LLM-guided Chemical Process Optimization with a Multi-Agent Approach

2025-06-25

AI Summary

Traditional optimization methods—such as gradient-based approaches, evolutionary algorithms, and grid search—struggle in chemical process optimization when operational constraints are ill-defined, leading to heavy reliance on expert heuristics. Method: This paper proposes a multi-agent large language model (LLM)-based framework for autonomous constraint inference and collaborative optimization. It decouples constraint generation from optimization guidance, leveraging domain-knowledge-enhanced AutoGen agents—including modules for constraint generation, parameter validation, simulation execution, and optimization steering—to enable two-stage iterative optimization without predefined bounds. Results: Applied to a hydrodealkylation case study, the method converges within 20 minutes—31× faster than grid search—with fewer iterations and competitive performance across cost, yield, and cost-per-unit-yield objectives. It significantly reduces dependence on prior constraint knowledge while maintaining solution quality.

Technology Category

• Search and Optimization: Sampling/Simulation-based Search
• Constraint Satisfaction and Optimization: Constraint Optimization
• Machine Learning: Optimization

Application Category

• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Search and Retrieval-Augmented AI: Agentic search
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

Abstract

Chemical process optimization is crucial to maximize production efficiency and economic performance. Traditional methods, including gradient-based solvers, evolutionary algorithms, and parameter grid searches, become impractical when operating constraints are ill-defined or unavailable, requiring engineers to rely on subjective heuristics to estimate feasible parameter ranges. To address this constraint definition bottleneck, we present a multi-agent framework of large language model (LLM) agents that autonomously infer operating constraints from minimal process descriptions, then collaboratively guide optimization using the inferred constraints. Our AutoGen-based agentic framework employs OpenAI's o3 model, with specialized agents for constraint generation, parameter validation, simulation execution, and optimization guidance. Through two phases - autonomous constraint generation using embedded domain knowledge, followed by iterative multi-agent optimization - the framework eliminates the need for predefined operational bounds. Validated on the hydrodealkylation process across cost, yield, and yield-to-cost ratio metrics, the framework demonstrated competitive performance with conventional optimization methods while achieving better computational efficiency, requiring fewer iterations to converge. Our approach converged in under 20 minutes, achieving a 31-fold speedup over grid search. Beyond computational efficiency, the framework's reasoning-guided search demonstrates sophisticated process understanding, correctly identifying utility trade-offs, and applying domain-informed heuristics. This approach shows significant potential for optimization scenarios where operational constraints are poorly characterized or unavailable, particularly for emerging processes and retrofit applications.

Problem

• Autonomously infer chemical process constraints from minimal descriptions
• Optimize production efficiency without predefined operational bounds
• Improve computational efficiency and convergence in process optimization

Innovation

• LLM agents autonomously infer operating constraints
• Multi-agent framework guides optimization collaboratively
• Embedded domain knowledge enables constraint-free optimization