Towards LLM-enabled autonomous combustion research: A literature-aware agent for self-corrective modeling workflows

2026-01-04

arXiv.org

AI Summary

This work proposes FlamePilot, the first large language model agent that integrates scientific literature comprehension with self-correcting computational fluid dynamics (CFD) workflows to address the absence of autonomous AI assistants capable of synthesizing domain knowledge and CFD tools in complex scientific domains such as combustion modeling. FlamePilot enables end-to-end autonomous simulation—from parsing research papers to parameter optimization and post-processing—by combining atomic tool invocation, literature-based information extraction, and simulation automation, supporting both OpenFOAM and DeepFlame. On public benchmarks, it achieves an executable score of 1.0 and a success rate of 0.438, substantially outperforming existing approaches. The system successfully demonstrates a fully automated, multi-step parameter convergence study for MILD combustion, establishing a transparent and interpretable paradigm for AI-augmented scientific co-inquiry.

Technology Category

• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Search and Optimization: Sampling/Simulation-based Search
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• Search and Retrieval-Augmented AI: Agentic search
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems

Abstract

The rapid evolution of large language models (LLMs) is transforming artificial intelligence into autonomous research partners, yet a critical gap persists in complex scientific domains such as combustion modeling. Here, practical AI assistance requires the seamless integration of domain literature knowledge with robust execution capabilities for expertise-intensive tools such as computational fluid dynamics (CFD) codes. To bridge this gap, we introduce FlamePilot, an LLM agent designed to empower combustion modeling research through automated and self-corrective CFD workflows. FlamePilot differentiates itself through an architecture that leverages atomic tools to ensure the robust setup and execution of complex simulations in both OpenFOAM and extended frameworks such as DeepFlame. The system is also capable of learning from scientific articles, extracting key information to guide the simulation from initial setup to optimized results. Validation on a public benchmark shows FlamePilot achieved a perfect 1.0 executability score and a 0.438 success rate, surpassing the prior best reported agent scores of 0.625 and 0.250, respectively. Furthermore, a detailed case study on Moderate or Intense Low-oxygen Dilution (MILD) combustion simulation demonstrates its efficacy as a collaborative research copilot, where FlamePilot autonomously translated a research paper into a configured simulation, conducted the simulation, post-processed the results, proposed evidence-based refinements, and managed a multi-step parameter study to convergence under minimal human intervention. By adopting a transparent and interpretable paradigm, FlamePilot establishes a foundational framework for AI-empowered combustion modeling, fostering a collaborative partnership where the agent manages workflow orchestration, freeing the researcher for high-level analysis.

Problem

• combustion modeling
• large language models
• autonomous research
• computational fluid dynamics
• scientific literature integration

Innovation

• LLM agent
• self-corrective modeling
• combustion simulation
• CFD automation
• literature-aware AI