search

iMeanAI / WebCanvas

Connect agents to live web environments evaluation.
https://www.imean.ai/web-canvas
MIT License
198 stars 11 forks source link
agent benchmark-framework llm-agent llm-evaluation

readme

WebCanvas: Streamline Your Web Agent Development and Evaluation

License MIT Python Version 3.11 GitHub Issues PRs Welcome GitHub Stars GitHub Forks

Platform Platform • Paper Paper • Dataset Dataset • Discord Discord • Twitter Twitter • WeChat WeChat

Existing benchmarks for web agent tasks are either offline and static, or operate within a fully reproducible environment with limited Internet dynamics. The WebCanvas project aims to pioneer the online evaluation of web agents. Additionally, we offer a suite of toolkits for scaling and maintaining web agent data to support this endeavor. We welcome any constructive feedback on the project and look forward to partnering with you in developing agents for web tasks!

Main Figure

🔥 News

🌟Features

🚀 Roadmap

📋 TODO

🔍 Evaluation on Existing WebCanvas Benchmarks

Setting Up the Environment

First, ensure your environment is ready by installing the necessary dependencies:

conda create -n webcanvas python=3.11
conda activate webcanvas
pip install -r requirements.txt

Before running the repos, you need to set up the required API keys as using features dependent on external APIs. Please refer to this docs.

Recommended Environment for Mind2Web-Live

From our experiments, the experimental environment plays a crucial role in agent performance. We recommend experimenting on a Windows server using Chrome or Firefox browser engines, preferably on servers located in the United States. Below is the experiment results on Mind2Web-Live test set.

Planning Model IP Region System Browser Completion Rate Task Success Rate Efficiency Score
gpt-3.5-turbo-0125 United States Windows Chrome 40.2% 16.5% 3.03
gpt-3.5-turbo-0125 United States Windows Firefox 42.1% 20.2% 2.79
gpt-3.5-turbo-0125 United States Linux Chrome 36.5% 15.4% 3.33
gpt-3.5-turbo-0125 United Kingdom Windows Chrome 23.6% 8.65% 7.78
gpt-3.5-turbo-0125 Singapore Windows Chrome 42.3% 21.2% 2.95

Download Raw Data of a Challenge(includes all open challenges on WebCanvas platform)

Register on the platform here.

First, ensure your environment variables are correctly set so that the code can access the necessary credentials and URL.

export GRAPHQL_USERNAME=your_username
export GRAPHQL_PASSWORD=your_password

If you registered using your Google account, please setup a password in the profile page on iMean Builder.

To download a file, use the following command:

python data/dataset_io.py download \
    --challenge-id your_challenge_id \
    --save-path /path/to/save/file

Process the Raw Data

The raw data contain rich information on step level to inspire future research. However, it's not for our evaluation.

To process the raw data, run the follow command:

python data/raw_data_processor.py \
    --input-file path/to/input/file \
    --output-file path/to/output/file

Run the Evaluation

You can run the repos with the following command:

python evaluate.py \
    --global_reward_mode dom_reward \
    --index -1 \
    --single_task_name "Find Dota 2 game and add all DLC to cart in steam." \
    --planning_text_model gpt-4o-mini \
    --global_reward_text_model gpt-4o-mini

This command runs the script with DOM-based self-reward, processing the default task "Find Dota 2 game and add all DLC to cart in steam" or using the default data index -1. It also uses the GPT-3.5 Turbo model for both observation and global reward processing. The evaluation mode is controlled by the task_mode parameter in configs/setting.toml, allowing you to choose between batch mode and single mode(without automatic evaluation). Remember to specify your path to the test file in configs/setting.toml.

Parameter Descriptions

This program supports several command-line arguments to customize its behavior:

Interaction Mode

Evaluating web agents in an online environment can sometimes be painful due to issues like network problems or bot tests on certain websites. Adopting an evaluation method that accommodates these issues allows for an accurate assessment of an agent's performance under specific current conditions. Additionally, we provide a more flexible interaction mode, enabling users to manually solve environmental issues and get the optimized performance of their web agents. You can simply set the interaction_mode parameter in configs/setting.toml to enable this feature. We will accumulate our implementation on error handling in online agent inference, and try to minimize human efforts by triggering only when exceptions occur in the following version.

