ABot-Claw: A Foundation for Persistent, Cooperative, and Self-Evolving Robotic Agents

2026-04-11

AI Summary

This work addresses the disconnect between high-level reasoning and low-level execution in existing embodied intelligence systems operating in open environments, as well as their lack of closed-loop feedback and self-evolution capabilities. To bridge this gap, the paper proposes a three-layer decoupled architecture—comprising an OpenClaw layer, a shared services layer, and a robot embodiment layer—that integrates a unified embodiment interface, vision-centric cross-embodiment multimodal memory, a critic-based closed-loop feedback mechanism, and a general reward model. This architecture enables heterogeneous robot coordination, persistent contextual memory, and online replanning, thereby supporting long-horizon, collaborative closed-loop execution from natural language intent to physical action. The approach significantly enhances agents’ capacity for continuous self-evolution in dynamic, open-world settings.

Technology Category

• Intelligent Robots: Embodied AI
• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search

Abstract

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.

Problem

• embodied intelligence
• open-world robotics
• long-horizon execution
• multi-robot coordination
• persistent context

Innovation

• embodied intelligence
• closed-loop feedback
• multimodal memory
• heterogeneous robot coordination
• self-evolving agents