A Multimodal Social Agent

TL;DR

MuSA is a multimodal LLM-based social agent that automates and enhances social content analysis tasks like question answering and categorization, demonstrating significant performance improvements over baselines.

Contribution

This paper introduces MuSA, a novel multimodal LLM-based agent that integrates planning, reasoning, and refinement strategies for social content analysis tasks.

Findings

MuSA outperforms baseline models in question answering.

MuSA effectively generates titles and categorizes social content.

The approach improves automation and decision-making in social analysis.

Abstract

In recent years, large language models (LLMs) have demonstrated remarkable progress in common-sense reasoning tasks. This ability is fundamental to understanding social dynamics, interactions, and communication. However, the potential of integrating computers with these social capabilities is still relatively unexplored. However, the potential of integrating computers with these social capabilities is still relatively unexplored. This paper introduces MuSA, a multimodal LLM-based agent that analyzes text-rich social content tailored to address selected human-centric content analysis tasks, such as question answering, visual question answering, title generation, and categorization. It uses planning, reasoning, acting, optimizing, criticizing, and refining strategies to complete a task. Our approach demonstrates that MuSA can automate and improve social content analysis, helping decision-making processes across various applications. We have evaluated our agent's capabilities in question answering, title generation, and content categorization tasks. MuSA performs substantially better than our baselines.