Upload the Result for a Challenge

IMPORTANT: You should upload the generated out.json file to participate a challenge. To upload your result, use the following command:

python data/dataset_io.py upload \
    --file-path /path/to/your/file \
    --challenge-id your_challenge_id \
    --name your_agent_name \
    --base-model your_agent_base_model

Replace the placeholders with your actual values:

You can also submit through our platform. We will conduct an official check on your submission to prevent cheating.

Token Consumption Calculation

We provide a token consumption calculation functionality for evaluating the efficiency of your agent, and it is enabled automatically. The token consumption is calculated based on the number of tokens consumed by planning module and global reward reasoning module(if applicable) during the evaluation process. The token consumption calculation results of each experiment will be saved in the token_results folder in JSON format.

We use the tiktoken package to calculate the consumption of tokens. For those models whose encodings cannot be obtained, the default encoding "cl100k_base" is used. Therefore, for non-OPENAI models, the calculated tokens may have certain deviations.

The amount spent on tokens is only available when the model name is provided in the 'token_pricing' under setting.toml; otherwise, only the quantity of tokens will be counted. If you want to calculate the monetary expenditure of models not listed in 'token_pricing', you should first add the full name of the model (such as "gpt-4o-2024-05-13") to the 'pricing_models' list. Then, add the unit price of input and output for this model below the list, such as "gpt-4o-2024-05-13_input_price = 0.000005" and "gpt-4o-2024-05-13_output_price = 0.000015".

Few example results on Mind2Web-Live test set:

Planning Model Completion Score Task Success Rate USD Efficiency Score
GPT-4o-2024-05-13 51.4% 28.8% 0.142
Llama-3.1-405B-Instruct-Turbo 47.8% 24.0% 0.174
Llama-3.1-70B-Instruct-Turbo 44.8% 20.2% 0.031
GPT-4o-mini-2024-07-18 42.9% 21.2% 0.004
GPT-3.5-turbo-0125 42.5% 17.3% 0.092

📊 Create Your Own Benchmark Dataset

You can follow instructions on this documentation about how to create your own challenging benchmark for web agents.

Currently, you need to set up a challenge(you can keep it private at first) on WebCanvas Platform to download raw data of your dataset.

If your are thinking of scaling your Web trajectory data for training and evaluation, you can contact us directly for some technical assistance.

Demo video:

Demo video

🤝 Contributing

We welcome contributions to WebCanvas!

Thank you for your interest in improving WebCanvas. Your contributions are greatly appreciated and essential to the growth and success of our project. Please refer to the roadmap and TODOs for promising directions.

🌐 Community

We are building a vibrant and inclusive community around WebCanvas! Join our community to stay up-to-date with the latest developments and to contribute to the project:

📢 Feedback

We value your feedback and suggestions!

Citation

If you use this project in your research, please cite our paper:

@article{pan2024webcanvas,
  title={WebCanvas: Benchmarking Web Agents in Online Environments},
  author={Pan, Yichen and Kong, Dehan and Zhou, Sida and Cui, Cheng and Leng, Yifei and Jiang, Bing and Liu, Hangyu and Shang, Yanyi and Zhou, Shuyan and Wu, Tongshuang and others},
  journal={arXiv preprint arXiv:2406.12373},
  year={2024}
}

References

[^1]: Deng, Xiang, et al. "Mind2web: Towards a generalist agent for the web." Advances in Neural Information Processing Systems 36 (2024). [^2]: Zhou, Shuyan, et al. "Webarena: A realistic web environment for building autonomous agents." arXiv preprint arXiv:2307.13854 (2023). [^3]: Mialon, Grégoire, et al. "Gaia: a benchmark for general ai assistants." arXiv preprint arXiv:2311.12983 (2023). [^4]: Drouin, Alexandre, et al. "WorkArena: How Capable are Web Agents at Solving Common Knowledge Work Tasks?." arXiv preprint arXiv:2403.07718 (2024). [^5]: Zheng, Boyuan, et al. "Gpt-4v (ision) is a generalist web agent, if grounded." arXiv preprint arXiv:2401.01614 (2024).