# CRAFTS: Collaborative Role-Adaptive Fine-Tuning of LLM Agents for Chemical Process Simulation

arXiv: https://arxiv.org/abs/2608.01369 · HTML: https://mlsanity.com/paper/2608.01369/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Medical and scientific domain agents, one of 16 directions in LLM agents and tool use.
- Builds on 11 of its 36 references that are in the map.
- First posted on arXiv 2 Aug 2026.

## Placed in

- LLM agents and tool use / [Medical and scientific domain agents](https://mlsanity.com/agents/medical-and-scientific-domain-agents/)

## Builds on (most cited first, 11 of 11)

- [OpenAI GPT-5 System Card](https://mlsanity.com/paper/2601.03267/) (2025)
- [ChemCrow: Augmenting large-language models with chemistry tools](https://mlsanity.com/paper/2304.05376/) (2023)
- [ScienceAgentBench: Toward Rigorous Assessment of Language Agents for Data-Driven Scientific Discovery](https://mlsanity.com/paper/2410.05080/) (2024)
- [Towards End-to-End Automation of AI Research](https://mlsanity.com/paper/2606.15497/) (2026)
- [LLM-guided Chemical Process Optimization with a Multi-Agent Approach](https://mlsanity.com/paper/2506.20921/) (2025)
- [UniM: A Unified Any-to-Any Interleaved Multimodal Benchmark](https://mlsanity.com/paper/2603.05075/) (2026)
- [SFILES 2.0: An extended text-based flowsheet representation](https://mlsanity.com/paper/2208.00778/) (2022)
- [Toward autocorrection of chemical process flowsheets using large language models](https://mlsanity.com/paper/2312.02873/) (2023)
- [Large Language Model Agent for User-friendly Chemical Process Simulations](https://mlsanity.com/paper/2601.11650/) (2026)
- [Sketch2Simulation: Automating Flowsheet Generation via Multi Agent Large Language Models](https://mlsanity.com/paper/2603.24629/) (2026)
- [CeProAgents: A Hierarchical Agents System for Automated Chemical Process Development](https://mlsanity.com/paper/2603.01654/) (2026)

## Abstract (arXiv)

Constructing an executable chemical-process model remains manually intensive. Chemical engineers translate underspecified requests into coupled decisions about unit operations, thermodynamics, streams, specifications, degrees of freedom (DoF), initialization, solver repair, and optimization; one error can invalidate the model. CRAFTS mirrors the staged workflow of chemical engineers by decomposing simulation building into bounded subtasks assigned to seven bounded roles, with deterministic IDAES/Pyomo gates between stages. Given a natural-language request, process flowsheet diagram (PFD) evidence, and curated chemical-engineering knowledge, Input Understanding and Intent recover requirements, constraints, and process semantics; visual, topology, and specification specialists translate them into typed simulator contracts; and Debug and Optimization support bounded repair and eligible optimization. Fine-tuning is applied to the three schema-critical visual, topology, and specification roles, while the remaining roles use untuned Qwen. The resulting VisualGraphIR, TopologyIR, SpecIR, BuildPlan, and SolveReport expose unit, port, thermodynamic, numerical, and execution decisions. Compatible constructors, property packages, and runners are attached only after semantic artifacts pass engineering gates. We introduce OpenIDAES-450, a 450-case IDAES process- simulation dataset, and evaluate the complete seven-role LangChain/LangGraph workflow through solve and eligible optimization on its frozen 82-case held-out split. CRAFTS completes the prescribed validation and execution contract for for 91.5% of cases and achieves unit, stream, and directed-connection F1 scores of 0.815, 0.791, and 0.782. These results demonstrate the effectiveness of role specialization, typed intermediate representations, and deterministic engineering gates for reliable automated process-model construction.