Salvato in:
| Autori principali: | , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2510.06579 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866911197393059840 |
|---|---|
| author | Yu, Haofei Xuan, Keyang Li, Fenghai Zhu, Kunlun Lei, Zijie Zhang, Jiaxun Qi, Ziheng Richardson, Kyle You, Jiaxuan |
| author_facet | Yu, Haofei Xuan, Keyang Li, Fenghai Zhu, Kunlun Lei, Zijie Zhang, Jiaxun Qi, Ziheng Richardson, Kyle You, Jiaxuan |
| contents | Automatic research with Large Language Models (LLMs) is rapidly gaining importance, driving the development of increasingly complex workflows involving multi-agent systems, planning, tool usage, code execution, and human-agent interaction to accelerate research processes. However, as more researchers and developers begin to use and build upon these tools and platforms, the complexity and difficulty of extending and maintaining such agentic workflows have become a significant challenge, particularly as algorithms and architectures continue to advance. To address this growing complexity, TinyScientist identifies the essential components of the automatic research workflow and proposes an interactive, extensible, and controllable framework that easily adapts to new tools and supports iterative growth. We provide an open-source codebase, an interactive web demonstration, and a PyPI Python package to make state-of-the-art auto-research pipelines broadly accessible to every researcher and developer. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_06579 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | TinyScientist: An Interactive, Extensible, and Controllable Framework for Building Research Agents Yu, Haofei Xuan, Keyang Li, Fenghai Zhu, Kunlun Lei, Zijie Zhang, Jiaxun Qi, Ziheng Richardson, Kyle You, Jiaxuan Computation and Language Automatic research with Large Language Models (LLMs) is rapidly gaining importance, driving the development of increasingly complex workflows involving multi-agent systems, planning, tool usage, code execution, and human-agent interaction to accelerate research processes. However, as more researchers and developers begin to use and build upon these tools and platforms, the complexity and difficulty of extending and maintaining such agentic workflows have become a significant challenge, particularly as algorithms and architectures continue to advance. To address this growing complexity, TinyScientist identifies the essential components of the automatic research workflow and proposes an interactive, extensible, and controllable framework that easily adapts to new tools and supports iterative growth. We provide an open-source codebase, an interactive web demonstration, and a PyPI Python package to make state-of-the-art auto-research pipelines broadly accessible to every researcher and developer. |
| title | TinyScientist: An Interactive, Extensible, and Controllable Framework for Building Research Agents |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2510.06579 |