Research

Overview and Motivation Presentation on integrating reinforcement learning concepts with LLM engines to improve performance Multiple approaches exist to enhance LLM performance: in-context learning, post-training (reinforcement learning), and fine-tuning Focus on efficiently integrating RL concepts with LLMs, particularly for multi-agent systems Covers differences between reinforcement learning on LLMs versus reinforcement learning on LLM agents Addresses RL implementation in HPC systems due to memory-intensive requirements Multi-Agent System Fundamentals Multi-agent systems consist of multiple LLMs, each with specific roles and functions State acts as history, compiling all previous agent turns, context, and evidence in multi-turn systems Communication Topologies ...

Overview On March 21, 2025, Dr. Mona Rahimi, an associate professor in the Computer Science department, delivered a presentation on An AI-Driven Requirements Engineering Framework Tailored for Evaluating AI-Based Software, a problem she and her students have been investigating. With the rise of AI-based software, many traditional software engineering methodologies have become ineffective. In her talk, Dr. Rahimi discussed the redefinition of requirement specification and proposed methods for aligning AI perception with requirements engineering.