Ruida Zhou

[Yuanxin Liu @Yuanxin02]

Think about how you actually solve a hard problem. You don't get it in one shot. You take an attempt, look at the feedback, and revise. Again and again.

That's how LLMs are deployed too: wrapped in a harness (revision, tree search, evolution) that loops.

So why do we still train them for a single shot? We built REVES to fix that. [1/8]

[Ruida Zhou @ZhouRuida]

Check out HiPER: Leveraging the hierarchical nature in the agentic tasks via hierarchical RL (particular a Hierarchical Advantage Estimation) achieves sota ALFWorld and WebShop. Simple to implement and good performance gain.

[Jiangweizhi Peng @jonp_07]

1/ LLM agents still struggle with long-horizon tasks.
Why?
Because today's RL algorithms treat agent behavior as a flat sequence of actions, while humans solve problems hierarchically: we plan, pursue subgoals, and adapt when plans change.
Our new work, HiPER (accepted at ICML 2026 🎉), brings this hierarchical structure directly into RL training.