← Saturday, October 3, 2026AgentsPaper

PyRUA-Lean raises robot-agent success while using fewer tokens

huggingface.co by Ruiyang Si et al. Editor score 8/10

PyRUA-Lean lets agents compose robot primitives and VLA policies into Python cells with local retries and selective observations; it raises success from 63.1% to 71.7% while using 65% fewer input tokens. The design shows how execution between model calls can improve agent efficiency.

What

PyRUA-Lean is a code-execution framework for robot agents that reduces repeated model calls and redundant observations.

Method

It composes robot primitives and VLA policies into Python cells with checks and retries, returning requested images and state for replanning.

Why it matters

At equal LLM-call budgets, it raises overall success from 63.1% to 71.7%; on jointly solved tasks it uses 65% fewer input tokens.

Read on huggingface.co → Code · 17 stars

Headline, summary, brief and diagram are written by a model from the source's own text; the link, byline and numbers come from the source. Read the original before relying on a claim.