HiBerNAC: Hierarchical Brain-emulated Robotic Neural Agent Collective for Disentangling Complex Manipulation

TL;DR

HiBerNAC is a neuro-inspired hierarchical robotic agent framework that improves complex manipulation task performance by integrating multimodal reasoning, reflection, and multi-agent collaboration, inspired by neuroscience.

Contribution

This work introduces HiBerNAC, a novel neuro-inspired hierarchical framework combining multimodal planning, reflection, and multi-agent mechanisms for advanced robotic manipulation.

Findings

Reduces average long-horizon task completion time by 23%

Achieves success rates of 12-31% on multi-path tasks where prior models fail

Demonstrates scalable collective intelligence through dynamic agent specialization

Abstract

Recent advances in multimodal vision-language-action (VLA) models have revolutionized traditional robot learning, enabling systems to interpret vision, language, and action in unified frameworks for complex task planning. However, mastering complex manipulation tasks remains an open challenge, constrained by limitations in persistent contextual memory, multi-agent coordination under uncertainty, and dynamic long-horizon planning across variable sequences. To address this challenge, we propose \textbf{HiBerNAC}, a \textbf{Hi}erarchical \textbf{B}rain-\textbf{e}mulated \textbf{r}obotic \textbf{N}eural \textbf{A}gent \textbf{C}ollective, inspired by breakthroughs in neuroscience, particularly in neural circuit mechanisms and hierarchical decision-making. Our framework combines: (1) multimodal VLA planning and reasoning with (2) neuro-inspired reflection and multi-agent mechanisms, specifically designed for complex robotic manipulation tasks. By leveraging neuro-inspired functional modules with decentralized multi-agent collaboration, our approach enables robust and enhanced real-time execution of complex manipulation tasks. In addition, the agentic system exhibits scalable collective intelligence via dynamic agent specialization, adapting its coordination strategy to variable task horizons and complexity. Through extensive experiments on complex manipulation tasks compared with state-of-the-art VLA models, we demonstrate that \textbf{HiBerNAC} reduces average long-horizon task completion time by 23\%, and achieves non-zero success rates (12\textendash 31\%) on multi-path tasks where prior state-of-the-art VLA models consistently fail. These results provide indicative evidence for bridging biological cognition and robotic learning mechanisms.