arXiv subjects

Rem Collier

Publications and source records attributed to Rem Collier.

6 recordsLinked to original sources

arXiv2026

astra-langchain4j: Experiences Combining LLMs and Agent Programming

Given the emergence of Generative AI over the last two years and the increasing focus on Agentic AI as a form of Multi-Agent System it is important to explore both how such technologies can impact the use of traditional Agent Toolkits and how the wealth of experience encapsulated in those toolkits can influence the design of the new agentic platforms. This paper presents an overview of our experience developing a prototype large language model (LLM) integration for the ASTRA programming language. It presents a brief overview of the toolkit, followed by three example implementations, concluding with a discussion of the experiences garnered through the examples.

cs.AI↗

arXiv2024

Do you want to play a game? Learning to play Tic-Tac-Toe in Hypermedia Environments

We demonstrate the integration of Transfer Learning into a hypermedia Multi-Agent System using the Multi-Agent MicroServices (MAMS) architectural style. Agents use RDF knowledge stores to reason over information and apply Reinforcement Learning techniques to learn how to interact with a Tic-Tac-Toe API. Agents form advisor-advisee relationships in order to speed up individual learning and exploit and learn from data on the Web.

cs.MA↗

arXiv2023

Using Multi-Agent MicroServices (MAMS) for Agent Based Modelling

This paper demonstrates the use of the Multi-Agent MicroServices (MAMS) architectural style through a case study based around the development of a prototype traffic simulation in which agents model a population of individuals who travel from home to work and vice versa by car.

cs.MA↗

arXiv2018

Towards a Programmable Framework for Agent Game Playing

The field of Game Theory provides a useful mechanism for modeling many decision-making scenarios. In participating in these scenarios individuals and groups adopt particular strategies, which generally perform with varying levels of success. However, most results have focussed on players that play the same game in an iterated fashion. This paper describes a framework which can be used to observe agents when they do not know in advance which game they are going to play. That is, the same group of agents could first play a few rounds of the Iterated Prisoner's Dilemma, and then a few rounds of the Linear Public Goods Game, and then a few rounds of Minority Game, or perhaps all games in a strictly alternating fashion or a randomized instantiation of games. This framework will allow for investigation of agents in more complex settings, when there is uncertainty about the future, and limited resources to store strategies.

cs.MA↗

arXiv2014

An Agent-Based Approach to Component Management

This paper details the implementation of a software framework that aids the development of distributed and self-configurable software systems. This framework is an instance of a novel integration strategy called SoSAA (SOcially Situated Agent Architecture), which combines Component-Based Software Engineering and Agent-Oriented Software Engineering, drawing its inspiration from hybrid agent control architectures. The framework defines a complete construction process by enhancing a simple component-based framework with reasoning and self-awareness capabilities through a standardized interface. The capabilities of the resulting framework are demonstrated through its application to a non-trivial Multi Agent System (MAS). The system in question is a pre-existing Information Retrieval (IR) system that has not previously taken advantage of CBSE principles. In this paper we contrast these two systems so as to highlight the benefits of using this new hybrid approach. We also outline how component-based elements may be integrated into the Agent Factory agent-oriented application framework.

cs.MA↗

arXiv2014

ProbFuse: A Probabilistic Approach to Data Fusion

Data fusion is the combination of the results of independent searches on a document collection into one single output result set. It has been shown in the past that this can greatly improve retrieval effectiveness over that of the individual results. This paper presents probFuse, a probabilistic approach to data fusion. ProbFuse assumes that the performance of the individual input systems on a number of training queries is indicative of their future performance. The fused result set is based on probabilities of relevance calculated during this training process. Retrieval experiments using data from the TREC ad hoc collection demonstrate that probFuse achieves results superior to that of the popular CombMNZ fusion algorithm.

cs.IR↗