2 papers
cs.AI2025
EnCompass: Enhancing Agent Programming with Search Over Program Execution Paths
Zhening Li, Armando Solar-Lezama, Yisong Yue +1
We introduce a new approach to agent programming, the development of LLM-based agents. Current approaches to agent programming often entangle two aspects of agent design: the core…
cs.LG2024
When Do Skills Help Reinforcement Learning? A Theoretical Analysis of Temporal Abstractions
Zhening Li, Gabriel Poesia, Armando Solar-Lezama
Skills are temporal abstractions that are intended to improve reinforcement learning (RL) performance through hierarchical RL. Despite our intuition about the properties of an envi…