FeynmanBench: Benchmarking Multimodal LLMs on Diagrammatic Physics Reasoning
This provides a physics-grounded benchmark for AI in theoretical physics, addressing a gap in evaluating multistep diagrammatic reasoning, though it is incremental as it focuses on a specific domain.
The authors tackled the problem of evaluating multimodal large language models (MLLMs) on diagrammatic physics reasoning by introducing FeynmanBench, a benchmark with over 2000 tasks across the Standard Model, and found that state-of-the-art MLLMs exhibit systematic failures in enforcing physical constraints and global topology.
Breakthroughs in frontier theory often depend on the combination of concrete diagrammatic notations with rigorous logic. While multimodal large language models (MLLMs) show promise in general scientific tasks, current benchmarks often focus on local information extraction rather than the global structural logic inherent in formal scientific notations. In this work, we introduce FeynmanBench, the first benchmark centered on Feynman diagram tasks. It is designed to evaluate AI's capacity for multistep diagrammatic reasoning, which requires satisfying conservation laws and symmetry constraints, identifying graph topology, converting between diagrammatic and algebraic representations, and constructing scattering amplitudes under specific conventions and gauges. To support large-scale and reproducible evaluation, we developed an automated pipeline producing diverse Feynman diagrams along with verifiable topological annotations and amplitude results. Our database spans the electromagnetic, weak, and strong interactions of the Standard Model, encompasses over 100 distinct types and includes more than 2000 tasks. Experiments on state-of-the-art MLLMs reveal systematic failure modes, including unstable enforcement of physical constraints and violations of global topological conditions, highlighting the need for physics-grounded benchmarks for visual reasoning over scientific notation. FeynmanBench provides a logically rigorous test of whether AI can effectively engage in scientific discovery, particularly within theoretical physics.