Large Action Models (LAMs) extend large language models by enabling autonomous decision-making and tool execution, making them promising for automating scientific workflows. However, scientific workflows impose strict requirements on reproducibility, auditability, and deterministic execution, which are not satisfied by generic LLM-based agents. Unconstrained action generation can lead to silent state changes, non-deterministic executions, and irreproducible experimental results, limiting the applicability of LAMs in scientific settings. In this paper, we propose R-LAM, a reproducibility-constrained framework for applying Large Action Models to scientific workflow automation. R-LAM introduces structured action schemas, deterministic execution policies, and explicit provenance tracking to ensure that every action and intermediate artifact is auditable and replayable. The framework supports failure-aware execution loops and controlled workflow forking, enabling iterative experimentation without compromising reproducibility. We implement R-LAM as a lightweight Python framework and release it as an open-source PyPI package to facilitate reproducible research. An experimental evaluation of representative scientific workflows demonstrates that R-LAM improves reproducibility success rates and execution reliability compared to unconstrained LLM-based agents, while retaining adaptive control over workflow execution.

翻译：大行动模型（LAMs）通过支持自主决策与工具执行扩展了大语言模型的能力，使其在科学工作流自动化领域展现出巨大潜力。然而，科学工作流对可复现性、可审计性与确定性执行提出了严格要求，而基于通用大语言模型的智能体无法满足这些需求。无约束的行动生成可能导致隐式状态变更、非确定性执行以及不可复现的实验结果，从而限制了大行动模型在科学场景中的应用。本文提出R-LAM——一个面向科学工作流自动化的可复现性约束大行动模型框架。R-LAM通过引入结构化行动模式、确定性执行策略与显式溯源追踪机制，确保每个行动及中间产物均可审计与重演。该框架支持故障感知执行循环与受控工作流分叉，可在保持可复现性的前提下实现迭代式实验探索。我们将R-LAM实现为轻量级Python框架，并作为开源PyPI软件包发布以促进可复现性研究。在典型科学工作流上的实验评估表明，相较于无约束的基于大语言模型的智能体，R-LAM在保持工作流执行自适应控制能力的同时，显著提升了可复现成功率与执行可靠性。