Hierarchical Reinforcement Learning with Stable Temporal Abstraction for Language Model Agents

Excerpt

arXiv:2610.05473v1 Announce Type: new Abstract: Hierarchical reinforcement learning improves long-horizon control by organizing primitive actions around persistent subgoals and assigning credit at multiple temporal scales. Recent hierarchical language agents bring these benefits to interactive tasks by explicitly separating subgoal planning from action execution. We observe, however, that an explicit hierarchy does not by itself determine how stable the resulting temporal abstraction is: the lea