AgentSPEX: An Agent SPecification and EXecution Language

TL;DR

AgentSPEX is a new language and framework for designing, executing, and visualizing structured, controllable workflows for language model agents, improving interpretability and modifiability.

Contribution

It introduces AgentSPEX, supporting explicit control flow, modularity, and visualization, addressing limitations of reactive prompting and tightly coupled frameworks.

Findings

AgentSPEX enables explicit control flow with branching and loops.

It improves interpretability and accessibility over existing frameworks.

AgentSPEX performs well on 7 benchmark tasks.

Abstract

Language-model agent systems commonly rely on reactive prompting, in which a single instruction guides the model through an open-ended sequence of reasoning and tool-use steps, leaving control flow and intermediate state implicit and making agent behavior potentially difficult to control. Orchestration frameworks such as LangGraph, DSPy, and CrewAI impose greater structure through explicit workflow definitions, but tightly couple workflow logic with Python, making agents difficult to maintain and modify. In this paper, we introduce AgentSPEX, an Agent SPecification and EXecution Language for specifying LLM-agent workflows with explicit control flow and modular structure, along with a customizable agent harness. AgentSPEX supports typed steps, branching and loops, parallel execution, reusable submodules, and explicit state management, and these workflows execute within an agent harness that provides tool access, a sandboxed virtual environment, and support for checkpointing, verification, and logging. Furthermore, we provide a visual editor with synchronized graph and workflow views for authoring and inspection. We include ready-to-use agents for deep research and scientific research, and we evaluate AgentSPEX on 7 benchmarks. Finally, we show through a user study that AgentSPEX provides a more interpretable and accessible workflow-authoring paradigm than a popular existing agent framework.