Multi-Agent LLM Actor-Critic Framework for Social Robot Navigation

TL;DR

Experimental results confirm that SAMALM effectively balances local autonomy with global oversight, yielding socially compliant behaviors and strong adaptability across diverse multi-robot scenarios.

Abstract

Recent advances in robotics and large language models (LLMs) have sparked growing interest in human-robot collaboration and embodied intelligence. To enable the broader deployment of robots in human-populated environments, socially-aware robot navigation (SAN) has become a key research area. While deep reinforcement learning approaches that integrate human-robot interaction (HRI) with path planning have demonstrated strong benchmark performance, they often struggle to adapt to new scenarios and environments. LLMs offer a promising avenue for zero-shot navigation through commonsense inference. However, most existing LLM-based frameworks rely on centralized decision-making, lack robust verification mechanisms, and face inconsistencies in translating macro-actions into precise low-level control signals. To address these challenges, we propose SAMALM, a decentralized multi-agent LLM actor-critic framework for multi-robot social navigation. In this framework, a set of parallel LLM actors, each reflecting distinct robot personalities or configurations, directly generate control signals. These actions undergo a two-tier verification process via a global critic that evaluates group-level behaviors and individual critics that assess each robot's context. An entropy-based score fusion mechanism further enhances self-verification and re-query, improving both robustness and coordination. Experimental results confirm that SAMALM effectively balances local autonomy with global oversight, yielding socially compliant behaviors and strong adaptability across diverse multi-robot scenarios. More details and videos about this work are available at: https://sites.google.com/view/SAMALM.

Figures (5)

• Figure 1: SAMALM procedure in a multi-robot social navigation scenario: The decentralized decision-making system supports self-verification and re-query, consisting of multiple parallel LLM-actors, evaluated by both the individual LLM-critic and a global LLM-critic.
• Figure 2: SAMALM architecture: SAMALM is a decentralized multi-agent LLM actor-critic framework designed for multi-robot social navigation. In SAMALM, a set of LLM-actors generates low-level control signals for the robots, respectively. These generated actions are then evaluated by relative LLM-critics from both the team-level and agent-level perspective, which either confirms the actions or prompts a re-query with critic feedback. Once the actions pass the evaluation threshold, they are executed by the system’s executors in the multi-robot environment.
• Figure 3: An illustration of multi-robot world model construction.
• Figure 4: Multi-Agent LLM Actor-Critic Framework: SAMALM facilitates multi-robot social navigation using a set of parallel LLM actors that extract semantic correlations from local world model observations and work in tandem with both global and local critics. The global critic assesses multi-robot behaviors by considering both inter-group and intra-group dynamics, while local critics evaluate individual actions based on long-term and short-term factors. Ultimately, the global and local critic scores are integrated via an entropy-based fusion mechanism that accounts for the level of disagreement among the critics, enabling self-verification and re-query with critic feedback.
• Figure 5: The illustration of heterogeneous multi-robot social navigation simulation scenario, where 3 robots are navigating by individual LLM-actor to distinct destinations across the crowd with 10 humans.