# MARS: Multi-Agent Robotic System with Multimodal Large Language Models for Assistive Intelligence Source: [MARS: Multi-Agent Robotic System with Multimodal Large Language Models for Assistive Intelligence]() Collection index: [llms.txt]() Data updated: 2026-04-09T05:00:13.067Z Authors: Renjun Gao Published: 2025-11-03T13:58:37.000Z ## Abstract Multimodal large language models (MLLMs) have shown remarkable capabilities in cross-modal understanding and reasoning, offering new opportunities for intelligent assistive systems, yet existing systems still struggle with risk-aware planning, user personalization, and grounding language plans into executable skills in cluttered homes. We introduce MARS - a Multi-Agent Robotic System powered by MLLMs for assistive intelligence and designed for smart home robots supporting people with disabilities. The system integrates four agents: a visual perception agent for extracting semantic and spatial features from environment images, a risk assessment agent for identifying and prioritizing hazards, a planning agent for generating executable action sequences, and an evaluation agent for iterative optimization. By combining multimodal perception with hierarchical multi-agent decision-making, the framework enables adaptive, risk-aware, and personalized assistance in dynamic indoor environments. Experiments on multiple datasets demonstrate the superior overall performance of the proposed system in risk-aware planning and coordinated multi-agent execution compared with state-of-the-art multimodal models. The proposed approach also highlights the potential of collaborative AI for practical assistive scenarios and provides a generalizable methodology for deploying MLLM-enabled multi-agent systems in real-world environments. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Information Analysis and Processing on MARS Level 1 (test)](): Information Analysis and Processing; MARS Level 1 (test); Average Ranking (AI GPT-5): 1.7. - [Information Analysis and Processing on MARS Level 2 (Evaluation Set)](): Information Analysis and Processing; MARS Level 2 (Evaluation Set); Average Ranking (AI GPT-5): 2.2. - [Information Analysis and Processing on MARS Level 3 (Evaluation Set)](): Information Analysis and Processing; MARS Level 3 (Evaluation Set); Avg Rank (AI GPT-5): 1.9. - [Information Analysis and Processing on MARS Overall (Evaluation Set)](): Information Analysis and Processing; MARS Overall (Evaluation Set); Average Ranking (AI GPT-5): 1.93. ## Original sources and implementation [Original paper]() [PDF]()