ABot-Claw: A Foundation for Persistent, Cooperative, and Self-Evolving Robotic Agents
This work addresses the gap between planning and physical execution for multi-robot systems in open-world settings, offering a foundation for persistent and self-improving robotic agents.
ABot-Claw bridges high-level reasoning and low-level execution for persistent, cooperative robotic agents by integrating a unified embodiment interface, visual-centric multimodal memory, and critic-based closed-loop feedback. It enables real-world interaction and self-evolving capabilities in open environments.
Current embodied intelligent systems still face a substantial gap between high-level reasoning and low-level physical execution in open-world environments. Although Vision-Language-Action (VLA) models provide strong perception and intuitive responses, their open-loop nature limits long-horizon performance. Agents incorporating System 2 cognitive mechanisms improve planning, but usually operate in closed sandboxes with predefined toolkits and limited real-system control. OpenClaw provides a localized runtime with full system privileges, but lacks the embodied control architecture required for long-duration, multi-robot execution. We therefore propose ABot-Claw, an embodied extension of OpenClaw that integrates: 1) a unified embodiment interface with capability-driven scheduling for heterogeneous robot coordination; 2) a visual-centric cross-embodiment multimodal memory for persistent context retention and grounded retrieval; and 3) a critic-based closed-loop feedback mechanism with a generalist reward model for online progress evaluation, local correction, and replanning. With a decoupled architecture spanning the OpenClaw layer, shared service layer, and robot embodiment layer, ABot-Claw enables real-world interaction, closes the loop from natural language intent to physical action, and supports progressively self-evolving robotic agents in open, dynamic environments.