Paper page - ASPIRE: Agentic /Skills Discovery for Robotics

Source: https://huggingface.co/papers/2607.00272 Authors:

,

,

,

,

,

,

,

,

,

,

,

,

Abstract

ASPIRE is a continual learning system that autonomously develops and refines robot control programs through iterative exploration, achieving superior performance and zero-shot generalization in manipulation and household tasks while enabling sim-to-real transfer.

Traditional robot programming is challenging: it requires orchestrating multimodal perception, managing physical contact dynamics, and handling diverse configurations and execution failures. We introduce ASPIRE (Agentic Skill Programming through Iterative Robot Exploration), acontinual learningsystem that autonomously writes and refines robot control programs in acode-as-policy paradigmwhile compounding experience into a reusableskill library. ASPIRE discovers skills that persist across tasks, simulation and real-world settings, and embodiments. It operates in an open-ended loop with three components: (1) aclosed-loop robot execution enginethat exposes fine-grainedmultimodal traces, enabling autonomousfailure diagnosis,repair synthesis, and validation; (2) a continually expandingskill librarythat distills validated fixes into reusable, transferable knowledge; and (3)evolutionary searchthat generates diverse task sequences and control programs to explore beyond single-trajectory refinement. ASPIRE surpasses prior methods by up to 77% on LIBERO-Pro manipulation under perturbation, 72% on Robosuite bimanual handover, and 32% on BEHAVIOR-1K long-horizon household tasks. Its accumulated library also enables zero-shot generalization to unseen long-horizon tasks: on LIBERO-Pro Long, ASPIRE achieves 31% success versus 4% for prior methods despite their use of test-time reasoning and retries. Finally, simulation-discovered skills provide initial evidence ofsim-to-real transfer, substantially reducing real-robot programming effort across different embodiments and robot APIs.

View arXiv pageView PDFProject pageAdd to collection

Get this paper in your agent:

hf papers read 2607\.00272

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2607.00272 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2607.00272 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2607.00272 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.