Principle-Evolvable Scientific Discovery via Uncertainty Minimization
This addresses computational waste in scientific discovery for researchers using AI agents, though it appears incremental as it builds on existing Bayesian optimization and anomaly-driven methods.
The paper tackles the inefficiency of LLM-based scientific agents caused by fixed initial priors by proposing PiEvo, a principle-evolvable framework that shifts focus from searching hypotheses to evolving underlying scientific principles, achieving up to 93.15% solution quality with a 31.1% improvement over state-of-the-art and an 83.3% speedup in convergence.
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.