Democratizing Scientific Intelligence via an Extended-Mind-Inspired Agentic System: Surpassing Frontier Proprietary Models in Scientific Reasoning and Research with Less Data, a Smaller Model, and Low-Cost Training

Scientific intelligence, which requires long-horizon reasoning and research across diverse and highly specialized domains, remains a key challenge for artificial intelligence. Although large language models (LLMs) have achieved strong performance on general tasks, their single-model paradigm faces fundamental limitations in scientific domains, including reduced effectiveness under specialization, high scaling costs with diminishing returns, and insufficient capacity for fine-grained long-horizon tasks. In this paper, we introduce an extended-mind-inspired paradigm, extending intelligence to an agentic system composed of an LLM, interactive objects, and autonomous interaction processes, enabling deep specialization, new scaling dimensions, and stronger representational capacity. Building on this, we introduce ExoMind, the first extended-mind-inspired agentic system, which integrates systematic data engineering, a scientific interaction framework, and a systematic training strategy. Across diverse scientific reasoning and research tasks, our method achieves substantial and consistent performance improvements using less data, a smaller model, and low-cost training. Notably, ExoMind achieves leading performance among frontier open-source and closed-source models on challenging scientific benchmarks (as shown in Fig. 1), while also improving general-purpose capabilities. These results suggest a customizable, cost-efficient, and high-performance pathway toward democratizing scientific intelligence.