# R-LAM: Reproducibility-Constrained Large Action Models for Scientific Workflow Automation

arXiv: https://arxiv.org/abs/2601.09749 · HTML: https://mlsanity.com/paper/2601.09749/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 21 references that are in the map.
- First posted on arXiv 12 Jan 2026.

## Builds on (most cited first, 9 of 9)

- [AgentBench: Evaluating LLMs as Agents](https://mlsanity.com/paper/2308.03688/) (2023)
- [TheAgentCompany: Benchmarking LLM Agents on Consequential Real World Tasks](https://mlsanity.com/paper/2412.14161/) (2024)
- [MedAgentBench: A Realistic Virtual EHR Environment to Benchmark Medical LLM Agents](https://mlsanity.com/paper/2501.14654/) (2025)
- [Large Action Models: From Inception to Implementation](https://mlsanity.com/paper/2412.10047/) (2024)
- [AlabOS: A Python-based Reconfigurable Workflow Management Framework for Autonomous Laboratories](https://mlsanity.com/paper/2405.13930/) (2024)
- [The (R)evolution of Scientific Workflows in the Agentic AI Era: Towards Autonomous Science](https://mlsanity.com/paper/2509.09915/) (2025)
- [WorkflowHub: a registry for computational workflows](https://mlsanity.com/paper/2410.06941/) (2024)
- [Snakemaker: Seamlessly transforming ad-hoc analyses into sustainable Snakemake workflows with generative AI](https://mlsanity.com/paper/2505.02841/) (2025)
- [Architecting Large Action Models for Human-in-the-Loop Intelligent Robots](https://mlsanity.com/paper/2512.11620/) (2025)

## Built on by (most cited first, 2 of 2)

- [Schema-Bound LLM Control of Scientific Instrumentation through Model Context Protocol Skills](https://mlsanity.com/paper/2607.17012/) (2026)
- [Harness Engineering for Predictable Agentic Systems: An Empirical Study of Deterministic Execution Constraints](https://mlsanity.com/paper/2608.26197/) (2026)

## Abstract (arXiv)

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.