Retrieval-Augmented Instruction Tuning for Automated Process Engineering Calculations : A Tool-Chaining Problem-Solving Framework with Attributable Reflection

TL;DR

This paper presents a retrieval-augmented instruction-tuning framework for small code language models to autonomously solve process engineering calculations, improving explainability and cost-effectiveness.

Contribution

It introduces a novel autonomous agent framework combining instruction tuning and retrieval-augmented code generation for process engineering tasks.

Findings

Framework matches large proprietary models on benchmarks

Curated datasets improve model training for engineering problems

Enhanced explainability and knowledge editing capabilities

Abstract

The current technology landscape lacks a foundational AI model for solving process engineering calculations. In this work, we introduce a novel autonomous agent framework leveraging Retrieval-Augmented Instruction-Tuning (RAIT) to enhance open, customizable small code language models (SLMs) for these calculations. By combining instruction tuned code SLMs with Retrieval-Augmented Code Generation (RACG) using external tools, the agent generates, debugs, and optimizes code from natural language specifications. Our approach addresses the limitations of the current lack of a foundational AI model for specialized process engineering tasks and offers benefits of explainability, knowledge editing, and cost-effectiveness. Additionally, we curate custom datasets of chemical and process engineering problems and solutions to overcome data scarcity. Experimental results show that our framework matches the performance of large-scale proprietary models on benchmark datasets, proving its effectiveness and usability.