| | --- |
| | license: apache-2.0 |
| | language: |
| | - en |
| | pipeline_tag: text-generation |
| | library_name: transformers |
| | --- |
| | |
| | # Introduction |
| |
|
| | We present **UniScientist**, an agentic large language model featuring 30 billion total parameters, with only 3 billion activated per token. Developed by UniPat AI, the model is specifically designed for **universal scientific research** tasks spanning 50+ disciplines. UniScientist achieves state-of-the-art performance across a range of research benchmarks, including FrontierScience-Research, FrontierScience-Olympiad, DeepResearch Bench, DeepResearch Bench II, and ResearchRubrics. |
| |
|
| | More details can be found in our [Blog](https://unipat.ai/blog/UniScientist). |
| |
|
| | ## Key Features |
| |
|
| | - **Evolving Polymathic Synthesis**: A human-LLM collaborative data paradigm that generates research-grade scientific problems across 50+ disciplines, each accompanied by co-evolved rubrics refined through completeness, consistency, and distinguishability checks. |
| | - **Agentic Research Loop**: The model conducts scientific research by iteratively acquiring evidence, deriving formally-justified results, and updating hypotheses via abductive inference, using tools including `web_search`, `google_scholar`, `page_fetching`, and `code_interpreter`. |
| | - **Report Aggregation**: Given multiple candidate research reports, the model learns to synthesize a consolidated report integrating the best elements, enabling research quality to self-evolve over time. |
| |
|
| | ## Download |
| |
|
| | You can download the model then run the inference scripts in https://github.com/UniPat-AI/UniScientist. |
| |
|
| | ```bibtex |
| | @misc{unipat2026uniscientist, |
| | title = {UniScientist: Advancing Universal Scientific Research Intelligence}, |
| | author = {UniPat AI Team}, |
| | year = {2026}, |
| | howpublished = {\url{https://github.com/UniPat-AI/UniScientist}} |
| | } |
| | ``` |
| |
|
