LegalWebAgent: Empowering Access to Justice via LLM-Based Web Agents

TL;DR

LegalWebAgent leverages multimodal large language models to create an autonomous web agent that assists users in navigating legal websites, understanding legal information, and performing legal-related actions, significantly improving access to justice.

Contribution

This work introduces a novel multimodal LLM-based web agent framework that automates legal information retrieval and procedural tasks, enhancing access to justice for ordinary citizens.

Findings

Achieved a peak success rate of 86.7% in real-world legal tasks.

Demonstrated high autonomy in complex legal web interactions.

Validated effectiveness through a comprehensive benchmark with 15 tasks.

Abstract

Access to justice remains a global challenge, with many citizens still finding it difficult to seek help from the justice system when facing legal issues. Although the internet provides abundant legal information and services, navigating complex websites, understanding legal terminology, and filling out procedural forms continue to pose barriers to accessing justice. This paper introduces the LegalWebAgent framework that employs a web agent powered by multimodal large language models to bridge the gap in access to justice for ordinary citizens. The framework combines the natural language understanding capabilities of large language models with multimodal perception, enabling a complete process from user query to concrete action. It operates in three stages: the Ask Module understands user needs through natural language processing; the Browse Module autonomously navigates webpages, interacts with page elements (including forms and calendars), and extracts information from HTML structures and webpage screenshots; the Act Module synthesizes information for users or performs direct actions like form completion and schedule booking. To evaluate its effectiveness, we designed a benchmark test covering 15 real-world tasks, simulating typical legal service processes relevant to Qu\'ebec civil law users, from problem identification to procedural operations. Evaluation results show LegalWebAgent achieved a peak success rate of 86.7%, with an average of 84.4% across all tested models, demonstrating high autonomy in complex real-world scenarios.