesong Yao
22
AgentGym-RL: An Open-Source Framework to Train LLM Agents for Long-Horizon Decision Making via Multi-Turn RL
ICLR 2026Oral
17
Generalizable End-to-End Tool-Use RL with Synthetic CodeGym
ICLR 2026Poster
16
Scaling Long-Horizon Agent via Context Folding
ICLR 2026Rejected
19
Critique-RL: Training Language Models For Critiquing Through Two-Stage Reinforcement Learning
ICLR 2026Poster
10
Scaling LLM Multi-turn RL with End-to-end Summarization-based Context Management
ICLR 2026Withdrawn