PhySense: Principle-Based Physics Reasoning Benchmarking for Large Language Models
This addresses the gap in AI systems for efficient and interpretable scientific reasoning, though it is incremental as it focuses on benchmarking rather than solving the problem directly.
The authors tackled the problem that large language models (LLMs) fail to emulate concise, principle-based reasoning in physics, by introducing PhySense, a benchmark that reveals consistent failures across state-of-the-art LLMs to align with expert-like reasoning paths.
Large language models (LLMs) have rapidly advanced and are increasingly capable of tackling complex scientific problems, including those in physics. Despite this progress, current LLMs often fail to emulate the concise, principle-based reasoning characteristic of human experts, instead generating lengthy and opaque solutions. This discrepancy highlights a crucial gap in their ability to apply core physical principles for efficient and interpretable problem solving. To systematically investigate this limitation, we introduce PhySense, a novel principle-based physics reasoning benchmark designed to be easily solvable by experts using guiding principles, yet deceptively difficult for LLMs without principle-first reasoning. Our evaluation across multiple state-of-the-art LLMs and prompt types reveals a consistent failure to align with expert-like reasoning paths, providing insights for developing AI systems with efficient, robust and interpretable principle-based scientific reasoning.