• Computer Science > Artificial Intelligence [Submitted on 18 Feb 2026] Title:OpenSage: Self-programming Agent Generation Engine View PDF HTML (experimental)Abstract: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.
Article Summaries:
- OpenSage: Self‑Programming Agent Generation Engine
Researchers have released OpenSage, a novel agent development kit (ADK) that enables large language models (LLMs) to autonomously design agents with their own topology, toolsets, and hierarchical memory. Unlike existing ADKs that require manual component design, OpenSage allows agents to create and manage sub‑agents and specialized toolkits, particularly for software‑engineering tasks. Experiments on three state‑of‑the‑art benchmarks demonstrate performance gains over current ADKs, and ablation studies confirm the contribution of each design element. The authors argue that OpenSage marks a shift toward AI‑centered agent creation, reducing human intervention in agent design.
Sources: