通过不确定性最小化实现原理可演化的科学发现
Principle-Evolvable Scientific Discovery via Uncertainty Minimization
AI总结:
提出PiEvo框架,将科学发现视为原理空间上的贝叶斯优化,通过信息导向假设选择与异常驱动增强机制,使智能体自主演化理论世界观,在四个基准上平均解质量达90.81%~93.15%,收敛速度提升83.3%。
摘要:
基于大型语言模型的科学智能体加速了科学发现,但由于固守初始先验,常常效率低下。现有方法主要在静态假设空间中操作,限制了新现象的发现,当基线理论失效时导致计算浪费。为解决此问题,我们提出将焦点从搜索假设转向演化底层科学原理。我们提出PiEvo,一个原理可演化框架,将科学发现视为在扩展原理空间上的贝叶斯优化。通过集成基于高斯过程的信息导向假设选择和异常驱动增强机制,PiEvo使智能体能够自主完善其理论世界观。在四个基准上的评估表明,PiEvo (1) 平均解质量高达90.81%~93.15%,比现有最优方法提升29.7%~31.1%;(2) 通过优化紧凑原理空间显著降低样本复杂度,收敛步骤加速83.3%;(3) 在不同科学领域和LLM骨干上保持稳健性能。代码公开于\hyperlink{https://github.com/amair-lab/PiEvo}{github.com/amair-lab/PiEvo}。
英文摘要:
Large Language Model (LLM)-based scientific agents have accelerated scientific discovery, yet they often suffer from significant inefficiencies due to adherence to fixed initial priors. Existing approaches predominantly operate within a static hypothesis space, which restricts the discovery of novel phenomena, resulting in computational waste when baseline theories fail. To address this, we propose shifting the focus from searching hypotheses to evolving the underlying scientific principles. We present PiEvo, a principle-evolvable framework that treats scientific discovery as Bayesian optimization over an expanding principle space. By integrating Information-Directed Hypothesis Selection via Gaussian Process and an anomaly-driven augmentation mechanism, PiEvo enables agents to autonomously refine their theoretical worldview. Evaluation across four benchmarks demonstrates that PiEvo (1) achieves an average solution quality of up to 90.81%~93.15%, representing a 29.7%~31.1% improvement over the state-of-the-art, (2) attains an 83.3% speedup in convergence step via significantly reduced sample complexity by optimizing the compact principle space, and (3) maintains robust performance across diverse scientific domains and LLM backbones. Code is publicly available at \hyperlink{https://github.com/amair-lab/PiEvo}{github.com/amair-lab/PiEvo}.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。