1 citations · 1 across the 5 of their papers we have counts for
4 papers · 1 filter
X-Tree: Tokenizing Reusable Experience for Efficient Agent Generalization
Sitao Cheng, Xunjian Yin, Zhiyuan Sun +4
Multi-step agents are trained on flat action streams: SFT and RLVR weight every token uniformly and ignore the sub-procedures that recur across tasks, the hierarchy that lets human…
ASH: Agents that Self-Hone in Long-Horizon Worlds
Benjamin Schneider, Xavier Schneider, Victor Zhong +1
Long-horizon visuomotor tasks remain a fundamental challenge in AI, as current methods rely on hand-engineered rewards or action-labeled demonstrations, neither of which scales. We…
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…
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…