Multimodal Multi-Agent Empowered Legal Judgment Prediction

2026-01-19

AI Summary

This work addresses the limitations of traditional legal judgment prediction methods, which often exhibit poor adaptability and lack standardized procedures when handling cases involving multiple charges, multimodal evidence, and complex factual scenarios. To overcome these challenges, we propose JurisMMA, a novel framework that introduces, for the first time, a multimodal multi-agent architecture to decompose the adjudication process into standardized stages, enabling the collaborative integration of heterogeneous judicial data such as textual records and video evidence. We construct JurisMM, a large-scale multimodal dataset comprising over 100,000 Chinese judicial records, and evaluate our approach on both this dataset and the LawBench benchmark. Experimental results demonstrate that JurisMMA significantly improves judgment prediction accuracy, advancing legal AI toward more systematic, modular, and process-oriented paradigms.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Computer Vision: Multi-modal Vision
• Natural Language Processing: Language Grounding & Multi-modal NLP

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Web Mining and Content Analysis: Mining multimedia, multimodal, multilingual, cross-lingual Web data
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Legal Judgment Prediction (LJP) aims to predict the outcomes of legal cases based on factual descriptions, serving as a fundamental task to advance the development of legal systems. Traditional methods often rely on statistical analyses or role-based simulations but face challenges with multiple allegations, diverse evidence, and lack adaptability. In this paper, we introduce JurisMMA, a novel framework for LJP that effectively decomposes trial tasks, standardizes processes, and organizes them into distinct stages. Furthermore, we build JurisMM, a large dataset with over 100,000 recent Chinese judicial records, including both text and multimodal video-text data, enabling comprehensive evaluation. Experiments on JurisMM and the benchmark LawBench validate our framework's effectiveness. These results indicate that our framework is effective not only for LJP but also for a broader range of legal applications, offering new perspectives for the development of future legal methods and datasets.

Problem

• Legal Judgment Prediction
• Multimodal Data
• Multi-Agent System
• Legal AI
• Judicial Decision Making

Innovation

• Multimodal
• Multi-Agent
• Legal Judgment Prediction
• Task Decomposition
• JurisMM