HERAKLES: Hierarchical Skill Compilation for Open-ended LLM Agents

arXiv:2508.14751v2 Announce Type: replace Abstract: We study goal-conditioned reinforcement learning in partially observable environments with sparse rewards and large, structured goal spaces. In such settings, complex goals often require composing simpler skills, but learning these compositions efficiently remains challenging. This difficulty is particularly relevant in open-ended exploration settings, where agents are exposed to increasingly complex goals over time and must continuously expand and reorganize their skill repertoire. We assume the goal space admits prerequisite relations, enabling latent decomposition of tasks into subgoals, and leverage language to represent and reason over these goals. To exploit this structure, we propose HERAKLES, a hierarchical agent that jointly learns a high-level LLM policy and a low-level controller. The high-level policy selects subgoals among those the low-level can reliably achieve, while the low-level executes them and progressively compiles successful behaviors into reusable skills. Both policies are trained concurrently: the high-level guides exploration and structures behavior, while the low-level distills trajectories into efficient goal-conditioned skills. As training progresses, more goals become directly executable, enabling scalable skill composition. This results in a hybrid system combining planning and execution, improving efficiency and adaptation in open-ended, compositional environments.

Abstract:We study goal-conditioned reinforcement learning in partially observable environments with sparse rewards and large, structured goal spaces. In such settings, complex goals often require composing simpler skills, but learning these compositions efficiently remains challenging. This difficulty is particularly relevant in open-ended exploration settings, where agents are exposed to increasingly complex goals over time and must continuously expand and reorganize their skill repertoire. We assume the goal space admits prerequisite relations, enabling latent decomposition of tasks into subgoals, and leverage language to represent and reason over these goals. To exploit this structure, we propose HERAKLES, a hierarchical agent that jointly learns a high-level LLM policy and a low-level controller. The high-level policy selects subgoals among those the low-level can reliably achieve, while the low-level executes them and progressively compiles successful behaviors into reusable skills. Both policies are trained concurrently: the high-level guides exploration and structures behavior, while the low-level distills trajectories into efficient goal-conditioned skills. As training progresses, more goals become directly executable, enabling scalable skill composition. This results in a hybrid system combining planning and execution, improving efficiency and adaptation in open-ended, compositional environments.

Machine Learning (cs.LG)

arXiv:2508.14751 [cs.LG]

(or arXiv:2508.14751v2 [cs.LG] for this version)

https://doi.org/10.48550/arXiv.2508.14751 Focus to learn more arXiv-issued DOI via DataCite

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

aiqbench analysis

HERAKLES: Hierarchical Skill Compilation for Open-ended LLM Agents

Related coverage