Date: November 24th, 2026
Time: 11:00 AM – 1:00 PM ET
Location: Zoom Meeting
Siheng Xiong
Machine Learning PhD Student
School of Electrical and Computer Engineering
Georgia Institute of Technology
Committee
- Dr. Faramarz Fekri (Advisor), Georgia Institute of Technology
- Dr. Ghassan AlRegib, Georgia Institute of Technology
- Dr. Kartik Goyal, Georgia Institute of Technology
- Dr. Suguman Bansal, Georgia Institute of Technology
- Dr. Karthikeyan Sundaresan, Georgia Institute of Technology
Abstract
Large language models (LLMs) have demonstrated strong capabilities in complex problem-solving but still face challenges in reliable multi-step reasoning, planning, and self-improvement. While chain-of-thought (CoT) prompting enables intermediate reasoning, it often lacks explicit structures to guide and verify the reasoning process. We introduce structure-driven agentic reasoning, a paradigm that integrates structured representations with adaptive reasoning and learning to improve LLM capabilities. Specifically, we explore graph-based reasoning for temporal understanding and logical verification, hierarchical planning and execution, adaptive information acquisition through reinforcement learning, and experience-driven skill evolution. Extensive experiments across temporal, mathematical, logical, and knowledge-intensive tasks demonstrate improvements in reasoning accuracy, efficiency, and skill transfer. Together, these findings highlight the potential of explicit structure to support more reliable, efficient, and adaptive reasoning in LLMs.