AgentSPEX: An Agent SPecification and EXecution Language
Published in arXiv preprint, 2026
AgentSPEX is an Agent SPecification and EXecution Language for specifying LLM-agent workflows with explicit control flow and modular structure, along with a customizable agent harness. It supports typed steps, branching and loops, parallel execution, reusable submodules, and explicit state management; workflows execute within an agent harness that provides tool access, a sandboxed virtual environment, and support for checkpointing, verification, and logging. We also provide a visual editor with synchronized graph and workflow views for authoring and inspection, ship ready-to-use agents for deep research and scientific research, evaluate AgentSPEX on 7 benchmarks, and show through a user study that AgentSPEX offers a more interpretable and accessible workflow-authoring paradigm than a popular existing agent framework. Project page: agentspex.ai. Code: ScaleML/AgentSPEX.
Recommended citation: Pengcheng Wang*, Jerry Huang*, Jiarui Yao*, Rui Pan, Peizhi Niu, Yaowenqi Liu, Ruida Wang, Renhao Lu, Yuwei Guo, & Tong Zhang (2026). AgentSPEX: An Agent SPecification and EXecution Language. arXiv preprint arXiv:2604.13346.
Download Paper