APOLLO: an open platform for LLM-based multi-agent interaction research
APOLLO: an open platform for LLM-based multi-agent interaction research
Traditional decision-making processes often struggle to capture diverse stakeholder perspectives and anticipate potential outcomes. Complex decisions and persuasions might rely on insights and perspectives which might not be available. In this paper, we leverage recent advances in large language models and retrieval-augmented generation to introduce APOLLO—an Architecture and oPen-source system that Orchestrates Large Language mOdels. APOLLO coordinates multiple LLMs by engaging them in collaborative discourse to reach a consensus on user-defined prompts. This system enables HCI and AI researchers and practitioners, and allows them to explore and experiment with LLM-based multi-agents systems in a user-configurable and customisable manner. By providing this flexible platform, APOLLO enables new avenues for studying and designing human-AI interactions, investigating the impact of multi-agent interaction on human behaviour, and ultimately facilitates a deeper understanding of how AI-driven collaboration can enhance human-AI interaction and decision making.
Decision-Making, Generative AI, Human-AI Interaction, LLM, Large Language Models, Multi-Agent Systems, Research Software
107-112
Johny, Abel
b05cbe7a-1d75-466e-8161-4c3d3aed5daa
Schneiders, Eike
9da80af0-1e27-4454-90e2-eb1abf7108bd
Clos, Jeremie
398fea21-4dc6-42ee-a2f1-cad9a789b378
17 July 2026
Johny, Abel
b05cbe7a-1d75-466e-8161-4c3d3aed5daa
Schneiders, Eike
9da80af0-1e27-4454-90e2-eb1abf7108bd
Clos, Jeremie
398fea21-4dc6-42ee-a2f1-cad9a789b378
Johny, Abel, Schneiders, Eike and Clos, Jeremie
(2026)
APOLLO: an open platform for LLM-based multi-agent interaction research.
Wiafe, Isaac, Babiker, Areej, Ham, Jaap, Oyibo, Kiemute and Vlahu-Gjorgievska, Elena
(eds.)
In APOLLO: An Open Platform for LLM-Based Multi-agent Interaction Research.
vol. 2542,
Springer Nature.
.
(doi:10.1007/978-3-031-97177-8_10).
Record type:
Conference or Workshop Item
(Paper)
Abstract
Traditional decision-making processes often struggle to capture diverse stakeholder perspectives and anticipate potential outcomes. Complex decisions and persuasions might rely on insights and perspectives which might not be available. In this paper, we leverage recent advances in large language models and retrieval-augmented generation to introduce APOLLO—an Architecture and oPen-source system that Orchestrates Large Language mOdels. APOLLO coordinates multiple LLMs by engaging them in collaborative discourse to reach a consensus on user-defined prompts. This system enables HCI and AI researchers and practitioners, and allows them to explore and experiment with LLM-based multi-agents systems in a user-configurable and customisable manner. By providing this flexible platform, APOLLO enables new avenues for studying and designing human-AI interactions, investigating the impact of multi-agent interaction on human behaviour, and ultimately facilitates a deeper understanding of how AI-driven collaboration can enhance human-AI interaction and decision making.
Text
Pers_Tech__APOLLO-2
- Accepted Manuscript
More information
Published date: 17 July 2026
Keywords:
Decision-Making, Generative AI, Human-AI Interaction, LLM, Large Language Models, Multi-Agent Systems, Research Software
Identifiers
Local EPrints ID: 504928
URI: http://eprints.soton.ac.uk/id/eprint/504928
ISSN: 1865-0929
PURE UUID: 94675c78-b237-4dd4-acfd-8b7d5dd8fec8
Catalogue record
Date deposited: 22 Sep 2025 16:55
Last modified: 23 Sep 2025 02:21
Export record
Altmetrics
Contributors
Author:
Abel Johny
Author:
Eike Schneiders
Author:
Jeremie Clos
Editor:
Isaac Wiafe
Editor:
Areej Babiker
Editor:
Jaap Ham
Editor:
Kiemute Oyibo
Editor:
Elena Vlahu-Gjorgievska
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics