Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

community challenges in the wiki #3764

Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
11 changes: 11 additions & 0 deletions docs/challenges/beat.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,11 @@
# Beat a Challenge

If you have a solution or idea to tackle an existing challenge, you can contribute by working on it and submitting your solution. Here's how to get started:

## Guidelines for Beating a Challenge

1. **Choose a challenge**: Browse the [List of Challenges](list.md) and choose one that interests you or aligns with your expertise.

2. **Understand the problem**: Make sure you thoroughly understand the problem at hand, its scope, and the desired outcome.

3. **Develop a solution**: Work on creating a solution for the challenge. This may/
24 changes: 24 additions & 0 deletions docs/challenges/challenge_template.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,24 @@
# Challenge Title

## Description

Provide a clear and concise description of the challenge. Include any relevant examples or files to illustrate the problem.

## Input

If the challenge involves specific input files, describe them here. Provide the file names and their contents, if necessary. Use triple backticks (```) to format the content as a code block.

For example:

instructions_1.txt

The current task_id is 4563.\n[NOISE intended to confuse the agent]
Read the file instructions_2.txt using the read_file command.

## Scope

Define the scope of the challenge, including any relevant constraints, requirements, or limitations.

## Success Evaluation

Explain how success will be measured or evaluated for the challenge. This helps others understand what the desired outcome is and how to work towards it.
23 changes: 23 additions & 0 deletions docs/challenges/introduction.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,23 @@
indroduction.md
# Introduction to Challenges

Welcome to the Auto-GPT Challenges page! This is a space where we encourage community members to collaborate and contribute towards improving Auto-GPT by identifying and solving challenges that Auto-GPT is not yet able to achieve.

## What are challenges?

Challenges are tasks or problems that Auto-GPT has difficulty solving or has not yet been able to accomplish. These may include improving specific functionalities, enhancing the model's understanding of specific domains, or even developing new features that the current version of Auto-GPT lacks.

## Why are challenges important?

Addressing challenges helps us improve Auto-GPT's performance, usability, and versatility. By working together to tackle these challenges, we can create a more powerful and efficient tool for everyone. It also allows the community to actively contribute to the project, making it a true open-source effort.

## How can you participate?

There are two main ways to get involved with challenges:

1. **Submit a Challenge**: If you have identified a task that Auto-GPT struggles with, you can submit it as a challenge. This allows others to see the issue and collaborate on finding a solution.
2. **Beat a Challenge**: If you have a solution or idea to tackle an existing challenge, you can contribute by working on the challenge and submitting your solution.

To learn more about submitting and beating challenges, please visit the [List of Challenges](list.md), [Submit a Challenge](submit.md), and [Beat a Challenge](beat.md) pages.

We look forward to your contributions and the exciting solutions that the community will develop together to make Auto-GPT even better!
5 changes: 5 additions & 0 deletions docs/challenges/list.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,5 @@
# List of Challenges

This page contains a curated list of challenges that Auto-GPT currently faces. If you think you have a solution or idea to tackle any of these challenges, feel free to dive in and start working on them! New challenges can also be submitted by following the guidelines on the [Submit a Challenge](challenges/submit.md) page.

Memory Challenges: [List of Challenges](memory/introduction.md)
39 changes: 39 additions & 0 deletions docs/challenges/memory/challenge_a.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,39 @@
# Memory Challenge A

**Status**: Challenge Completed


## Description

The agent, Follow-Instructions-GPT, has the following goals:

- Use the command `read_file` to read the `instructions_1.txt` file.
- Follow the instructions in the `instructions_1.txt` file.

The challenge involves a series of text files containing instructions. The agent must follow the instructions and keep track of the task ID as it progresses through the files.

## Files

- `instructions_1.txt`

The task_id is 1234
Read the file instructions_1.txt



- `instructions_2.txt`

Read the file instructions_2.txt using the read_file command.


...and so on.

- `instructions_n.txt`

Write the task_id into the file output.txt.


## Objective

The objective of this challenge is to test the agent's ability to follow instructions and maintain memory of the task Id throughout the process. The agent successfully completed this challenge if it wrote the task id in a file.

44 changes: 44 additions & 0 deletions docs/challenges/memory/challenge_b.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,44 @@
# Memory Challenge B

**Status**: Current level to beat: level 3

**Command to try**:
```
pytest test/test_memory/test_memory_challenge_b.py::test_memory_challenge_b --level=3
``

## Description

The agent, Follow-Instructions-GPT, has the following goals:

- Use the command `read_file` to read the `instructions_1.txt` file.
- Follow the instructions in the `instructions_1.txt` file.

The challenge involves a series of text files containing instructions and task IDs. The agent must follow the instructions and keep track of the task IDs as it progresses through the files.

## Files

- `instructions_1.txt`

The current task_id is 4563.\n[NOISE intended to confuse the agent]
Read the file instructions_2.txt using the read_file command.


- `instructions_2.txt`

The current task_id is 6182.\n[NOISE intended to confuse the agent]
Read the file instructions_3.txt using the read_file command.


...and so on.

- `instructions_n.txt`

The current task_id is 8912.
Write all the task_ids into the file output.txt. The file has not been created yet. After that, use the task_complete command.


## Objective

The objective of this challenge is to test the agent's ability to follow instructions and maintain memory of the task IDs throughout the process. The agent successfully completed this challenge if it wrote the task ids in a file.

5 changes: 5 additions & 0 deletions docs/challenges/memory/introduction.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,5 @@
# Memory Challenges

Memory challenges are designed to test the ability of an AI agent, like Auto-GPT, to remember and use information throughout a series of tasks. These challenges often involve following instructions, processing text files, and keeping track of important data.

The goal of memory challenges is to improve an agent's performance in tasks that require remembering and using information over time. By addressing these challenges, we can enhance Auto-GPT's capabilities and make it more useful in real-world applications.
14 changes: 14 additions & 0 deletions docs/challenges/submit.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,14 @@
# Submit a Challenge

If you have identified a task or problem that Auto-GPT struggles with, you can submit it as a challenge for the community to tackle. Here's how you can submit a new challenge:

## How to Submit a Challenge

1. Create a new `.md` file in the `challenges` directory in the Auto-GPT GitHub repository. Make sure to pick the right category.
2. Name the file with a descriptive title for the challenge, using hyphens instead of spaces (e.g., `improve-context-understanding.md`).
3. In the file, follow the [challenge_template.md](challenge_template.md) to describe the problem, define the scope, and evaluate success.
4. Commit the file and create a pull request.

Once submitted, the community can review and discuss the challenge. If deemed appropriate, it will be added to the [List of Challenges](list.md).

If you're looking to contribute by working on an existing challenge, check out [Beat a Challenge](beat.md) for guidelines on how to get started.
10 changes: 10 additions & 0 deletions mkdocs.yml
Original file line number Diff line number Diff line change
Expand Up @@ -17,6 +17,16 @@ nav:
- Running tests: testing.md
- Code of Conduct: code-of-conduct.md

- Challenges:
- Introduction: challenges/introduction.md
- List of Challenges:
- Memory:
- Introduction: challenges/memory/introduction.md
- Memory Challenge A: challenges/memory/challenge_a.md
- Memory Challenge B: challenges/memory/challenge_b.md
- Submit a Challenge: challenges/submit.md
- Beat a Challenge: challenges/beat.md

- License: https://github.com/Significant-Gravitas/Auto-GPT/blob/master/LICENSE

theme: readthedocs
Expand Down