OpenSage: Self-programming Agent Generation Engine

TL;DR

OpenSage introduces an autonomous agent development kit that enables large language models to self-generate agent topologies, toolsets, and structured memory, improving performance and reducing human intervention.

Contribution

It is the first ADK allowing LLMs to automatically create and manage agent components and memory, advancing towards AI-centered agent development.

Findings

OpenSage outperforms existing ADKs on three benchmarks.

Hierarchical memory improves agent efficiency.

Self-generated topology enhances agent adaptability.

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. 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.