RoboClaw: An Agentic Framework for Scalable Long-Horizon Robotic Tasks

TL;DR

RoboClaw introduces an integrated agentic framework using vision-language models to enhance autonomous, scalable, long-horizon robotic manipulation with minimal human intervention.

Contribution

It unifies data collection, policy learning, and task execution under a single VLM-driven controller with novel self-resetting action pairs for autonomous operation.

Findings

Achieved 25% higher success rate on long-horizon tasks.

Reduced human effort by 53.7% in robot lifecycle.

Demonstrated improved stability and scalability in real-world experiments.

Abstract

Vision-Language-Action (VLA) systems have shown strong potential for language-driven robotic manipulation. However, scaling them to long-horizon tasks remains challenging. Existing pipelines typically separate data collection, policy learning, and deployment, resulting in heavy reliance on manual environment resets and brittle multi-policy execution. We present RoboClaw, an agentic robotics framework that unifies data collection, policy learning, and task execution under a single VLM-driven controller. At the policy level, RoboClaw introduces Entangled Action Pairs (EAP), which couple forward manipulation behaviors with inverse recovery actions to form self-resetting loops for autonomous data collection. This mechanism enables continuous on-policy data acquisition and iterative policy refinement with minimal human intervention. During deployment, the same agent performs high-level reasoning and dynamically orchestrates learned policy primitives to accomplish long-horizon tasks. By maintaining consistent contextual semantics across collection and execution, RoboClaw reduces mismatch between the two phases and improves multi-policy robustness. Experiments in real-world manipulation tasks demonstrate improved stability and scalability compared to conventional open-loop pipelines, while significantly reducing human effort throughout the robot lifecycle, achieving a 25% improvement in success rate over baseline methods on long-horizon tasks and reducing human time investment by 53.7%.