3 papers
cs.AI2026
ASH: Agents that Self-Hone via Embodied Learning
Benjamin Schneider, Xavier Schneider, Victor Zhong +1
Long-horizon embodied tasks remain a fundamental challenge in AI, as current methods rely on hand-engineered rewards or action-labeled demonstrations, neither of which scales. We i…
cs.AI2026
Atomic Skills are the Prerequisite: When Reinforcement Learning Synthesizes Compositional Reasoning, and When It Only Amplifies
Sitao Cheng, Xunjian Yin, Ruiwen Zhou +5
Does Reinforcement Learning (RL) merely amplify existing skills, or synthesize novel skills? We investigate this question through the lens of Complementary Reasoning: the critical…
cs.AI2025
How well can LLMs provide planning feedback in grounded environments?
Yuxuan Li, Victor Zhong
Learning to plan in grounded environments typically requires carefully designed reward functions or high-quality annotated demonstrations. Recent works show that pretrained foundat…