ScienceBoard

Code, environment and data for “ScienceBoard: Evaluating Multimodal Autonomous Agents in Realistic Scientific Workflows”

Docker migration: this checkout adds a Docker-native desktop backend for headless cloud servers. Runtime use does not require VMware or KVM. See the feasibility assessment, architecture, and cloud quick start. The original VMware mode is retained for compatibility and reference-image maintenance.

The local Docker pipeline is operational: all six application families initialize, the deterministic 20-task subset has completed with a real model, and a final end-to-end key-bank canary passed. Run ./run.sh --mode docker --check, then follow the cloud quick start. Known environment and upstream-service limits are tracked in known issues.

🗞️ Updates

• 2026-01-26: ScienceBoard is accepted by ICLR 2026! 🎉
• 2025-08-28: We release CODA, a dual-brain agent that achieves SOTA on ScienceBoard. 🧠
• 2025-06-30: We release new evaluation results (GUI-Actor, UI-TARS-1.5) and agent trajectories. 🎊
• 2025-06-08: ScienceBoard will be presented at WCUA@ICML 2025 as an oral paper! 🚀
• 2025-06-04: We release the virtual machine snapshot of ScienceBoard. 🌏
• 2025-05-27: Initial release of our paper, environment, benchmark, and 🌐 Project Website. Check it out! 🚀

🛠️ Usage

🐳 Docker on a headless/cloud host

After loading or building the sanitized scienceboard:0.1 image and filling .env, no VMware process or VM file is needed:

./run.sh --mode docker --check
./scripts/materialize_smoke_subset.py
./run.sh --mode docker --tasks .artifacts/smoke20 --no-ignore

Image creation/transfer, resource sizing, key-bank configuration, and full suite commands are in the cloud quick start.

📦 Legacy VMware/raw installation

The infrastructure of the framework is based on OSWorld together with VMware Workstation Pro (which is free for personal use since May, 2024) in Ubuntu or Windows. Please make sure that your device meets the minimal requirements of these preliminaries.

1. Download VMware Workstation Pro 17 and our pre-made images from Hugging Face;

2. Clone this repository and install packages needed:

   git clone https://github.com/OS-Copilot/ScienceBoard
   cd ScienceBoard
   conda create -n sci python=3.11
   conda activate sci
   pip install -r requirements.txt
   

3. We recommend you to change evaluating process in main.py directly with some sensitive information hidden in environment variables, especially when it comes to complicate configs concerning community.

[!NOTE]
Community specifies the form of cooperation in which one or more models completes the tasks. You can customize your own multi-agents system by creating a new class inheriting Community together with the method of __call__().

⚙️ Env Config

🔐 As a storage location for sensitive info

1. Used in our template of main.py:

   • VM_PATH: path to vmware .vmx file; will be automatically extracted (repeatedly) if set to path of VM.zip
   • HTTPX_PROXY: proxy URL if needed; avoid clashes with HTTP_PROXY and HTTPS_PROXY on Linux;
   • OPENAI_API_KEY: API key for OpenAI GPT;
   • GOOGLE_API_KEY: API key for Google Gemini;
   • ANTHROPIC_API_KEY: API key for Anthropic Claude;

   and variables for open-source models:

   Model	Base URL	Name
   QwenVL	QWEN_VL_URL	QWEN_VL_NAME
   InternVL	INTERN_VL_URL	INTERN_VL_NAME
   QVQ	QVQ_VL_URL	QVQ_VL_NAME
   OS-Atlas	OS_ACT_URL	OS_ACT_NAME
   GUI-Actor	GUI_ACTOR_URL	GUI_ACTOR_NAME
   UI-Tars	TARS_DPO_URL	TARS_DPO_NAME

2. Used in sci/Presets.py:

   • LEAN_LIB_PATH: path for Lean 4 REPL;
   • QT6_LIB_PATH: dynamic library directory for Qt6;
   • FFI_LIB_PATH: dynamic library file for libffi.so;
   • KALG_BIN_PATH: executable binary file of KAlgebra;
   • CELE_BIN_PATH: executable binary file of Celestia;
   • GIS_BIN_PATH: executable binary file of Grass GIS.

🧪 As a functionality

• DEBUG_ERR_FACT: insert a breakpoint when eval exception occur if set to any value;

📏 Parameter Config

1. Automata: a simple encapsulation for Model and Agent
   • model_style: affect the request format and response processing of model calling; you can customize your own style by adding _request_{style}() and _access_{style}() under Model;
   • overflow_style: affect the way we detect overflow of token; you can customize your own style by adding {style}() under Overflow;
   • code_style: affect the way we process code blocks when communicating with models; you can customize your own style by adding wrap_{style}() and extract_{style}() under CodeLike.
2. Tester: __init__() only register a new config. use __call__() for actual evaluation after init.
   • tasks_path: the directory or file path for json file(s) of task(s); all *.json files under the path specified will be recursively loaded when a directory path is provided;
   • logs_path: the directory path for log files and will be created automatically when not existed; the structure of the directory will be arranged according to that under tasks_path;
   • community: the way of cooperation among multiple agents; use AllInOne for standard setting inherited from OSWorld;
   • ignore: skipped when log indicates that the task is finished (by checking the existence of result.out) if set to True; so you can re-run the same program to retry failure cases only;
   • debug: finish the tasks manually instead of calling models;
   • relative: allow VM to execute pyautogui codes with relative coordinates; basically used by InternVL-3.

