Course positioning
Taught by Edward Chang, CS 372 is a research-oriented course on moving LLMs from pattern matching to deliberate reasoning and planning. It covers multi-LLM collaboration, entropy-guided information exchange, constitutional AI, and temporal reasoning, with healthcare as an application case.
What it covers
- System 1 vs System 2: intuition and deliberate reasoning
- Multi-LLM collaboration: the MACI framework, role division, debate
- Information exchange: entropy guidance, uncertainty propagation
- Constitutional AI: principle constraints, self-correction
- Temporal reasoning and planning: time awareness, long-horizon tasks
- Applications: diagnosis, treatment planning, and more
- Project: implement an AGI-style reasoning system
Prerequisites
Machine learning and deep learning basics.
Assessment & workload
Lectures/discussion plus a hands-on project. Check the current syllabus for details.
Who it's for
Graduate students interested in AGI, reasoning, planning, and multi-agent systems; people comfortable with speculative material.
Study advice
Listen critically: some concepts (such as 'consciousness') are contested. Focus on verifiable reasoning and planning methods.
Related courses
Official course description
Course Description:Large Language Models (LLMs) have revolutionized AI through remarkable pattern matching capabilities. However, the path to Artificial General Intelligence (AGI) requires advancing beyond unconscious (System 1) to conscious (System 2) processing. This research-oriented course explores fundamental approaches to elevate LLMs toward AGI capabilities through conscious reasoning, planning, and decision-making. Core Research 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? The course examines: 1. Theoretical foundations of consciousness in AI 2. Multi-LLM Agent Collaborative Intelligence (MACI) frameworks 3. Entropy-guided information exchange 4. Constitutional AI principles 5. Temporal reasoning and planning architectures. Through lectures, discussions, and hands-on projects, students will explore practical implementations across various domains. While healthcare provides immediate applications (diagnosis, treatment planning), the principles apply broadly to any field requiring AGI-level reasoning capabilities. Prerequisites: Machine Learning, Deep Learning