2 papers
cs.CL2026
It Takes Workflows to Evolve Better Workflows
Xuehang Guo, Haoyu Wang, Haifeng Chen +3
Tackling complex real-world tasks can exceed the capabilities of a single large language model (LLM), motivating the use of multi-agent workflows that coordinate specialized agents…
cs.RO2026
DexPolicy: Scheduled Exploration for Trajectory-Guided Dexterous Manipulation
Haoyu Wang, Siyuan Qian, Yanjun Li +4
Reinforcement learning (RL) for dexterous manipulation must discover finger-object contacts and then control the object precisely; the action noise that serves the first goal can i…