adaptive_learning_agent: student misconception detection example

Feature Description

I'd like to add a new example under simple_ai_agents/ called adaptive_learning_agent.

It's a small Streamlit app that takes a student's answer to a quiz question, uses an LLM (Gemini) to classify whether the answer is correct and, if wrong, what type of misconception it reflects (e.g. a specific calculation error vs. a conceptual misunderstanding). It then displays a simple mastery/knowledge-gap score for that topic.

This fits the "straightforward, practical use-case" category and uses Gemini via the free-tier API, consistent with other examples in the repo. I'll follow the folder structure, README template, requirements.txt, and .env.example conventions described in CONTRIBUTING.md.

I'm working on this as part of a college hackathon and would like to submit it as a PR in the next few days.

Target Project

No response

Project Directory

advance_ai_agents

Motivation

No response

Proposed Solution

No response

User Impact

No response

Alternatives Considered

No response

Screenshots/Mockups

No response

Implementation Checklist

• I have searched for similar feature requests
• I have provided a detailed description of the feature
• I have explained the motivation and user impact
• I have considered alternative solutions