ASPIRE: Agentic /Skills Discovery for Robotics
ASPIRE: Agentic /Skills Discovery for Robotics
ASPIRE is a continual learning system that autonomously writes and refines robot control programs in a code-as-policy paradigm. It combines a closed-loop execution engine, a growing skill library, and an evolutionary search process to improve performance in manipulation tasks and enable zero-shot generalization. ASPIRE outperforms prior methods by up to 77% on perturbed manipulation tasks and achieves 99% success on LIBERO-Pro tasks with Claude Opus 5.5.
ASPIRE introduces a continual learning system for robotics that autonomously writes and refines control programs, achieving significant performance improvements over prior methods in manipulation and long-horizon tasks. The system combines a closed-loop execution engine, a growing skill library, and an evolutionary search process to enable zero-shot generalization and real-world application.
Source: arXiv Robotics — research abstracts · Read original article ↗
Loading article text…
What the source reports
Publisher-reported claims, with original evidence. These results have not been independently verified by RoboSignal.
- paper: not_reported
- code: not_reported
- weights: not_reported
- dataset: not_reported
Source excerpts and review record
Automatically extracted; no manual editorial approval recorded.
istills validated fixes into reusable, transferable robotic knowledge; and (3) an evolutionary search procedure that generates diverse programs, systematically debugging them to explore beyond single-trajectory refinement. ASPIRE surpasses prior methods by up to 77% on manipulation tasks under perturbation, 72% on Robosuite's bimanual handover task, and up to 32% on long-horizon household tasks. The accumulated skill
Open source S4
library further enables zero-shot generalization: on representative unseen long-horizon tasks, ASPIRE achieves 31% success, outperforming the 4% success rate of prior methods. Performance scales with the capabilities of frontier models. With Claude Opus 5.5, ASPIRE nearly saturates these benchmarks, achieving 99% average success across all 80 LIBERO-Pro tasks and 100% success on representative Robosuite and BEHAVIOR
Open source S5
Source：arXiv Robotics — research abstracts · arxiv.org