ArgLLM-App: an interactive system for argumentative reasoning with large language models
File(s)
Accepted version
Author(s)
Dejl, Adam
Gorur, Deniz
Toni, Francesca
Type
Conference Paper
Abstract
Argumentative LLMs (ArgLLMs) are an existing approach leveraging Large Language Models (LLMs) and computational argumentation for decision-making, with the aim of making the resulting decisions faithfully explainable to and contestable by humans. Here we propose a web-based system implementing ArgLLM-empowered agents for binary tasks. ArgLLM-App supports visualisation of the produced explanations and interaction with human users, allowing them to identify and contest any mistakes in the system’s reasoning. It is highly modular and enables drawing information from trusted external sources. A video demonstration of ArgLLM-App is available at https://youtu.be/vzwlGOr0sPM
Date Acceptance
2026-02-13
Publisher
International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS).
Copyright Statement
Copyright This paper is embargoed until publication. Once published the Version of Record (VoR) will be available on immediate open access.
Source
25th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2026)
Publication Status
Accepted
Start Date
2026-05-25
Finish Date
2026-05-29
Coverage Spatial
Paphos, Cyprus