Multi-Agent LLM Actor-Critic Framework for Social Robot Navigation
Anonymous Authors
Anonymous University
To submit to IROS 2026
[LLM-Actor Textual_Demo] [LLM-Critic Textual_Demo] [Re-Query Textual_Demo]
Embedded Files
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.
Architecture of SAMALM
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.
Multi-Agent LLM Actor-Critic Framework
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.
Multi-Robot World Model Representation
An illustration of multi-robot world model construction.
An illustration of multi-robot world model construction.
Multi-Robot Social Navigation Scene
Multi-Robot Social Navigation Scene
Comparison Simulation Experiments and Trajectory Illustrations
Open Space Simulator
Open Space Simulator
Fov-90° Simulator
Fov-90° Simulator
Test-Case-1: SAMALM (our model)
Test-Case-1: SAMALM (our model)
GPT-Actor + WM (world model) + Auto-CoT [+ Critic + Requery]
GPT-Actor + WM (world model) + Auto-CoT [+ Critic + Requery]
Test-Case-1: GPT-Actor + WM (world model) + Auto-CoT (Ablation Model)
Test-Case-1: GPT-Actor + WM (world model) + Auto-CoT (Ablation Model)
[without Critic]
[without Critic]
Test-Case-2: SAMALM (our model)
Test-Case-2: SAMALM (our model)
GPT-Actor + WM (world model) + Auto-CoT [+ Critic + Requery]
GPT-Actor + WM (world model) + Auto-CoT [+ Critic + Requery]
Test-Case-2: GPT-Actor + WM (world model) + Auto-CoT (Ablation Model)
Test-Case-2: GPT-Actor + WM (world model) + Auto-CoT (Ablation Model)
[without Critic]
[without Critic]
More Trajectory Results
GPT-4 + Auto-CoT + WM
GPT-4 + Auto-CoT + WM
GPT-4o without Auto-CoT
GPT-4o without Auto-CoT
GPT-4 without Auto-CoT
GPT-4 without Auto-CoT
GPT-3.5
GPT-3.5
SAMALM Implementation Details
(1). LLM-Actor Input and Output
(Input) Environmental Configuration Prompt Engineering:
(Input) World Model Representation Prompt Engineering:
(Input) Auto-CoT Prompt Engineering:
(Output) LLM-Actor Inference Output:
The Entire Text Demo of LLM-Actor Input-Output
(2). LLM-Critic Input and Output
(Input) Evaluation Rules and Environmental Configuration Prompt Engineering:
(Input) Critic Observation Prompt Engineering:
(Input) Auto-CoT Prompt Engineering:
(Input) Global-Critic Prompt Engineering:
(Output) Local LLM-Critic Inference Output [Step-1 in Critic-CoT]:
(Output) Global-Critic Inference Output [Step-1 in Critic-CoT]:
(Output) All LLM-Critics Inference Output [Step-3 in Critic-CoT]:
[Note: Only inference information from CoT's Step-3 will be fed into LLM-Actors as evaluation feeback.]
(Output) All LLM-Critics Q-Value Output [Step-4 in Critic-CoT]:
The Entire Text Demo of LLM-Actor Input-Output
(3). Multi-LLM Actor-Critic Re-Query Mechanism
Actor-Critic Re-Query Object Example:
(Input) Re-Query LLM-Actor Environmental Configuration Prompt Engineering:
(Input) Re-Query LLM-Actor Observation Prompt Engineering:
(Input) Re-Query LLM-Actor Feedback (from Critic) Prompt Engineering:
(Input) Re-Query LLM-Actor CoT Prompt Engineering:
(Output) Re-Query LLM-Actor Inference w.r.t Critic Feedback Output:
Actor-Critic Re-Query Procedure Example:
The Entire Text Demo of LLM-Actor Re-Query Procedure
References
Page updated
Google Sites
Report abuse