{"id":27921520,"url":"https://github.com/cs194group/multi-agent-misconceptions","last_synced_at":"2025-05-13T15:40:11.777Z","repository":{"id":264112990,"uuid":"892354075","full_name":"CS194Group/multi-agent-misconceptions","owner":"CS194Group","description":"A multi-agent system predicting student misconceptions using the Exchange-of-Thought (EoT) framework, utilizing dspy and OpenAI to process questions, generate misconceptions, and evaluate semantic similarities.","archived":false,"fork":false,"pushed_at":"2024-12-20T06:34:11.000Z","size":19172,"stargazers_count":4,"open_issues_count":0,"forks_count":1,"subscribers_count":0,"default_branch":"final","last_synced_at":"2025-05-06T21:08:34.198Z","etag":null,"topics":["dspy","eot","machine-learning","multi-agent-systems","openai-api"],"latest_commit_sha":null,"homepage":"https://cs194group-misconception-webpage-home-ff9be8.streamlit.app","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/CS194Group.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2024-11-22T00:34:12.000Z","updated_at":"2024-12-27T18:06:10.000Z","dependencies_parsed_at":null,"dependency_job_id":"8153249c-a5a1-4634-87c5-154bf90b2b49","html_url":"https://github.com/CS194Group/multi-agent-misconceptions","commit_stats":null,"previous_names":["cs194group/multi-agent-misconceptions"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CS194Group%2Fmulti-agent-misconceptions","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CS194Group%2Fmulti-agent-misconceptions/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CS194Group%2Fmulti-agent-misconceptions/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/CS194Group%2Fmulti-agent-misconceptions/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/CS194Group","download_url":"https://codeload.github.com/CS194Group/multi-agent-misconceptions/tar.gz/refs/heads/final","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":252769422,"owners_count":21801378,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["dspy","eot","machine-learning","multi-agent-systems","openai-api"],"created_at":"2025-05-06T21:08:45.051Z","updated_at":"2025-05-06T21:08:48.470Z","avatar_url":"https://github.com/CS194Group.png","language":"Jupyter Notebook","readme":"# Multi-Agent Misconception Analysis System\n\nA multi-agent system designed to enhance learning environments by predicting student misconceptions based on their answers to questions. This project uses **dspy** and **OpenAI** to process questions, generate potential misconceptions, and evaluate semantic similarities between these misconceptions, facilitating a deeper understanding of student reasoning.\n\n## Features\n\n- **Multi-Agent Communication**: Implements the Exchange-of-Thought (EoT) framework inspired by large language model communication paradigms like Memory, Report, Relay, and Debate.\n- **Misconception Prediction**: Identifies the reasoning behind incorrect answers provided by students.\n- **Semantic Evaluation**: Analyzes and ranks misconceptions based on their similarity to student reasoning.\n\n## Getting Started\n\n### Prerequisites\n\n- Python 3.8+\n- `dspy` library\n- OpenAI API key\n\n### Installation\n\n1. Clone the repository:\n\n   ```bash\n   git clone https://github.com/CS194Group/multi-agent-misconceptions.git\n   cd multi-agent-misconceptions\n   ```\n\n2. Install required dependencies:\n   ```bash\n   pip install -r requirements.txt\n   ```\n\n### Usage\n\n#### Training and Evaluation\n\nRun the main script to process questions and evaluate misconceptions:\n`bash\n    python main.py\n    `\n\n#### Data\n\nPlace your training, testing, and validation datasets in the `data/` directory.\n\n### Project Structure\n\n- `agents/`: Contains multi-agent logic for generating and evaluating misconceptions.\n- `data/`: Includes training, testing, and validation datasets.\n- `dataloader.py`: Preprocessing and data loading utilities.\n- `evaluation.py`: Performance evaluation and reporting tools.\n- `main.py`: Entry point for training and inference.\n- `predictmode.py`: Prediction logic for generating misconceptions.\n\n### Structure of .env File \n    \n```bash\nLAMBDA_API_KEY=\"\"\nLAMBDA_API_BASE=\"https://api.lambdalabs.com/v1/\"\nLAMBDA_API_MODEL=\"llama3.1-70b-instruct-berkeley\"\nOPENAI_API_KEY=\"\"\nWANDB_API_KEY=\"\"\n```","funding_links":[],"categories":[],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcs194group%2Fmulti-agent-misconceptions","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fcs194group%2Fmulti-agent-misconceptions","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcs194group%2Fmulti-agent-misconceptions/lists"}