Get started
Author

Leowei Liang

Observed name: Liang, Leowei
Observed institution: University of Pennsylvania
OpenAlex ID: A5140889669
Terminal-RSI: Recursive Self-Improving Terminal Agents via Recursive Self-Rewrite and Policy-Refine
2026 · Yang, Junyao, Li, Zongxia, et al. · arXiv (Cornell University)
PDF
Long-Horizon-Terminal-Bench 2.0: Automating Diverse Task Construction and Measuring Sustained Agent Progress
2026 · Li, Zongxia, Li, Zhongzhi, et al. · arXiv (Cornell University)
PDF
Self-Supervised Scaling of Terminal Environments for Scientific Domains
2026 · Li, Zhongzhi, Shi, Yucheng, et al. · arXiv (Cornell University)
PDF
T1: Terminal Agent Reinforcement Learning for Long-Horizon Tasks
2026 · Yang, Junyao, Shi, Yucheng, et al. · arXiv (Cornell University)
PDF
FlowBalance: Verifier-Grounded Self-Improvement from On-Policy Reasoning Experience
2026 · Huang, Zixun, Panaganti, Kishan, et al. · arXiv (Cornell University)
PDF
UI-Mate: Advancing Open-Weight Foundation GUI Agents with In-Context Demonstrations
2026 · Ding, Zihan, Dou, Longxu, et al. · arXiv (Cornell University)
PDF
Recursive Synthesis for Long-Horizon Terminal Tasks
2026 · Li, Zhongzhi, Shi, Yucheng, et al. · arXiv (Cornell University)
PDF
Stale but Stable: Staleness-Adaptive Trust Regions for Stabilizing Asynchronous Reinforcement Learning
2026 · Yang, Junyao, Shi, Yucheng, et al. · arXiv (Cornell University)
PDF
Long-Horizon-Terminal-Bench: Testing the Limits of Agents on Long-Horizon Terminal Tasks with Dense Reward-Based Grading
2026 · Li, Zongxia, Li, Zhongzhi, et al. · arXiv (Cornell University)
PDF
Works count: 9
Citation count:
H-index:
I10-index:
Year
Topic
Type