Search papers, labs, and topics across Lattice.
MyAG introduces a novel graph-based framework that facilitates the design and analysis of composable LLM agent systems by employing three distinct graph abstractions: component, workflow, and search graphs. This structured approach enables the flexible reuse of components and supports hierarchical composition, allowing for more efficient execution control and performance analysis. Experimental results demonstrate that MyAG significantly enhances the design flexibility and performance-efficiency tradeoffs of agent systems, making it a valuable tool for researchers and practitioners alike.
MyAG reveals that a graph-based approach can revolutionize the design of LLM agent systems, enabling unprecedented flexibility and efficiency in execution.
We present MyAG, a graph-based framework for designing and analyzing composable LLM agent systems. Our framework separates agent system construction into three graph abstractions: a component graph for agents, environments, and modules; a workflow graph for execution control; and a search graph for runtime execution. This separation allows users to flexibly reuse the same components with different strategies. We further support hierarchical composition through recursive system nodes and provide monitoring and visualization tools for inspecting agent execution. Experiments on representative agent applications show that our framework supports flexible agent system design and helps analyze performance-efficiency tradeoffs. Our framework is publicly available and fully open-source.
