Agent-Centric Projection of Prompting Techniques and Implications for Synthetic Training Data for Large Language Models

Dhruv Dhamani, Mary Lou Maher

2025

Abstract

Recent advances in prompting techniques and multi-agent systems for Large Language Models (LLMs) have produced increasingly complex approaches. However, we lack a framework for characterizing and comparing prompting techniques or understanding their relationship to multi-agent LLM systems. This position paper introduces and explains the concepts of linear contexts (a single, continuous sequence of interactions) and non-linear contexts (branching or multi-path) in LLM systems. These concepts enable the development of an agent-centric projection of prompting techniques, a framework that can reveal deep connections between prompting strategies and multi-agent systems. We propose three conjectures based on this framework: (1) results from non-linear prompting techniques can predict outcomes in equivalent multi-agent systems, (2) multi-agent system architectures can be replicated through single-LLM prompting techniques that simulate equivalent interaction patterns, and (3) these equivalences suggest novel approaches for generating synthetic training data. We argue that this perspective enables systematic cross-pollination of research findings between prompting and multi-agent domains, while providing new directions for improving both the design and training of future LLM systems.

Paper Citation

in Harvard Style

Dhamani D. and Maher M. (2025). Agent-Centric Projection of Prompting Techniques and Implications for Synthetic Training Data for Large Language Models. In Proceedings of the 17th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART; ISBN 978-989-758-737-5, SciTePress, pages 1254-1261. DOI: 10.5220/0013318300003890

in Bibtex Style

@conference{icaart25,
author={Dhruv Dhamani and Mary Maher},
title={Agent-Centric Projection of Prompting Techniques and Implications for Synthetic Training Data for Large Language Models},
booktitle={Proceedings of the 17th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART},
year={2025},
pages={1254-1261},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013318300003890},
isbn={978-989-758-737-5},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 17th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART
TI - Agent-Centric Projection of Prompting Techniques and Implications for Synthetic Training Data for Large Language Models
SN - 978-989-758-737-5
AU - Dhamani D.
AU - Maher M.
PY - 2025
SP - 1254
EP - 1261
DO - 10.5220/0013318300003890
PB - SciTePress