Saved in:
| Main Authors: | , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2602.16891 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914389836169216 |
|---|---|
| author | Li, Hongwei Wang, Zhun Dai, Qinrun Nie, Yuzhou Peng, Jinjun Liu, Ruitong Zhang, Jingyang Zhu, Kaijie He, Jingxuan Wang, Lun Ding, Yangruibo Chen, Yueqi Guo, Wenbo Song, Dawn |
| author_facet | Li, Hongwei Wang, Zhun Dai, Qinrun Nie, Yuzhou Peng, Jinjun Liu, Ruitong Zhang, Jingyang Zhu, Kaijie He, Jingxuan Wang, Lun Ding, Yangruibo Chen, Yueqi Guo, Wenbo Song, Dawn |
| contents | Agent development kits (ADKs) provide effective platforms and tooling for constructing agents, and their designs are critical to the constructed agents' performance, especially the functionality for agent topology, tools, and memory. However, current ADKs either lack sufficient functional support or rely on humans to manually design these components, limiting agents' generalizability and overall performance. We propose OpenSage, the first ADK that enables LLMs to automatically create agents with self-generated topology and toolsets while providing comprehensive and structured memory support. OpenSage offers effective functionality for agents to create and manage their own sub-agents and toolkits. It also features a hierarchical, graph-based memory system for efficient management and a specialized toolkit tailored to software engineering tasks. Extensive experiments across three state-of-the-art benchmarks with various backbone models demonstrate the advantages of OpenSage over existing ADKs. We also conduct rigorous ablation studies to demonstrate the effectiveness of our design for each component. We believe OpenSage can pave the way for the next generation of agent development, shifting the focus from human-centered to AI-centered paradigms. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_16891 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | OpenSage: Self-programming Agent Generation Engine Li, Hongwei Wang, Zhun Dai, Qinrun Nie, Yuzhou Peng, Jinjun Liu, Ruitong Zhang, Jingyang Zhu, Kaijie He, Jingxuan Wang, Lun Ding, Yangruibo Chen, Yueqi Guo, Wenbo Song, Dawn Artificial Intelligence Cryptography and Security Software Engineering Agent development kits (ADKs) provide effective platforms and tooling for constructing agents, and their designs are critical to the constructed agents' performance, especially the functionality for agent topology, tools, and memory. However, current ADKs either lack sufficient functional support or rely on humans to manually design these components, limiting agents' generalizability and overall performance. We propose OpenSage, the first ADK that enables LLMs to automatically create agents with self-generated topology and toolsets while providing comprehensive and structured memory support. OpenSage offers effective functionality for agents to create and manage their own sub-agents and toolkits. It also features a hierarchical, graph-based memory system for efficient management and a specialized toolkit tailored to software engineering tasks. Extensive experiments across three state-of-the-art benchmarks with various backbone models demonstrate the advantages of OpenSage over existing ADKs. We also conduct rigorous ablation studies to demonstrate the effectiveness of our design for each component. We believe OpenSage can pave the way for the next generation of agent development, shifting the focus from human-centered to AI-centered paradigms. |
| title | OpenSage: Self-programming Agent Generation Engine |
| topic | Artificial Intelligence Cryptography and Security Software Engineering |
| url | https://arxiv.org/abs/2602.16891 |