AgentScope 1.0: A Developer-Centric Framework for Building Agentic Applications

Papers with Code Trending Tools

Summary

AgentScope 1.0 is released as a developer-centric framework for building agentic applications, featuring unified interfaces, async design, and runtime sandboxes.

Driven by rapid advancements of Large Language Models (LLMs), agents are empowered to combine intrinsic knowledge with dynamic tool use, greatly enhancing their capacity to address real-world tasks. In line with such an evolution, AgentScope introduces major improvements in a new version (1.0), towards comprehensively supporting flexible and efficient tool-based agent-environment interactions for building agentic applications. Specifically, we abstract foundational components essential for agentic applications and provide unified interfaces and extensible modules, enabling developers to easily leverage the latest progress, such as new models and MCPs. Furthermore, we ground agent behaviors in the ReAct paradigm and offer advanced agent-level infrastructure based on a systematic asynchronous design, which enriches both human-agent and agent-agent interaction patterns while improving execution efficiency. Building on this foundation, we integrate several built-in agents tailored to specific practical scenarios. AgentScope also includes robust engineering support for developer-friendly experiences. We provide a scalable evaluation module with a visual studio interface, making the development of long-trajectory agentic applications more manageable and easier to trace. In addition, AgentScope offers a runtime sandbox to ensure safe agent execution and facilitates rapid deployment in production environments. With these enhancements, AgentScope provides a practical foundation for building scalable, adaptive, and effective agentic applications.
Original Article
View Cached Full Text

Cached at: 05/08/26, 08:57 AM

Paper page - AgentScope 1.0: A Developer-Centric Framework for Building Agentic Applications

Source: https://huggingface.co/papers/2508.16279 Published on Aug 22, 2025

·

Submitted byhttps://huggingface.co/taesiri

taesirion Aug 25, 2025

#3 Paper of the day Authors:

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

,

Abstract

AgentScope enhances agentic applications by providing flexible tool-based interactions, unified interfaces, and advanced infrastructure based on the ReAct paradigm, supporting efficient and safe development and deployment.

Driven by rapid advancements ofLarge Language Models(LLMs), agents are empowered to combine intrinsic knowledge with dynamic tool use, greatly enhancing their capacity to address real-world tasks. In line with such an evolution,AgentScopeintroduces major improvements in a new version (1.0), towards comprehensively supporting flexible and efficient tool-based agent-environment interactions for building agentic applications. Specifically, we abstract foundational components essential for agentic applications and provide unified interfaces and extensible modules, enabling developers to easily leverage the latest progress, such as new models and MCPs. Furthermore, we ground agent behaviors in theReAct paradigmand offer advanced agent-level infrastructure based on a systematicasynchronous design, which enriches both human-agent and agent-agent interaction patterns while improving execution efficiency. Building on this foundation, we integrate severalbuilt-in agentstailored to specific practical scenarios.AgentScopealso includes robust engineering support for developer-friendly experiences. We provide a scalable evaluation module with avisual studio interface, making the development of long-trajectory agentic applications more manageable and easier to trace. In addition,AgentScopeoffers aruntime sandboxto ensure safe agent execution and facilitates rapid deployment in production environments. With these enhancements,AgentScopeprovides a practical foundation for building scalable, adaptive, and effective agentic applications.

View arXiv pageView PDFGitHub24.7kAdd to collection

Get this paper in your agent:

hf papers read 2508\.16279

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2508.16279 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2508.16279 in a dataset README.md to link it from this page.

Spaces citing this paper1

Collections including this paper28

Browse 28 collections that include this paper

Similar Articles

Very Large-Scale Multi-Agent Simulation in AgentScope

Papers with Code Trending

This paper introduces enhancements to the AgentScope platform, featuring an actor-based distributed mechanism and flexible environment support to enable scalable, efficient, and user-friendly very large-scale multi-agent simulations.