CS372: Artificial Intelligence for Reasoning, Planning, and Decision Making

Course Overview

Join us for an audacious aim—elevating LLMs from pattern matching to conscious reasoning, validation, and planning.

Large Language Models (LLMs) have revolutionized AI through remarkable pattern matching capabilities. However, the path to Artificial General Intelligence (AGI) requires advancing beyond unconscious, reactive processing (automatic, stimulus-response behavior) to deliberate reasoning and validated planning. This course explores approaches to enhance LLMs with AGI-oriented capabilities through systematic reasoning, planning, and decision-making.

Core Questions:

1. How can we enable LLMs to transition from pattern matching to conscious deliberation?
2. What frameworks support robust reasoning and verifiable decisions?
3. How do we implement planning and temporal awareness in LLM systems?
4. What role does multi-LLM agent collaboration play in advancing toward AGI capabilities?
5. More generally, what are the limitations of the current LLM architecture to overcome?

The course examines:

1. Theoretical foundations of consciousness, reasoning, and planning in AI
2. Multi-LLM Agent Collaborative Intelligence (MACI) frameworks
3. Entropy-guided information exchange
4. AI ethical alignment with checks and balance
5. Linguistic behavior modeling
6. Persistent memory management for validation and long-live workflow.
7. Temporal reasoning and planning system architectures

Through lectures, discussions, and hands-on projects, students will explore and implement multi-agent systems that advance beyond current state-of-the-art frameworks (e.g., LangGraph) to address planning problems across various domains, including project planning, supply chain management, emergency room logistics, and natural disaster response.

1. Assignments 30%
2. Dashes: 20%
3. Final Presentation and Report: 40%
4. Class Participation: 10%