12.03 — Section Resources
Overview
This lesson provides references to the academic paper, implementation resources, and tools used throughout the Reflexion Agent section.
Research Paper
| Resource |
Details |
| Paper |
Reflexion: Language Agents with Verbal Reinforcement Learning |
| Authors |
Noah Shinn, Federico Cassano, Ashwin Gopinath, Karthik Narasimhan, Shunyu Yao |
| Institutions |
Northeastern University, MIT, Princeton University |
| Key Idea |
Agents that verbally reflect on task feedback signals, maintaining a self-reflective text in episodic memory to improve decision-making in subsequent trials |
The Reflexion paper formalizes the pattern of iterative self-improvement through verbal self-reflection — exactly what this section implements.
Implementation References
| Resource |
Description |
| LangChain Blog |
The LangChain team (particularly Lance Martin) published a blog post implementing the Reflexion architecture with LangGraph. This course's implementation is a refactored, simplified version of that work. |
| Course Repository |
All code for this section is available in the course repository under projects/reflexion-agent branch. |