ASPIRE is a self-improving continual learning system for robotics that writes and refines code-as-policy robot control programs from execution feedback. It inspects rollout traces, diagnoses failures, repairs programs, validates corrected behaviors, and saves reusable skills for future tasks. ASPIRE operates in an open-ended learning loop with three key components: a closed-loop robot execution engine, a continually expanding skill library, and an evolutionary search procedure.
For each perception, planning, grasping, and control call, the engine records the observations, inputs, outputs, and visual evidence if possible. These rich multimodal traces allow the agent to selectively inspect salient primitive logs, progressively localize failures, and validate repairs through re-execution.
ASPIRE maintains a growing skill library that distills validated fixes into modular, transferable robotic knowledge retrievable as in-context guidance for future tasks.
ASPIRE employs an evolutionary search procedure that generates diverse task sequences and control programs, exploring beyond single-trajectory self-improvement through iterative debugging and parallel refinement.
Each card pairs a CaP-Agent0 baseline or initial task attempt with the final behavior after ASPIRE diagnosed the rollout and rewrote the program. Hover over a demo video to view the baseline or initial program and the ASPIRE fix code. Use the filters to narrow the gallery. This is not an exhaustive list of all tasks.
Explore the expansive skill library learned by ASPIRE. The gallery is organized into 18 categories, each containing multiple skills. This is a representative sample, not an exhaustive list.
Across all benchmarks, an environment seed fixes each task instance, including object poses, distractors, and initial robot/object states. We use disjoint debug and evaluation seeds: ASPIRE learns on a small debug split, then reports success on larger held-out evaluation seeds with one generated program per LIBERO-Pro/Robosuite task, while CaP-Agent0 regenerates a separate program for each seed with test-time reasoning and retries. For BEHAVIOR-1K evaluation, ASPIRE uses incremental block execution, generating each next code block from the current multimodal trace.
ASPIRE writes control programs that generalize across object types, object positions, and task details.
ASPIRE handles contact-heavy tabletop manipulation tasks. Most notably, ASPIRE improved two-arm handover success rate from the baseline of 20% to 92% through iterative debugging.
For long-horizon mobile manipulation, we show navigation separately from task completion.
Skills learned across LIBERO-90 carry over to held-out long-horizon tasks. As the skill library grows, coding agents achieve higher success rate on LIBERO-Long.
For each task, we compare real-robot debugging with and without retrieving a corresponding simulation-discovered skill from ASPIRE’s library. Token counts are measured until the first successful real-robot program. Success Rate reports held-out evaluation trials of the code that achieved that first success. When equipped with ASPIRE skills, the coding agent reaches its first success with fewer tokens, and the generated code achieves a higher success rate.
Output tokens (M)
Total tokens (M)
Held-out success rate (%)
We present ASPIRE, a self-improving continual learning robotic system that autonomously writes and refines robot control programs while compounding experience into a reusable skill library. ASPIRE operates in an open-ended learning loop with three components: a closed-loop robot execution engine that exposes fine-grained multimodal traces, a continually expanding skill library that distills validated fixes into transferable knowledge, and an evolutionary search procedure that explores diverse task sequences and control programs. Across diverse benchmarks, ASPIRE substantially outperforms existing VLA and coding-agent baselines, demonstrates strong zero-shot transfer to unseen long-horizon tasks, and provides initial evidence that the skills discovered in sim can transfer across embodiment to significantly reduce real-robot programming token cost despite different robot embodiments and APIs.
*Equal contribution · †Project leads
@article{lu2026aspire,
title = {ASPIRE: Agentic /Skills Discovery for Robotics},
author = {Runyu Lu and Yubo Wu and Ethan Kou and Max Fu and Wenli Xiao and
Ajay Mandlekar and Yinzhen Xu and Guanya Shi and Ken Goldberg and
Ang Chen and Mosharaf Chowdhury and Yuke Zhu and Linxi Fan and Guanzhi Wang},
year = {2026},
journal = {arXiv preprint}
}
We thank Nadun Ranawaka, Jimmy Wu, Matin Furutan, Haotian Lin, Abhi Maddukuri, Yulu Gan, Matin Nikoui, and Yuqi Xie for their help with open-source support, real robot infrastructure, advice and guidance on the paper, website release, and experimental equipment. We are also grateful to the members of NVIDIA GEAR, UMich SymbioticLab, UsesysLab, UC Berkeley AUTOLab, CMU LeCAR Lab for their kind support.