The Year in AI Papers
The year/Independent research

Paper 2508.16279

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

Dawei Gao, Zitao Li, Yuexiang Xie, Weirui Kuang, Liuyi Yao, Bingchen Qian, Zhijian Ma, Yue Cui, Haohao Luo, Shen Li, Lu Yi, Yi Yu, et al.

Published
Aug 2025
Research lab
Independent
Citations
11
GitHub
29K stars

01 In brief

Summary

AgentScope 1.0 is a developer-centric framework for building agentic applications, grounded in the ReAct paradigm.

It provides foundational components (message, model, memory, tool) with unified interfaces and extensible modules, supporting multimodal messages, diverse LLM providers, and MCP integration.

The framework includes agent-level infrastructure with parallel tool calls, asynchronous execution, real-time steering, state persistence, and non-invasive customization via hooks.

Built-in agents include a Deep Research Agent, Browser-use Agent, and Meta Planner.

Multi-agent applications are supported via agent-as-a-tool and pipelines/message hubs.

Developer-friendly toolkits include an evaluation module (GeneralEvaluator and RayEvaluator), a Studio visual interface for tracing and evaluation visualization, and a Runtime with an Engine and Sandbox for secure deployment.

The framework aims to bridge prototype agents and real-world applications, offering scalability, adaptability, and efficiency.

02 From the paper

Abstract

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.