NovelSeek：当智能体化身科学家——构建从假设到验证的闭环系统

摘要

人工智能（AI）正在加速推动科学研究范式的变革，不仅提升了研究效率，还促进了创新突破。我们推出了NovelSeek，这是一个统一的闭环多智能体框架，旨在跨多个科学研究领域开展自主科学研究（ASR），使研究人员能够以前所未有的速度和精度解决这些领域中的复杂问题。NovelSeek凸显了三大关键优势：1）可扩展性：NovelSeek已在12项科学研究任务中展现了其广泛适用性，能够生成创新思路以提升基线代码的性能。2）交互性：NovelSeek在自动化端到端流程中提供了人机专家反馈与多智能体交互的接口，实现了领域专家知识的无缝融合。3）高效性：与人类努力相比，NovelSeek在多个科学领域以显著减少的时间成本取得了令人瞩目的性能提升。例如，在反应产率预测中，仅用12小时就从27.6%提升至35.4%；在增强子活性预测中，仅处理4小时，准确率就从0.52提升至0.79；在二维语义分割中，仅30小时，精度就从78.8%提升至81.0%。

English

Artificial Intelligence (AI) is accelerating the transformation of scientific research paradigms, not only enhancing research efficiency but also driving innovation. We introduce NovelSeek, a unified closed-loop multi-agent framework to conduct Autonomous Scientific Research (ASR) across various scientific research fields, enabling researchers to tackle complicated problems in these fields with unprecedented speed and precision. NovelSeek highlights three key advantages: 1) Scalability: NovelSeek has demonstrated its versatility across 12 scientific research tasks, capable of generating innovative ideas to enhance the performance of baseline code. 2) Interactivity: NovelSeek provides an interface for human expert feedback and multi-agent interaction in automated end-to-end processes, allowing for the seamless integration of domain expert knowledge. 3) Efficiency: NovelSeek has achieved promising performance gains in several scientific fields with significantly less time cost compared to human efforts. For instance, in reaction yield prediction, it increased from 27.6% to 35.4% in just 12 hours; in enhancer activity prediction, accuracy rose from 0.52 to 0.79 with only 4 hours of processing; and in 2D semantic segmentation, precision advanced from 78.8% to 81.0% in a mere 30 hours.

NovelSeek：当智能体化身科学家——构建从假设到验证的闭环系统

NovelSeek: When Agent Becomes the Scientist -- Building Closed-Loop System from Hypothesis to Verification

摘要

Summary

Support

Support