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

arXiv: https://arxiv.org/abs/2503.09758 · HTML: https://mlsanity.com/paper/2503.09758/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use.
- Builds on 32 of its 39 references that are in the map.
- First posted on arXiv 12 Mar 2025.

## Placed in

- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 30 of 32)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [Do As I Can, Not As I Say: Grounding Language in Robotic Affordances](https://mlsanity.com/paper/2204.01691/) (2022)
- [AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation](https://mlsanity.com/paper/2308.08155/) (2023)
- [ChatDev: Communicative Agents for Software Development](https://mlsanity.com/paper/2307.07924/) (2023)
- [CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing](https://mlsanity.com/paper/2305.11738/) (2023)
- [Automatic Chain of Thought Prompting in Large Language Models](https://mlsanity.com/paper/2210.03493/) (2022)
- [LM-Nav: Robotic Navigation with Large Pre-Trained Models of Language, Vision, and Action](https://mlsanity.com/paper/2207.04429/) (2022)
- [Navigation World Models](https://mlsanity.com/paper/2412.03572/) (2024)
- [RoCo: Dialectic Multi-Robot Collaboration with Large Language Models](https://mlsanity.com/paper/2307.04738/) (2023)
- [SMART-LLM: Smart Multi-Agent Robot Task Planning using Large Language Models](https://mlsanity.com/paper/2309.10062/) (2023)
- [Socially Aware Motion Planning with Deep Reinforcement Learning](https://mlsanity.com/paper/1703.08862/) (2017)
- [Language Models Meet World Models: Embodied Experiences Enhance Language Models](https://mlsanity.com/paper/2305.10626/) (2023)
- [Evaluating and Inducing Personality in Pre-trained Language Models](https://mlsanity.com/paper/2206.07550/) (2022)
- [Robot Learning on the Job: Human-in-the-Loop Autonomy and Learning During Deployment](https://mlsanity.com/paper/2211.08416/) (2022)
- [Intention Aware Robot Crowd Navigation with Attention-Based Interaction Graph](https://mlsanity.com/paper/2203.01821/) (2022)
- [VLM-Social-Nav: Socially Aware Robot Navigation through Scoring using Vision-Language Models](https://mlsanity.com/paper/2404.00210/) (2024)
- [CoNVOI: Context-aware Navigation using Vision Language Models in Outdoor and Indoor Environments](https://mlsanity.com/paper/2403.15637/) (2024)
- [LiP-LLM: Integrating Linear Programming and dependency graph with Large Language Models for multi-robot task planning](https://mlsanity.com/paper/2410.21040/) (2024)
- [Multi-Robot Cooperative Socially-Aware Navigation Using Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2309.15234/) (2023)
- [Language and Sketching: An LLM-driven Interactive Multimodal Multitask Robot Navigation Framework](https://mlsanity.com/paper/2311.08244/) (2023)
- [SICNav: Safe and Interactive Crowd Navigation using Model Predictive Control and Bilevel Optimization](https://mlsanity.com/paper/2310.10982/) (2023)
- [NaviSTAR: Socially Aware Robot Navigation with Hybrid Spatio-Temporal Graph Transformer and Preference Learning](https://mlsanity.com/paper/2304.05979/) (2023)
- [World Models for Math Story Problems](https://mlsanity.com/paper/2306.04347/) (2023)
- [Human-Aware Physical Human-Robot Collaborative Transportation and Manipulation with Multiple Aerial Robots](https://mlsanity.com/paper/2210.05894/) (2022)
- [Topology-Driven Parallel Trajectory Optimization in Dynamic Environments](https://mlsanity.com/paper/2401.06021/) (2024)
- [Attention Graph for Multi-Robot Social Navigation with Deep Reinforcement Learning](https://mlsanity.com/paper/2401.17914/) (2024)
- [HeR-DRL:Heterogeneous Relational Deep Reinforcement Learning for Decentralized Multi-Robot Crowd Navigation](https://mlsanity.com/paper/2403.10083/) (2024)

## Built on by (most cited first, 8 of 8)

- [Multi-agent Embodied AI: Advances and Future Directions](https://mlsanity.com/paper/2505.05108/) (2025)
- [VIKI-R: Coordinating Embodied Multi-Agent Cooperation via Reinforcement Learning](https://mlsanity.com/paper/2506.09049/) (2025)
- [GauDP: Reinventing Multi-Agent Collaboration through Gaussian-Image Synergy in Diffusion Policies](https://mlsanity.com/paper/2511.00998/) (2025)
- [MARO: Learning Stronger Reasoning from Social Interaction](https://mlsanity.com/paper/2601.12323/) (2026)
- [Advances and Innovations in the Multi-Agent Robotic System (MARS) Challenge](https://mlsanity.com/paper/2601.18733/) (2026)
- [Ego to World: Collaborative Spatial Reasoning in Embodied Systems via Reinforcement Learning](https://mlsanity.com/paper/2603.14811/) (2026)
- [The Robot's Inner Critic: Self-Refinement of Social Behaviors through VLM-based Replanning](https://mlsanity.com/paper/2603.20164/) (2026)
- [Observe, Share, or Predict? Disentangling Partner Information in Embodied Multi-Agent Collaboration](https://mlsanity.com/paper/2610.16895/) (2026)

## Abstract (arXiv)

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.