Research

Paper

AI LLM February 27, 2026

ArgLLM-App: An Interactive System for Argumentative Reasoning with Large Language Models

Authors

Adam Dejl, Deniz Gorur, Francesca Toni

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. ArgLLM-App is publicly available at https://argllm.app, with a video demonstration at https://youtu.be/vzwlGOr0sPM.

Metadata

arXiv ID: 2602.24172
Provider: ARXIV
Primary Category: cs.CL
Published: 2026-02-27
Fetched: 2026-03-02 06:04

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2602.24172v1</id>\n    <title>ArgLLM-App: An Interactive System for Argumentative Reasoning with Large Language Models</title>\n    <updated>2026-02-27T16:52:27Z</updated>\n    <link href='https://arxiv.org/abs/2602.24172v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2602.24172v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>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. ArgLLM-App is publicly available at https://argllm.app, with a video demonstration at https://youtu.be/vzwlGOr0sPM.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.CL'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.AI'/>\n    <published>2026-02-27T16:52:27Z</published>\n    <arxiv:comment>AAMAS 2026 Demonstration Track</arxiv:comment>\n    <arxiv:primary_category term='cs.CL'/>\n    <author>\n      <name>Adam Dejl</name>\n    </author>\n    <author>\n      <name>Deniz Gorur</name>\n    </author>\n    <author>\n      <name>Francesca Toni</name>\n    </author>\n    <arxiv:doi>10.65109/NWEK7590</arxiv:doi>\n    <link href='https://doi.org/10.65109/NWEK7590' rel='related' title='doi'/>\n  </entry>"
}