AgentScope 1.0: A Developer-Centric Framework for Building Agentic Applications
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866916912093462528 |
|---|---|
| author | Gao, Dawei Li, Zitao Xie, Yuexiang Kuang, Weirui Yao, Liuyi Qian, Bingchen Ma, Zhijian Cui, Yue Luo, Haohao Li, Shen Yi, Lu Yu, Yi He, Shiqi Luo, Zhiling Zhou, Wenmeng Zhang, Zhicheng He, Xuguang Chen, Ziqian Liao, Weikai Kushnazarov, Farruh Isakulovich Li, Yaliang Ding, Bolin Zhou, Jingren |
| author_facet | Gao, Dawei Li, Zitao Xie, Yuexiang Kuang, Weirui Yao, Liuyi Qian, Bingchen Ma, Zhijian Cui, Yue Luo, Haohao Li, Shen Yi, Lu Yu, Yi He, Shiqi Luo, Zhiling Zhou, Wenmeng Zhang, Zhicheng He, Xuguang Chen, Ziqian Liao, Weikai Kushnazarov, Farruh Isakulovich Li, Yaliang Ding, Bolin Zhou, Jingren |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_16279 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | AgentScope 1.0: A Developer-Centric Framework for Building Agentic Applications Gao, Dawei Li, Zitao Xie, Yuexiang Kuang, Weirui Yao, Liuyi Qian, Bingchen Ma, Zhijian Cui, Yue Luo, Haohao Li, Shen Yi, Lu Yu, Yi He, Shiqi Luo, Zhiling Zhou, Wenmeng Zhang, Zhicheng He, Xuguang Chen, Ziqian Liao, Weikai Kushnazarov, Farruh Isakulovich Li, Yaliang Ding, Bolin Zhou, Jingren Artificial Intelligence 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. |
| title | AgentScope 1.0: A Developer-Centric Framework for Building Agentic Applications |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2508.16279 |