2 papers
cs.AI2026
Recursive Harness Self-Improvement for Frontier Reasoning Data Synthesis
Wenlong Zhang, Zhengbo Jiao, Chenxu Zhang +5
Generating progressively harder reasoning problems requires synthesis procedures that adapt as the task distribution evolves. Existing task-level recursion reuses generated problem…
cs.AI2026
CUA-Sandbox: Efficient Environments for Computer-Use Agent Reinforcement Learning
Xin Yan, Zhengbo Jiao, Jiaqi Liu +11
Reinforcement learning enables computer-use agents to improve through interaction with real software environments, including websites and desktop applications. However, conventiona…