29 April 2026 in SSRN Electronic Journal
Oxygen lance control is a critical decision-making task in basic oxygen furnace (BOF) steelmaking. It regulates lance height to control decarburization rate, aiming to achieve stability. Existing approaches either rely on human expertise, requiring long-term training and experience accumulation, or use traditional machine-learning models that simplify the problem into numerical regression, resulting in limited interpretability and adaptability. In this work, we are the first to reformulate oxygen lance control as a structured multimodal generative decision-making task and propose a self-evolving reasoning Multimodal Large Language Model (MLLM) agent that performs structured reasoning. The agent jointly perceives real-time furnace mouth flame videos and historical process data to generate structured decision paths. To address the scarcity of high-quality annotated industrial data, we introduce OT-SERA, an Operation‐Trajectory guided Self‐Evolving Reasoning MLLM Agent for structured decision-making. OT-SERA includes an initialization phase and a refinement phase. In the Operation-Trajectory Guided Reasoning Initialization (OTGRI) phase: operation trajectories from real BOF steelmaking guide the generation of structured chain-of-thoughts (CoTs), which are then used to warm-up the agent by fine-tuning. In the Self-Evolving Reasoning Refinement (SERR) phase: the agent improves reasoning paths through self-evolving updates with path backtracking, automatically constructing high-quality CoTs without additional human annotation. Repeated the SERR further improve CoTs quality, highlighting the effectiveness. Extensive experiments on real-world BOF data show that OT-SERA outperforms strong time series and multimodal baselines under both normal and hard operating conditions. By integrating multimodal perception, OTGRI, and SERR, this work provides an effective solution for intelligent control of complex industrial processes.