Maat: The Agentic Legal Research Assistant for Competition Protection
2026-05-26 • Artificial Intelligence
Artificial Intelligence
AI summaryⓘ
The authors created Maat, a specialized AI tool to help legal experts review competition law cases more accurately. Unlike general AI assistants, Maat uses official sources and reliable data to avoid mistakes and provides clear citations. It also asks users for clarification if a question is unclear and uses web search when its main data is missing. Tests show Maat works better than existing AI helpers on practical case tasks. The authors have shared the related data publicly on GitHub.
competition lawlegal researchReAct agentretrieval-augmented generation (RAG)case lawlegal citationsAI assistantsweb search fallbackambiguity resolutiondataset
Authors
Basant Mounir, Farida Madkour, Amira Abdelaziz, Asmaa Sami
Abstract
Competition law experts conducting legal research must review extensive volumes of cases, decisions, and judicial reports to identify precedents and assess key elements in competition and merger cases. Although general research assistants such as Claude and ChatGPT and legal assistants such as SaulLM-7B and LegalGPT are increasingly used to assist legal research, they remain inadequate for competition law analysis: they lack specialized domain expertise, provide insufficient official citations, or hallucinate competition law cases. We propose Maat, a ReAct agent that orchestrates tools corresponding to different tasks of the research process. Designed iteratively with competition law experts, Maat grounds cases and findings in official sources using RAG for reliability, provides rich in-line citations, falls back to web search when database coverage is insufficient, and prompts the user for clarification when queries are ambiguous. Maat significantly outperforms all baseline assistants on case-specific tasks and performs within range of the top baseline on theoretical question tasks. The dataset used is available on GitHub.