TinyScientist: An Interactive, Extensible, and Controllable Framework for Building Research Agents

2025-10-07

AI Summary

Current large language model–driven automated scientific workflows—encompassing multi-agent collaboration, task planning, tool invocation, and code execution—suffer from poor scalability, high maintenance overhead, and inflexible integration. To address these challenges, this paper introduces LightAgent, a lightweight, modular agent framework. Methodologically, it adopts a decoupled interaction architecture that hierarchically separates planners, executors, tool adapters, and human–agent interfaces, enabling dynamic plug-and-play integration of new tools and algorithms. It supports dual-mode access via a web-based interface and a Python SDK, and is distributed as a PyPI package. The open-source implementation includes a complete codebase, an online demo, and comprehensive documentation. This significantly lowers the barrier to developing and deploying automated research systems and has been successfully applied across multiple interdisciplinary research domains.

Technology Category

• Multiagent Systems: Agent Communication
• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Search and Retrieval-Augmented AI: Agentic search
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

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.

Problem

• Addresses complexity in extending and maintaining LLM-based research workflows
• Proposes interactive framework adapting to new tools for automatic research
• Makes auto-research pipelines accessible through open-source implementation

Innovation

• Framework is interactive, extensible, and controllable
• Adapts easily to new tools and iterative growth
• Provides open-source codebase, web demo, and PyPI package