Salvato in:
Dettagli Bibliografici
Autori principali: Yu, Haofei, Xuan, Keyang, Li, Fenghai, Zhu, Kunlun, Lei, Zijie, Zhang, Jiaxun, Qi, Ziheng, Richardson, Kyle, You, Jiaxuan
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