Optimized Three-Dimensional Photovoltaic Structures with LLM guided Tree Search

TL;DR

This paper demonstrates how AI coding systems combined with tree search can autonomously generate and optimize three-dimensional photovoltaic structures, overcoming traditional limitations and discovering high-efficiency designs.

Contribution

It introduces a novel workflow integrating AI coding agents with tree search to generate and refine 3D PV structures, addressing reward hacking and optimizing performance.

Findings

AI-driven design yields higher energy densities than flat panels.

Iterative physics constraints eliminate reward hacking in design optimization.

Optimized designs include various configurations with improved diurnal performance.

Abstract

We present a case study for how AI coding systems can be used to generate novel scientific hypotheses. We combine a generic coding agent (Google's AntiGravity) with an LLM-driven tree search algorithm (Empirical Research Assistance / ERA) to autonomously generate high-efficiency three-dimensional photovoltaic (3DPV) structures that overcome losses limiting flat solar panels at mid-latitudes. These structures operate by presenting favorable angles to the sun throughout the day, and for illustrative purposes we focus on optimizing performance for a single solar day. Our workflow begins by using AntiGravity to reproduce calculations \cite{bernardi2012solar} showing that 3DPV can have energy densities much higher than stationary flat PV panels. We use these initial designs as the starting point for large scale tree search, where we seek improved solutions and score them for their diurnal yield. The initial tree search leads to nominally more efficient solutions, yet they are caused by algorithmic reward hacking, arising from non-physical design features such as structurally levitating disconnected tiers and exploitations of the discretizations in the optics solver. To counteract this, we develop a workflow where the coding agent iteratively patches the physics engine with constraints to eliminate reward hacking. With reward-hacking eliminated, ERA discovers a series of designs with various constraints and improved performance, including optimal designs with different fixed collector areas, optimizing zenith tracking and avoiding self shadowing. Combining coding agents with tree search (ERA) provides a powerful platform for scientific discovery, for problems whose solutions can be empirically evaluated with a score function.