Reinforcement Learning-Driven Multi-Agent Information Retrieval Using Large Language Models

This project investigates the integration of multiagent systems and Reinforcement Learning (RL) with large language models (LLMs) to enhance information retrieval and contextual understanding in complex environments. The focus is on developing frameworks where multiple agents collaborate using LLMs to efficiently access, interpret, and share information from vast and dynamic datasets. By leveraging RL, agents learn to optimize their retrieval strategies and refine their interactions with LLMs to improve the relevance and accuracy of retrieved information.

This research addresses challenges in multi-agent communication, information synthesis, and adaptive querying, with applications in knowledge discovery, automated research assistants, and real-time data-driven decision support systems. The project aims to advance the efficiency and scalability of multiagent systems in retrieving and processing contextualized information from structured and unstructured sources.

Expected Outcomes:

1. A robust framework for multiagent systems utilizing LLMs to retrieve, synthesize, and share information collaboratively.
2. Improved Reinforcement Learning algorithms tailored for optimizing Information Retrieval strategies in Multi-Agent environments.
3. Demonstrated applications in domains such as automated knowledge discovery and dynamic information monitoring.

Key Words: Multi-Agent systems, Reinforcement Learning, Large Language Models, Information Retrieval, Contextual Understanding, Knowledge Synthesis, Data-Driven Systems, Adaptive Querying.

Requirements:

Essential:

• Bachelor’s or Master’s degree (2:1 or above) in Computer Science, Artificial Intelligence, Maths & Statistics, and Engineering or any other relevant fields.
• Strong communication skills.
• Understanding of research methodologies and experimental design.
• Proficiency in programming languages such as Python, TensorFlow, and PyTorch.
• Familiarity with machine learning and deep learning techniques.

Desirable:

• Prior experience in Generative AI research particularly Large Language Models.
• Knowledge of reinforcement learning algorithms.
• Ability to work independently and collaboratively in an interdisciplinary environment.
• Creative problem-solving skills and a passion for exploring the intersection of LLMs, Multi-Agent, and Reinforcement Learning.

How to Apply:

Interested candidates should email Dr. Yashar Moshfeghi (yashar.moshfeghi@strath.ac.uk) and include the following attachments:

• Cover letter detailing contact information, motivation, background, and proposed research direction (max 3 pages).
• Up-to-date CV.
• Transcripts and certificates of all degrees.
• Two references, one academic.

Contact Dr. Yashar Moshfeghi to express interest. Applications will be processed on a ‘first come, first served’ basis, and the hiring process will conclude as soon as a suitable candidate is identified.

We are committed to inclusion across race, gender, age, religion, identity, and experience, and we believe that diversity makes us stronger by bringing in new ideas and perspectives. The University of Strathclyde was established in 1796 as “the place of useful learning”. This remains at the forefront of our vision today for Strathclyde to be a leading international technological university that makes a positive difference in the lives of its students, society and the world. Strathclyde was the first institute to win the coveted Times Higher Education “University of the Year” award twice, in 2012 and 2019, and has since been voted the Scottish University of the Year in 2020.