hierarchical skills 1multimodal agents 1policy co-evolution 1reinforcement learning 1skill learning 1
From the 1 of 2 linked papers with an AI index.
2 papers
cs.CL2026
SPyCE: Skill-Policy Co-evolution for Multimodal Agents
Ru Zhang, Weijie Qiu
The paper introduces SPyCE, a framework that jointly learns a hierarchical skill library and a policy for multimodal agents, allowing skills distilled from visual reasoning traject…
cs.LG2026
DEvo: Dual Difficulty-Aware Self-Evolution for Data-Efficient Reinforcement Learning
Ru Zhang, Renda Li, Ziyu Ma +4
Reinforcement learning (RL) has demonstrated potential for enhancing reasoning in large language models (LLMs). However, effective RL training, which requires medium-difficulty tra…