dorsal/arxiv
View SchemaR-LAM: Reproducibility-Constrained Large Action Models for Scientific Workflow Automation
| Authors | Suriya Sureshkumar |
|---|---|
| Categories | |
| ArXiv ID | 2601.09749vv1 |
| URL | https://arxiv.org/abs/2601.09749 |
| License | http://arxiv.org/licenses/nonexclusive-distrib/1.0/ |
Abstract
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.
{
"annotation_id": "801aeac1-a96c-4d45-9561-8fb32fe0161a",
"date_created": "2026-02-17T05:53:24.050000Z",
"date_modified": "2026-02-17T05:53:24.050000Z",
"file_hash": "2b30e54f43ba6f3e69b2559816424f756bc3c8f9ec8c443a197c2f9a01b23d8d",
"private": false,
"record": {
"abstract": "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.\n 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.\n 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.",
"arxiv_id": "2601.09749",
"authors": [
"Suriya Sureshkumar"
],
"categories": [
"cs.SE",
"cs.AI",
"cs.LG"
],
"license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
"title": "R-LAM: Reproducibility-Constrained Large Action Models for Scientific Workflow Automation",
"url": "https://arxiv.org/abs/2601.09749",
"version": "v1"
},
"schema_id": "dorsal/arxiv",
"source": {
"execution_id": "4bf50532-d40d-4cbb-bf1b-685291a28867",
"id": "arXiv Dataset",
"type": "Model",
"variant": "snapshot-2026-01-17",
"version": "0.1.0"
},
"user_id": 1000002
}