X-Intelligence 3.0: Training and Evaluating Reasoning LLM for Semiconductor Display

TL;DR

X-Intelligence 3.0 is a domain-specific reasoning LLM for the semiconductor display industry, trained with industry knowledge and evaluation frameworks, outperforming larger models in specialized tasks.

Contribution

The paper introduces X-Intelligence 3.0, a high-performance reasoning model tailored for the semiconductor display industry, with domain-specific training and evaluation methods.

Findings

Outperforms larger models like DeepSeek-R1-671B on industry benchmarks.

Uses a domain-specific retrieval-augmented generation mechanism.

Achieves expert-level reasoning with only 32 billion parameters.

Abstract

Large language models (LLMs) have recently achieved significant advances in reasoning and demonstrated their advantages in solving challenging problems. Yet, their effectiveness in the semiconductor display industry remains limited due to a lack of domain-specific training and expertise. To bridge this gap, we present X-Intelligence 3.0, the first high-performance reasoning model specifically developed for the semiconductor display industry. This model is designed to deliver expert-level understanding and reasoning for the industry's complex challenges. Leveraging a carefully curated industry knowledge base, the model undergoes supervised fine-tuning and reinforcement learning to enhance its reasoning and comprehension capabilities. To further accelerate development, we implemented an automated evaluation framework that simulates expert-level assessments. We also integrated a domain-specific retrieval-augmented generation (RAG) mechanism, resulting in notable performance gains on benchmark datasets. Despite its relatively compact size of 32 billion parameters, X-Intelligence 3.0 outperforms SOTA DeepSeek-R1-671B across multiple evaluations. This demonstrates its exceptional efficiency and establishes it as a powerful solution to the longstanding reasoning challenges faced by the semiconductor display industry.