We reproduce the workflow in \cite{polhill2017lessons}, based on
\cite{polhill2013nonlinearities}, using our provenance framework. The paper
documents an attempt to replicate the output analysis of a large social
simulation (FEARLUS-SPOMM). The provenance framework is used in this case to
capture ``coarse-grained'' provenance, specifically inputs, outputs, and code
versions. The main aim of this paper is to demonstrate that results can be
reproduced simply and predictably using this provenance framework. By inspection
of the outputs of the analysis that were included, the reproduction was a
success. This process produces a database of metadata of considerable size.

This extended abstract presents a dual-LLM supervised workflow for replicating the Ya-TASERPS agent-based model from NetLogo to Mesa. Treating the v1.0.0 NetLogo model as the canonical source, we validate the Mesa replication against NetLogo at three levels: structural parity, directional scenario checks, and large-run comparisons. The Mesa model preserves key structural features, reproduces the qualitative response of the source model to substantively important parameter changes, and matches broad significance patterns in large-run analyses. The case suggests that carefully supervised LLM-assisted workflows can support credible cross-platform replication while lowering practical barriers to auditable model reimplementation.

Agent-Based Modelling (ABM) relies on clear documentation to ensure credibility and transparency. Although standards exist for documenting models (e.g. ODD), processes (e.g. TRACE, EABSS), and data use (e.g. RAT-RS), their adoption remains limited due to the effort required to produce documentation that is often treated as supplementary. This paper explores the use of Large Language Models (LLMs) to facilitate and partially automate such processes. We conduct a feasibility study focusing on the underused Rigour and Transparency Reporting Standard (RAT-RS), using four LLMs to extract reports from a published ABM paper. We assess consistency and performance across question types, finding that LLMs generate coherent outputs and perform more reliably on descriptive than on explanatory or evaluative tasks. While LLMs can improve reporting quality and consistency, they also exhibit notable limitations. We identify practical heuristics for when LLM-assisted documentation is reliable and when human oversight is needed and call for systematic community-level exploration to enhance rigour and adoption in ABM reporting.