🚧 Possible Exceptions

1. Error when initializing:

   Traceback (most recent call last):
       File "/usr/lib/python3.11/site-packages/requests/models.py", line 971, in json
           return complexjson.loads(self.text, **kwargs)
               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
       File "/usr/lib/python3.11/json/__init__.py", line 346, in loads
           return _default_decoder.decode(s)
               ^^^^^^^^^^^^^^^^^^^^^^^^^^
       File "/usr/lib/python3.11/json/decoder.py", line 337, in decode
           obj, end = self.raw_decode(s, idx=_w(s, 0).end())
                   ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
       File "/usr/lib/python3.11/json/decoder.py", line 355, in raw_decode
           raise JSONDecodeError("Expecting value", s, err.value) from None
       json.decoder.JSONDecodeError: Expecting value: line 1 column 1 (char 0)
   

   the target app has not yet been started up when trying to initialize due to insufficient performance of your device; try to assign a bigger value for ‘wait’ field in json files of the tasks.

2. Failed to get accessibility tree:

   Traceback (most recent call last):
       File "os-sci/sci/Tester.py", line 396, in __call__
           counter._pass() if task_info() else counter._fail()
                           ^^^^^^^^^^^
       File "os-sci/sci/Tester.py", line 174, in __call__
           return self.task()
               ^^^^^^^^^^^
       File "os-sci/sci/base/task.py", line 175, in _avail_wrapper
           return method(self, *args, **kwargs)
               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
       File "os-sci/sci/base/task.py", line 393, in __call__
           return self.__call()
               ^^^^^^^^^^^^^
       File "os-sci/sci/base/task.py", line 381, in __call
           stop_type, stop_args = self.predict()
                               ^^^^^^^^^^^^^^
       File "os-sci/sci/base/task.py", line 175, in _avail_wrapper
           return method(self, *args, **kwargs)
               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
       File "os-sci/sci/base/log.py", line 462, in record_wrapper
           return_value = method(self)
                       ^^^^^^^^^^^^
       File "os-sci/sci/base/task.py", line 316, in predict
           invalid = self._step(step_index)
                   ^^^^^^^^^^^^^^^^^^^^^^
       File "os-sci/sci/base/task.py", line 260, in _step
           observation = {
                       ^
       File "os-sci/sci/base/task.py", line 261, in <dictcomp>
           obs_type: getattr(self.manager, obs_type)()
                   ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
       File "os-sci/sci/vm/vmanager.py", line 152, in _env_wrapper
           return method(self, *args, **kwargs)
               ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
       File "os-sci/sci/base/manager.py", line 85, in _assert_wrapper
           result = method(self)
                   ^^^^^^^^^^^^
       File "os-sci/sci/vm/vmanager.py", line 278, in a11y_tree
           a11y_tree = utils.linearize(raw_a11y_tree)
                       ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
       File "os-sci/sci/vm/utils.py", line 206, in linearize
           filtered_nodes = filter_nodes(ET.fromstring(a11y_tree), platform)
                                       ^^^^^^^^^^^^^^^^^^^^^^^^
       File "/usr/lib/python3.11/xml/etree/ElementTree.py", line 1338, in XML
           parser.feed(text)
       TypeError: a bytes-like object is required, not 'NoneType'
   

   fail to authenticate in newly downloaded images; input password once manually in VMWare and take a new snapshot using the same name as before and delete the former one.

🧑‍💻 Development Manual

🧩 Introduction of New Apps

If you are willing to add new applications into ScienceBoard, please make sure that you already have a full understanding of your target application and this repository.

1. Write a plugin or implant a server in your target application revealing its inner states. Listed below is repositories of our modified applications:
   • chimerax-states: a plugin for ChimeraX;
   • kalgebra: a recompilation copy of KAlgebra;
   • Celestia: a recompilation copy of Celestia;
   • grass-gis: GUI part in Python of Grass GIS.
2. Copy sci/Template and rename it to the name of your target application;
   • template.py: direct managers for the Raw / VM application;
   • task.py: initialization and evaluation of tasks using RESTful API with your server;
   • __init__.py: change the name of template.py.
3. Write json files of tasks and modified VM images.

🖼️ Crafting VM Image from Scratch

See Staff Manual of VM Image.

💻 Recommended Configuration

It is recommended to run this project with at least the following configuration:

• CPU: Intel Core i7-11700
• GPU: Integrated graphics is sufficient
• Memory: 32 GB RAM
• Storage: > 100 GB available disk space

📋 Citation

If you are interested in our work or find this repository / our data helpful, please consider using the following citation format when referencing our paper:

@article{sun2025scienceboard,
  title={ScienceBoard: Evaluating Multimodal Autonomous Agents in Realistic Scientific Workflows},
  author={Sun, Qiushi and Liu, Zhoumianze and Ma, Chang and Ding, Zichen and Xu, Fangzhi and Yin, Zhangyue and Zhao, Haiteng and Wu, Zhenyu and Cheng, Kanzhi and Liu, Zhaoyang and others},
  journal={arXiv preprint arXiv:2505.19897},
  year={2025}
}