SOURCE-LINKED INTELLIGENCE

From LLM-Generated Specifications to Learned Quadruped Locomotion

arXiv · AI, language, vision and robotics · article · Sep 7, 2026 · UTC

Quadruped robot locomotion policies are often trained using reinforcement learning, which in turn relies heavily on hand-crafted reward functions. Designing reward functions requires substantial manual engineering, and it is often unclear which local rewards will induce the desired global behavior. Shaped rewards from formal specifications in languages like Signal Temporal Logic (STL) can make rewards more interpretable, but writing STL specifications itself still requires domain expertise. We study whether large language models (LLMs) can fill this gap by generating Parametric Signal Temporal

Read original source ↗ Open in workspace

recordType

paper

region

Global