The field of artificial intelligence is witnessing a significant shift towards developing domain-specific superintelligence, with a focus on creating models that can acquire and compose domain primitives to achieve expertise. This is being pursued through various approaches, including the use of knowledge graphs, hierarchical multi-agent frameworks, and specialized large language models. These models are being applied to a range of domains, including medicine, materials science, and semiconductor display, with notable successes in achieving state-of-the-art performance and demonstrating the potential for significant advances in these fields. Noteworthy papers include Bottom-up Domain-specific Superintelligence, which presents a task generation pipeline for acquiring domain-specific expertise, and DREAMS, which introduces a hierarchical multi-agent framework for materials simulation. Other notable papers include X-Intelligence 3.0, Expert-Guided LLM Reasoning for Battery Discovery, Perovskite-R1, Improving LLMs' Generalized Reasoning Abilities by Graph Problems, Reasoning-Driven Retrosynthesis Prediction with Large Language Models via Reinforcement Learning, Can One Domain Help Others?, and CodeReasoner.
Domain-Specific Superintelligence and Reasoning Advances
Sources
Bottom-up Domain-specific Superintelligence: A Reliable Knowledge Graph is What We Need
DREAMS: Density Functional Theory Based Research Engine for Agentic Materials Simulation
X-Intelligence 3.0: Training and Evaluating Reasoning LLM for Semiconductor Display
Expert-Guided LLM Reasoning for Battery Discovery: From AI-Driven Hypothesis to Synthesis and Characterization
Perovskite-R1: A Domain-Specialized LLM for Intelligent Discovery of Precursor Additives and Experimental Design
Improving LLMs' Generalized Reasoning Abilities by Graph Problems
Reasoning-Driven Retrosynthesis Prediction with Large Language Models via Reinforcement Learning
Can One Domain Help Others? A Data-Centric Study on Multi-Domain Reasoning via Reinforcement Learning
CodeReasoner: Enhancing the Code Reasoning Ability with Reinforcement Learning